inferringincomeriskfromeconomicchoices · 2014. 5. 17. · inferringincomeriskfromeconomicchoices:...
TRANSCRIPT
![Page 1: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/1.jpg)
Inferring Income Risk from Economic Choices:An Indirect Inference Approach
Fatih Guvenen Anthony Smith
Minnesota and NBER Yale University
July 29, 2009
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 1 / 42
![Page 2: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/2.jpg)
Goals of this Paper:
1 Substantive Question:I To shed light on the nature of labor income risk...
I by exploiting the information contained in the joint dynamics ofhouseholds’ labor earnings and consumption choice decisions.
2 Methodology:I To better understand how “indirect inference” can be used to extract
information from individuals’ economic choices.
Main substantive conclusion: Typical calibrations of incompletemarkets models significantly overstate uninsurable income risk.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 2 / 42
![Page 3: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/3.jpg)
Goals of this Paper:
1 Substantive Question:I To shed light on the nature of labor income risk...
I by exploiting the information contained in the joint dynamics ofhouseholds’ labor earnings and consumption choice decisions.
2 Methodology:I To better understand how “indirect inference” can be used to extract
information from individuals’ economic choices.
Main substantive conclusion: Typical calibrations of incompletemarkets models significantly overstate uninsurable income risk.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 2 / 42
![Page 4: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/4.jpg)
Goals of this Paper:
1 Substantive Question:I To shed light on the nature of labor income risk...
I by exploiting the information contained in the joint dynamics ofhouseholds’ labor earnings and consumption choice decisions.
2 Methodology:I To better understand how “indirect inference” can be used to extract
information from individuals’ economic choices.
Main substantive conclusion: Typical calibrations of incompletemarkets models significantly overstate uninsurable income risk.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 2 / 42
![Page 5: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/5.jpg)
A Stochastic Process for Labor Income
y it : log labor earnings of household i at age t.
y it =
[a0 +a1t +a2t2 +a3Educ + ...
]︸ ︷︷ ︸common life-cycle component
+[α
i + βi t]︸ ︷︷ ︸
profile heterogeneity
+[z it + ε
it]︸ ︷︷ ︸
stochastic component
where z it = ρz i
t−1 + η it , and η i
t ,εit ∼ iid
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 3 / 42
![Page 6: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/6.jpg)
A Stochastic Process for Labor Income
y it : log labor earnings of household i at age t.
y it =
[a0 +a1t +a2t2 +a3Educ + ...
]︸ ︷︷ ︸common life-cycle component
+[α
i + βi t]︸ ︷︷ ︸
profile heterogeneity
+[z it + ε
it]︸ ︷︷ ︸
stochastic component
where z it = ρz i
t−1 + η it , and η i
t ,εit ∼ iid
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 3 / 42
![Page 7: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/7.jpg)
A Stochastic Process for Labor Income
y it : log labor earnings of household i at age t.
y it =
[a0 +a1t +a2t2 +a3Educ + ...
]︸ ︷︷ ︸common life-cycle component
+[α
i + βi t]︸ ︷︷ ︸
profile heterogeneity
+[z it + ε
it]︸ ︷︷ ︸
stochastic component
where z it = ρz i
t−1 + η it , and η i
t ,εit ∼ iid
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 3 / 42
![Page 8: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/8.jpg)
A Stochastic Process for Labor Income
y it : log labor earnings of household i at age t.
y it =
[a0 +a1t +a2t2 +a3Educ + ...
]︸ ︷︷ ︸common life-cycle component
+[α
i + βi t]︸ ︷︷ ︸
profile heterogeneity
+[z it + ε
it]︸ ︷︷ ︸
stochastic component
where z it = ρz i
t−1 + η it , and η i
t ,εit ∼ iid
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 3 / 42
![Page 9: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/9.jpg)
Three Questions about Labor Income Risk
1 How persistent and how large are income shocks? i.e., what is ρ andσ2
η ?
2 Do individuals differ systematically in their income growth rates? i.e.,is σ2
β� 0?
3 If indeed σ2β� 0, how much do individuals know about their β i at
different points in their life-cycle?
I i.e., what fraction of heterogeneity in β i is uncertainty as opposed toknown heterogeneity?
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 4 / 42
![Page 10: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/10.jpg)
Three Questions about Labor Income Risk
1 How persistent and how large are income shocks? i.e., what is ρ andσ2
η ?
2 Do individuals differ systematically in their income growth rates? i.e.,is σ2
β� 0?
3 If indeed σ2β� 0, how much do individuals know about their β i at
different points in their life-cycle?
I i.e., what fraction of heterogeneity in β i is uncertainty as opposed toknown heterogeneity?
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 4 / 42
![Page 11: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/11.jpg)
Three Questions about Labor Income Risk
1 How persistent and how large are income shocks? i.e., what is ρ andσ2
η ?
2 Do individuals differ systematically in their income growth rates? i.e.,is σ2
β� 0?
3 If indeed σ2β� 0, how much do individuals know about their β i at
different points in their life-cycle?
I i.e., what fraction of heterogeneity in β i is uncertainty as opposed toknown heterogeneity?
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 4 / 42
![Page 12: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/12.jpg)
Three Questions about Labor Income Risk
1 How persistent and how large are income shocks? i.e., what is ρ andσ2
η ?
2 Do individuals differ systematically in their income growth rates? i.e.,is σ2
β� 0?
3 If indeed σ2β� 0, how much do individuals know about their β i at
different points in their life-cycle?
I i.e., what fraction of heterogeneity in β i is uncertainty as opposed toknown heterogeneity?
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 4 / 42
![Page 13: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/13.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 14: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/14.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 15: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/15.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 16: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/16.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 17: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/17.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 18: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/18.jpg)
Outline of the Talk
1 Brief review of existing evidence on labor income risk
2 A life-cycle model of consumption-savings choice
3 Indirect Inference methodology
4 Identification with Consumption Data
5 Results (Monte Carlos and Real data)
6 Conclusions and future agenda
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 5 / 42
![Page 19: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/19.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 20: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/20.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 21: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/21.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 22: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/22.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 23: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/23.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 24: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/24.jpg)
Existing Evidence from Labor Income Data
1 HIP Process (“Heterogenous Income Profiles”):I Early studies estimated the full model and found:
σ2β� 0 and 0.5≤ ρ ≤0.8
I See Hause (1977), Lillard and Weiss (1979), Baker (1997), Haider (2001),Guvenen (2005)
2 RIP Process (“Restricted Income Profiles”):
I MaCurdy (1982) suggested a test for β i≡ 0 and could not reject it.
I Then he and the following literature:F imposed β i≡ 0 and estimated 0.95≤ ρ ≤ 1.0.
I See Abowd and Card (1989), Topel (1991), Moffitt and Gottschalk (1995),Hubbard, Skinner and Zeldes (1994), Storesletten et al. (2004), etc.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 6 / 42
![Page 25: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/25.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 26: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/26.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 27: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/27.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 28: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/28.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 29: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/29.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 30: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/30.jpg)
This Paper
Studies the joint dynamics of consumption and labor income to learn moreabout labor income risk.
Two Difficulties
First, GMM requires strong assumptions.
I “Indirect inference” circumvents many of these difficulties.
Second, long US panel on consumption does not exist.
I We construct a panel of imputed consumption (1968-1992) bycombining CEX and PSID.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 7 / 42
![Page 31: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/31.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 32: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/32.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 33: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/33.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 34: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/34.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 35: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/35.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 36: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/36.jpg)
The Model
Households work for R years. Spend S years in retirement.
Only choice is consumption-savings (inelastic labor supply).
CRRA utility function
Households face the unrestricted labor income process above.
A risk-free asset: Borrowing subject to potentially binding borrowingconstraints.
After retirement: Pension system mimicking the U.S. Social Securitysystem.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 8 / 42
![Page 37: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/37.jpg)
Information Structure
Recall: y it = α i + β i t + z i
t + ε it
At t = 0, each individual observes a signal about her own β i .
In each t > 0, individuals observe (α i ,y it ,ε
it) but must learn about(
β i ,z it).
Individuals use the Kalman filter to update their beliefs about(β i ,z i
t)
as new observatios on labor income arrive.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 9 / 42
![Page 38: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/38.jpg)
Information Structure
Recall: y it = α i + β i t + z i
t + ε it
At t = 0, each individual observes a signal about her own β i .
In each t > 0, individuals observe (α i ,y it ,ε
it) but must learn about(
β i ,z it).
Individuals use the Kalman filter to update their beliefs about(β i ,z i
t)
as new observatios on labor income arrive.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 9 / 42
![Page 39: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/39.jpg)
Information Structure
Recall: y it = α i + β i t + z i
t + ε it
At t = 0, each individual observes a signal about her own β i .
In each t > 0, individuals observe (α i ,y it ,ε
it) but must learn about(
β i ,z it).
Individuals use the Kalman filter to update their beliefs about(β i ,z i
t)
as new observatios on labor income arrive.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 9 / 42
![Page 40: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/40.jpg)
Information Structure
Recall: y it = α i + β i t + z i
t + ε it
At t = 0, each individual observes a signal about her own β i .
In each t > 0, individuals observe (α i ,y it ,ε
it) but must learn about(
β i ,z it).
Individuals use the Kalman filter to update their beliefs about(β i ,z i
t)
as new observatios on labor income arrive.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 9 / 42
![Page 41: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/41.jpg)
Prior and Posterior Beliefs
Priors: Bivariate Normal distribution with mean (β i1|0, z
i1|0) and
covariance matrix P1|0 =
[σ2
β ,0 00 σ2
z ,0
]Express the prior standard deviation as: σβ ,0 = λσβ . Then:
If λ = 0 → σβ ,0 = 0 and β i1|0 = β i (No prior uncertainty)
If λ = 1 → σβ ,0 = σβ and β i1|0 = β (Full prior uncertainty)
For realistic parameter values learning about β i is very slow (Guvenen2007).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 10 / 42
![Page 42: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/42.jpg)
Prior and Posterior Beliefs
Priors: Bivariate Normal distribution with mean (β i1|0, z
i1|0) and
covariance matrix P1|0 =
[σ2
β ,0 00 σ2
z ,0
]Express the prior standard deviation as: σβ ,0 = λσβ . Then:
If λ = 0 → σβ ,0 = 0 and β i1|0 = β i (No prior uncertainty)
If λ = 1 → σβ ,0 = σβ and β i1|0 = β (Full prior uncertainty)
For realistic parameter values learning about β i is very slow (Guvenen2007).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 10 / 42
![Page 43: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/43.jpg)
Prior and Posterior Beliefs
Priors: Bivariate Normal distribution with mean (β i1|0, z
i1|0) and
covariance matrix P1|0 =
[σ2
β ,0 00 σ2
z ,0
]Express the prior standard deviation as: σβ ,0 = λσβ . Then:
If λ = 0 → σβ ,0 = 0 and β i1|0 = β i (No prior uncertainty)
If λ = 1 → σβ ,0 = σβ and β i1|0 = β (Full prior uncertainty)
For realistic parameter values learning about β i is very slow (Guvenen2007).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 10 / 42
![Page 44: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/44.jpg)
Prior and Posterior Beliefs
Priors: Bivariate Normal distribution with mean (β i1|0, z
i1|0) and
covariance matrix P1|0 =
[σ2
β ,0 00 σ2
z ,0
]Express the prior standard deviation as: σβ ,0 = λσβ . Then:
If λ = 0 → σβ ,0 = 0 and β i1|0 = β i (No prior uncertainty)
If λ = 1 → σβ ,0 = σβ and β i1|0 = β (Full prior uncertainty)
For realistic parameter values learning about β i is very slow (Guvenen2007).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 10 / 42
![Page 45: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/45.jpg)
Prior and Posterior Beliefs
Priors: Bivariate Normal distribution with mean (β i1|0, z
i1|0) and
covariance matrix P1|0 =
[σ2
β ,0 00 σ2
z ,0
]Express the prior standard deviation as: σβ ,0 = λσβ . Then:
If λ = 0 → σβ ,0 = 0 and β i1|0 = β i (No prior uncertainty)
If λ = 1 → σβ ,0 = σβ and β i1|0 = β (Full prior uncertainty)
For realistic parameter values learning about β i is very slow (Guvenen2007).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 10 / 42
![Page 46: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/46.jpg)
Dynamic Programming Problem
Worker (t = 1, ..,R−1)
Vt(ωt , βt , zt) = maxCt ,at+1
{U(Ct) + δEt
[Vt+1(ωt+1, βt+1, zt+1)
]}s.t. (1)
Ct +at+1 = ωt (2)ωt = (1+ r)at +Yt (3)
at+1 ≥ a,and Kalman recursions
Retiree (t = R, ..,T )
Vt(ωt ,Y ) = maxCt ,at+1
[U(Ct) + δVt+1(ωt+1,Y )] (4)
s.t Y = Φ(YR) , and eq.(2,3)
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 11 / 42
![Page 47: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/47.jpg)
Dynamic Programming Problem
Worker (t = 1, ..,R−1)
Vt(ωt , βt , zt) = maxCt ,at+1
{U(Ct) + δEt
[Vt+1(ωt+1, βt+1, zt+1)
]}s.t. (1)
Ct +at+1 = ωt (2)ωt = (1+ r)at +Yt (3)
at+1 ≥ a,and Kalman recursions
Retiree (t = R, ..,T )
Vt(ωt ,Y ) = maxCt ,at+1
[U(Ct) + δVt+1(ωt+1,Y )] (4)
s.t Y = Φ(YR) , and eq.(2,3)
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 11 / 42
![Page 48: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/48.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 49: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/49.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 50: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/50.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 51: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/51.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 52: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/52.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 53: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/53.jpg)
Estimation via Indirect Inference
Hallmark of indirect inference: Think in terms of an auxiliary modelthat can be viewed as a reduced form of the structural model.
Specifically, pick an auxiliary model that is:I easy to estimate
I rich enough to provide a good descriptive statistical model of the data.
Mimicking structural equations works well.
Thinking in terms of dynamic relationships often lead to someconditional moment conditions that are not straightforward to seeotherwise.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 12 / 42
![Page 54: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/54.jpg)
Why Indirect Inference?
The standard method since Hall and Mishkin (1982) is to derive structuralequations explicitly and estimate them.
For example, with (i) quadratic utility, (ii) no borrowing constraint,(iii) no retirement, and (iv) persistent plus transitory shocks, we have:
∆Ct = φtηt + ψtεt
φ � 0, ψt ∼ 0
Suppose εt ≡ 0:
∆Ct = φtηt = φt∆Yt
Response of consumption growth to income growth reveals persistenceof income shocks.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 13 / 42
![Page 55: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/55.jpg)
Why Indirect Inference?
The standard method since Hall and Mishkin (1982) is to derive structuralequations explicitly and estimate them.
For example, with (i) quadratic utility, (ii) no borrowing constraint,(iii) no retirement, and (iv) persistent plus transitory shocks, we have:
∆Ct = φtηt + ψtεt
φ � 0, ψt ∼ 0
Suppose εt ≡ 0:
∆Ct = φtηt = φt∆Yt
Response of consumption growth to income growth reveals persistenceof income shocks.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 13 / 42
![Page 56: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/56.jpg)
Why Indirect Inference?
The standard method since Hall and Mishkin (1982) is to derive structuralequations explicitly and estimate them.
For example, with (i) quadratic utility, (ii) no borrowing constraint,(iii) no retirement, and (iv) persistent plus transitory shocks, we have:
∆Ct = φtηt + ψtεt
φ � 0, ψt ∼ 0
Suppose εt ≡ 0:
∆Ct = φtηt = φt∆Yt
Response of consumption growth to income growth reveals persistenceof income shocks.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 13 / 42
![Page 57: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/57.jpg)
Why Indirect Inference?
The standard method since Hall and Mishkin (1982) is to derive structuralequations explicitly and estimate them.
For example, with (i) quadratic utility, (ii) no borrowing constraint,(iii) no retirement, and (iv) persistent plus transitory shocks, we have:
∆Ct = φtηt + ψtεt
φ � 0, ψt ∼ 0
Suppose εt ≡ 0:
∆Ct = φtηt = φt∆Yt
Response of consumption growth to income growth reveals persistenceof income shocks.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 13 / 42
![Page 58: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/58.jpg)
An Example
0 5 10 15 20 25 30 35 40−1
0
1
2
3
4
5
Age
Labor Income Consumption
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 14 / 42
![Page 59: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/59.jpg)
An Example: Binding Constraints
0 5 10 15 20 25 30 35 40−1
0
1
2
3
4
5
Age
Labor Income ConsumptionAssets
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 15 / 42
![Page 60: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/60.jpg)
IDENTIFICATION
![Page 61: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/61.jpg)
Identification
Simplifying assumptions for intuition:(i) quadratic utility, (ii) no borrowing constraints, (iii) εt ≡ 0, and (iv)yt : level of income.
1 Optimal consumption choice:
HIP: ∆Ct = Πt ×(y it −(
αi + β
it−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξ it
2 If σ2β≡ 0, learning disappears → we get (certainty equivalent)
permanent income model:
RIP: ∆Ct = Ψt ×ηt
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 17 / 42
![Page 62: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/62.jpg)
Identification
Simplifying assumptions for intuition:(i) quadratic utility, (ii) no borrowing constraints, (iii) εt ≡ 0, and (iv)yt : level of income.
1 Optimal consumption choice:
HIP: ∆Ct = Πt ×(y it −(
αi + β
it−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξ it
2 If σ2β≡ 0, learning disappears → we get (certainty equivalent)
permanent income model:
RIP: ∆Ct = Ψt ×ηt
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 17 / 42
![Page 63: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/63.jpg)
Identification
Simplifying assumptions for intuition:(i) quadratic utility, (ii) no borrowing constraints, (iii) εt ≡ 0, and (iv)yt : level of income.
1 Optimal consumption choice:
HIP: ∆Ct = Πt ×(y it −(
αi + β
it−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξ it
2 If σ2β≡ 0, learning disappears → we get (certainty equivalent)
permanent income model:
RIP: ∆Ct = Ψt ×ηt
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 17 / 42
![Page 64: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/64.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 65: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/65.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
RIP:
∆C1=∆C2
} η>0
}η>0
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 66: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/66.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
η>0}
} η>0
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 67: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/67.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
}
}
}ξ1<0
η>0
η=ξ2>0
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 68: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/68.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
HIP: ∆C1<0 ∆C2>0
}
} η>0
ξ1<0
η=ξ2>0}
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 69: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/69.jpg)
1. Identification from Consumption Changes
1 2 3 4 5 6 7 8
0.5
1
1.5
2
2.5
3
3.5
Age
Lab
or E
arni
ngs
RIP: ∆C1=∆C
2>0
HIP: ∆C1<0, ∆C
2>0
} η=ξ2>0
}
} ξ1<0
η>0
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 18 / 42
![Page 70: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/70.jpg)
2. Identification from Consumption Levels
1 2 3 4 5 6 7 8 9 10
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
Age
Lab
or E
arni
ngs
Agent 1: Actual IncomeAgent 2: Actual Income
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 19 / 42
![Page 71: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/71.jpg)
2. Identification from Consumption Levels
1 2 3 4 5 6 7 8 9 10
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
Age
Lab
or E
arni
ngs
Agent 1: Actual IncomeAgent 2: Actual Income
Forecast Income Paths under RIP
RIP:
Ct=31 =Y
t=3=C
t=32
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 19 / 42
![Page 72: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/72.jpg)
2. Identification from Consumption Levels
1 2 3 4 5 6 7 8 9 10
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
Age
Lab
or E
arni
ngs
Agent 1: Actual IncomeAgent 2: Actual Income
Forecast Income Paths under RIP
HIP:
Ct=31 >C
t=32
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 19 / 42
![Page 73: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/73.jpg)
2. Identification from Consumption Levels
1 2 3 4 5 6 7 8 9 10
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
Age
Lab
or E
arni
ngs
Agent 1: Actual IncomeAgent 2: Actual Income
Forecast Income Paths under HIP
HIP:
Ct=31 >C
t=32
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 19 / 42
![Page 74: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/74.jpg)
Determining the Prior Information in HIP
1 2 3 4 5 6 7 8 9 10
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
Age
Lab
or E
arni
ngs
Forecast Income Paths under HIP with λ=1
Forecast Income underHIP with λ<1
If λ=1: Ct=31 =C
t=32
If λ<1: Ct=31 >C
t=32
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 20 / 42
![Page 75: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/75.jpg)
A Feasible Auxiliary Model:
∆Ct = Πt ×(Y i
t −(
α + βit−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξt
(5)
This regression is not feasible, so approximate with
ct = a0 +a1yt−1 +a2yt−2 +a3yt+1 +a4yt+2
+a5y1,t−3 +a6y t+3,T +a7∆y1,t−3 +a8∆y t+3,T
+a9ct−1 +a10ct−2 +a11ct+1 +a12ct+2 + error
where ct ≡ log (Ct) .
Add a second regression where yt is the dependent variable. Use thesame income regressors above.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 21 / 42
![Page 76: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/76.jpg)
A Feasible Auxiliary Model:
∆Ct = Πt ×(Y i
t −(
α + βit−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξt
(5)
This regression is not feasible, so approximate with
ct = a0 +a1yt−1 +a2yt−2 +a3yt+1 +a4yt+2
+a5y1,t−3 +a6y t+3,T +a7∆y1,t−3 +a8∆y t+3,T
+a9ct−1 +a10ct−2 +a11ct+1 +a12ct+2 + error
where ct ≡ log (Ct) .
Add a second regression where yt is the dependent variable. Use thesame income regressors above.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 21 / 42
![Page 77: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/77.jpg)
A Feasible Auxiliary Model:
∆Ct = Πt ×(Y i
t −(
α + βit−1t + ρ z i
t−1
))︸ ︷︷ ︸
ξt
(5)
This regression is not feasible, so approximate with
ct = a0 +a1yt−1 +a2yt−2 +a3yt+1 +a4yt+2
+a5y1,t−3 +a6y t+3,T +a7∆y1,t−3 +a8∆y t+3,T
+a9ct−1 +a10ct−2 +a11ct+1 +a12ct+2 + error
where ct ≡ log (Ct) .
Add a second regression where yt is the dependent variable. Use thesame income regressors above.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 21 / 42
![Page 78: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/78.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 79: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/79.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 80: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/80.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 81: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/81.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 82: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/82.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 83: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/83.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 84: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/84.jpg)
Monte Carlo Results
RRA = 2
Annual net interest rate is: r = 4%
T = 41, S = 15. Social security system mimicking the U.S.
Use the observed structure of missing data.
2200 individuals with approximately 12 observations per individual.
Starting values assigned randomly 20% away from truth.
Each run takes approximately 3 hours.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 22 / 42
![Page 85: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/85.jpg)
Monte Carlo Results
True value Mean estimate Std. dev.ρ 0.670 0.669 0.034ση 0.190 0.191 0.009σε 0.150 0.150 0.015σβ (×100) 2.650 2.652 0.121σα 0.490 0.493 0.031λ 0.500 0.504 0.054σuy 0.200 0.199 0.003σuc 0.200 0.199 0.008Note: Statistics are based on 150 replications
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 23 / 42
![Page 86: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/86.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 87: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/87.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 88: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/88.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 89: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/89.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 90: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/90.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 91: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/91.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 92: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/92.jpg)
Results
PSID data, 1968-1993.
Labor income data: household non-financial after tax income(adjusted for family size and demographics)
Consumption data: imputed (adjusted for family size anddemographics)
Measurement error:I yobs
t = yt +uyt , uy
t is i.i.d over time.
I cobst = ct +mc +uc
t , mc is an individual fixed effect, uct is i.i.d over
time.
Also estimate δ , γ (RRA coefficient), and a (borrowing constraint).
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 24 / 42
![Page 93: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/93.jpg)
Estimation of the Full Model
Parameter Estimate Std Error Descriptionρ 0.756 0.029 Persistenceση 0.189 0.005 Std. dev. of perm. shockσε 0.019 0.027 Std. dev. of transit. shockσβ (×100) 1.785 0.392 Growth rate heterogeneityσα 0.383 0.029 Level heterogeneitycorαβ −0.178 0.074 Correlationλ 0.191 0.124 Prior uncertaintyσuy 0.145 0.010 IID meas. error in incomeσuc 0.355 0.002 IID meas. error in cons.σuc 0.434 0.009 Fixed meas. error in cons.δ 0.958 0.003 Time discount factorγ 2.0* — RRA coefficienta -0.25* — Borrowing limit
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 25 / 42
![Page 94: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/94.jpg)
Estimation of the Full Model
Parameter Estimate Std Error Descriptionρ 0.756 0.029 Persistenceση 0.189 0.005 Std. dev. of perm. shockσε 0.019 0.027 Std. dev. of transit. shockσβ (×100) 1.785 0.392 Growth rate heterogeneityσα 0.383 0.029 Level heterogeneitycorαβ −0.178 0.074 Correlationλ 0.191 0.124 Prior uncertaintyσuy 0.145 0.010 IID meas. error in incomeσuc 0.355 0.002 IID meas. error in cons.σuc 0.434 0.009 Fixed meas. error in cons.δ 0.958 0.003 Time discount factorγ 2.0* — RRA coefficienta -0.25* — Borrowing limit
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 25 / 42
![Page 95: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/95.jpg)
Estimation of the Full Model
Parameter Estimate Std Error Descriptionρ 0.756 0.029 Persistenceση 0.189 0.005 Std. dev. of perm. shockσε 0.019 0.027 Std. dev. of transit. shockσβ (×100) 1.785 0.392 Growth rate heterogeneityσα 0.383 0.029 Level heterogeneitycorαβ −0.178 0.074 Correlationλ 0.191 0.124 Prior uncertaintyσuy 0.145 0.010 IID meas. error in incomeσuc 0.355 0.002 IID meas. error in cons.σuc 0.434 0.009 Fixed meas. error in cons.δ 0.958 0.003 Time discount factorγ 2.0* — RRA coefficienta -0.25* — Borrowing limit
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 25 / 42
![Page 96: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/96.jpg)
Estimation of the Full Model
Parameter Estimate Std Error Descriptionρ 0.756 0.029 Persistenceση 0.189 0.005 Std. dev. of perm. shockσε 0.019 0.027 Std. dev. of transit. shockσβ (×100) 1.785 0.392 Growth rate heterogeneityσα 0.383 0.029 Level heterogeneitycorαβ −0.178 0.074 Correlationλ 0.191 0.124 Prior uncertaintyσuy 0.145 0.010 IID meas. error in incomeσuc 0.355 0.002 IID meas. error in cons.σuc 0.434 0.009 Fixed meas. error in cons.δ 0.958 0.003 Time discount factorγ 2.0* — RRA coefficienta -0.25* — Borrowing limit
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 25 / 42
![Page 97: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/97.jpg)
Estimation of the Full Model
Parameter Estimate Std Error Descriptionρ 0.756 0.029 Persistenceση 0.189 0.005 Std. dev. of perm. shockσε 0.019 0.027 Std. dev. of transit. shockσβ (×100) 1.785 0.392 Growth rate heterogeneityσα 0.383 0.029 Level heterogeneitycorαβ −0.178 0.074 Correlationλ 0.191 0.124 Prior uncertaintyσuy 0.145 0.010 IID meas. error in incomeσuc 0.355 0.002 IID meas. error in cons.σuc 0.434 0.009 Fixed meas. error in cons.δ 0.958 0.003 Time discount factorγ 2.0* — RRA coefficienta -0.25* — Borrowing limit
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 25 / 42
![Page 98: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/98.jpg)
Quantifying Life Cycle Income Risk
30 35 40 45 50 55 60
0.1
0.3
0.5
0.7
0.9
Age
With
in−
Coh
ort V
aria
nce
of L
og In
com
e
Var(log(Income))US Data
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 26 / 42
![Page 99: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/99.jpg)
Quantifying Life Cycle Income Risk
30 35 40 45 50 55 60
0.1
0.3
0.5
0.7
0.9
Age
With
in−
Coh
ort V
aria
nce
of L
og In
com
e
Var(log(Income))Estimated Model
Var(log(Income))US Data
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 26 / 42
![Page 100: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/100.jpg)
Quantifying Life Cycle Income Risk
30 35 40 45 50 55 60
0.1
0.3
0.5
0.7
0.9
Age
With
in−
Coh
ort V
aria
nce
of L
og In
com
e
Forecast Variance(This paper)
Var(log(Income))Estimated Model
Var(log(Income))US Data
Conclusion 1: About 1/2 of cross-sectional income dispersion at retirementrepresents risk—the rest is known heterogeneity.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 26 / 42
![Page 101: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/101.jpg)
Quantifying Life Cycle Income Risk
30 35 40 45 50 55 60
0.1
0.3
0.5
0.7
0.9
Age
With
in−
Coh
ort V
aria
nce
of L
og In
com
e
Forecast Variance(This paper)
Var(log(Income))Estimated Model
Var(log(Income))US Data
Forecast Variance(Existing Literature)
Conclusion 2: Typical estimates in the literature overstate labor income risksignificantly.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 26 / 42
![Page 102: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/102.jpg)
Within-Cohort Evolution of Inequality
25 30 35 40 45 50 55 600.1
0.2
0.3
0.4
0.5
0.6
Age
With
in−
Coh
ort V
aria
nce
of L
og In
com
e an
d C
onsu
mpt
ion
(Mod
el N
orm
aliz
ed to
Mat
ch U
S D
ata
at a
ge 3
0)
Var(log(Income)), US Data
Var(log(Income)), Model
Var(log(Consumption)), Model
Var(log(Consumption)), US Data
Var(log(Consumption)), US Data, Smoothed
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 27 / 42
![Page 103: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/103.jpg)
Life Cycle Profile of Consumption
25 30 35 40 45 50 55 60 650.8
0.85
0.9
0.95
1
1.05
1.1
1.15
1.2
1.25
Age
Mea
n L
og C
onsu
mpt
ion
Prof
ile (
Nor
mal
ized
to 1
at A
ge 3
0)
US DataUS Data, SmoothedModel
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 28 / 42
![Page 104: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/104.jpg)
Conclusions and Future Directions
Monte Carlo results suggest that the indirect inference method worksvery well.
Estimates indicate
I (a) modest persistence of shocks, (b) large heterogeneity in incomegrowth rates, and (c) significant information about future incomegrowth rate (from 75 to 90% of total variance).
Implies: Typical calibrations of incomplete markets modelssubstantially overstate uninsurable income risk.
Next steps: (a) time-varying shock variances, (b) partial insurance.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 29 / 42
![Page 105: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/105.jpg)
Conclusions and Future Directions
Monte Carlo results suggest that the indirect inference method worksvery well.
Estimates indicate
I (a) modest persistence of shocks, (b) large heterogeneity in incomegrowth rates, and (c) significant information about future incomegrowth rate (from 75 to 90% of total variance).
Implies: Typical calibrations of incomplete markets modelssubstantially overstate uninsurable income risk.
Next steps: (a) time-varying shock variances, (b) partial insurance.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 29 / 42
![Page 106: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/106.jpg)
Conclusions and Future Directions
Monte Carlo results suggest that the indirect inference method worksvery well.
Estimates indicate
I (a) modest persistence of shocks, (b) large heterogeneity in incomegrowth rates, and (c) significant information about future incomegrowth rate (from 75 to 90% of total variance).
Implies: Typical calibrations of incomplete markets modelssubstantially overstate uninsurable income risk.
Next steps: (a) time-varying shock variances, (b) partial insurance.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 29 / 42
![Page 107: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/107.jpg)
Conclusions and Future Directions
Monte Carlo results suggest that the indirect inference method worksvery well.
Estimates indicate
I (a) modest persistence of shocks, (b) large heterogeneity in incomegrowth rates, and (c) significant information about future incomegrowth rate (from 75 to 90% of total variance).
Implies: Typical calibrations of incomplete markets modelssubstantially overstate uninsurable income risk.
Next steps: (a) time-varying shock variances, (b) partial insurance.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 29 / 42
![Page 108: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/108.jpg)
Conclusions and Future Directions
Monte Carlo results suggest that the indirect inference method worksvery well.
Estimates indicate
I (a) modest persistence of shocks, (b) large heterogeneity in incomegrowth rates, and (c) significant information about future incomegrowth rate (from 75 to 90% of total variance).
Implies: Typical calibrations of incomplete markets modelssubstantially overstate uninsurable income risk.
Next steps: (a) time-varying shock variances, (b) partial insurance.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 29 / 42
![Page 109: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/109.jpg)
Imputation of Consumption in PSID
PSID tracks food consumption only. CEX measures non-durableexpenditures but its panel structure is very limited.
Blundell, et al (2006) develop a structural procedure to imputeconsumption in PSID (1980-1992).
We modify and extend this methodology to construct a panel ofconsumption for PSID covering 1968-1992.
In particular, we also make use of CEX 1972-73 and use additionalregressors.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 30 / 42
![Page 110: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/110.jpg)
Imputation of Consumption in PSID
PSID tracks food consumption only. CEX measures non-durableexpenditures but its panel structure is very limited.
Blundell, et al (2006) develop a structural procedure to imputeconsumption in PSID (1980-1992).
We modify and extend this methodology to construct a panel ofconsumption for PSID covering 1968-1992.
In particular, we also make use of CEX 1972-73 and use additionalregressors.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 30 / 42
![Page 111: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/111.jpg)
Imputation of Consumption in PSID
PSID tracks food consumption only. CEX measures non-durableexpenditures but its panel structure is very limited.
Blundell, et al (2006) develop a structural procedure to imputeconsumption in PSID (1980-1992).
We modify and extend this methodology to construct a panel ofconsumption for PSID covering 1968-1992.
In particular, we also make use of CEX 1972-73 and use additionalregressors.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 30 / 42
![Page 112: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/112.jpg)
Imputation of Consumption in PSID
PSID tracks food consumption only. CEX measures non-durableexpenditures but its panel structure is very limited.
Blundell, et al (2006) develop a structural procedure to imputeconsumption in PSID (1980-1992).
We modify and extend this methodology to construct a panel ofconsumption for PSID covering 1968-1992.
In particular, we also make use of CEX 1972-73 and use additionalregressors.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 30 / 42
![Page 113: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/113.jpg)
Imputation of Consumption in PSID Results
1965 1970 1975 1980 1985 1990 1995−0.08
−0.06
−0.04
−0.02
0
0.02
0.04
0.06
0.08
0.1
Year
Cro
ss−
Sec
tiona
l Var
ianc
e of
Cos
umpt
ion
(Dev
iatio
n fr
om 1
980)
PSID Imputed: 1968−1992CE Non−Durable Consumption: 1980−92
CE Non−Durable, Kernel Smoothed
PSID Imputed, Kernel Smoothed
PSID Food Expenditures
PSID Food, Kernel Smoothed
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 31 / 42
![Page 114: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/114.jpg)
Imputation of Consumption in PSID Results
25 30 35 40 45 50 55 60 65−0.06
−0.04
−0.02
0
0.02
0.04
0.06
0.08
0.1
Age
(With
in−
Coh
ort)
Cro
ss−
Sec
tiona
l Var
ianc
e of
Log
Con
sum
ptio
n
PSID Imputed ConsumptionCE Non−Durable Consumption
CE Kernel Smoothed
PSID Kernel Smoothed
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 32 / 42
![Page 115: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/115.jpg)
Imputation of Consumption in PSID Results
25 30 35 40 45 50 55 60 650.8
0.85
0.9
0.95
1
1.05
1.1
1.15
1.2
1.25
Age
Ave
rage
Non
−D
urab
le C
onsu
mpt
ion
(Nor
mal
ized
to 1
at A
ge 3
0)
PSID Imputed ConsumptionCE Non−Durable ConsumptionCE Kernel SmoothedPSID Kernel Smoothed
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 33 / 42
![Page 116: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/116.jpg)
Imputation of Consumption in PSID Results
Imputed=.996*Actual+.277+error
R squared=.67
68
1012
Impu
ted
6 8 10 12Actual
Regression Line 45 degree line
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 34 / 42
![Page 117: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/117.jpg)
Ignoring profile heterogeneity biases ρ upward
yhit − yh
it =(
αi + β
ih+ εhit
)−(
αi + βh
)=(
βi −β
)h+ ε
hit
Under the (incorrect) assumption that β i ≡ β , a consistent estimatorof ρ is:
ρ =h (h−1)σ2
β
(h−1)2σ2β
+ σ2ε
−→ 1 for large h
If σ2β
= 0.0004, and σ2ε = 0.03, h = 20, yields ρ = 0.87.
If h = 30 ⇒ ρ = 0.95, when in fact true persistence is zero.If there is a population of individuals uniformly distributed from 25 to65 years of age, ρ = 0.91
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 35 / 42
![Page 118: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/118.jpg)
A comparison to the existing literature
Body Math: MaCurdy (1982) rejected HIP by testing a simple proposition:If individuals differ systematically in the slope of their income profiles thenincome growth rates should be positively autocorrelated at higher lags.
cov(∆yhi ,∆yh+k
i ) = σ2β−[
ρk−1(1−ρ
1+ ρ
)σ2η
], k = 2, ...
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 36 / 42
![Page 119: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/119.jpg)
Two concerns about the test:1 Low power against the alternative of HIP (even without AR(1) income
shocks):cov(∆yh
i ,∆yh+ki ) = σ
2β
= .00038≈ 0
2 With AR(1) income shocks:
cov(∆yhi ,∆yh+k
i ) = .00038−[.0033∗0.82k−1
]< 0,
for k < 12
⇒ Even with HIP autocovariances should be slightly negative andalways close to zero.
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 37 / 42
![Page 120: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/120.jpg)
Group ρ σ2α σ2
βcorrαβ σ2
η σ2ε
A .988 .058 — — .015 .061(.024) (.011) (.007) (.010)
A .821 .022 .00038 −.23 .029 .047(.030) (.074) (.00008) (.43) (.008) (.007)
C .979 .031 — — .0099 .047(.055) (.021) (.013) (.020)
C .805 .023 .00049 −.70 .025 .032(.061) (.112) (.00014) (1.22) (.015) (.017)
H .972 .053 — — .011 .052(.023) (.015) (.007) (.008)
H .829 .038 .00020 −.25 .022 .034(.029) (.081) (.00009) (.59) (.008) (.007)
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 38 / 42
![Page 121: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/121.jpg)
LagSample 0 1 2 3 4 5
Autocovariance(1) Data .0476 −.0176 .00058 −.00166 −.00014 −.00067
(.0019) (.0014) (.0008) (.0007) (.0008) (.0007)(2) Data .1215 −.0385 −.0031 −.0023 −.0025 −.00004
(.0023) (.0011) (.0010) (.0008) (.0007) (.0008)(3) Model .0840 −.0329 −.0014 −.0011 −.0007 −.0007
(.0013) (.0010) (.0008) (.0009) (.0008) (.0007)
Autocorrelation(4) Data 1.00 −.394 .013 −.039 −.003 −.016(5) Data 1.00 −.317 −.026 −.019 −.021 −.001(6) Model 1.00 −.391 −.016 −.012 −.009 −.009
(.000) (.008) (.009) (.010) (.008) (.009)
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 39 / 42
![Page 122: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/122.jpg)
Imputation of Consumption in PSID: Results
25 30 35 40 45 50 55 60 650.85
0.9
0.95
1
1.05
1.1
1.15
1.2
1.25
1.3
1.35
Age
Ave
rage
Lab
or In
com
e
CEX all years (before−tax)PSID (before−tax)CEX drop<80PSID (After−tax)
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 40 / 42
![Page 123: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/123.jpg)
Imputation of Consumption in PSID: Results
30 35 40 45 50 55 60 65−0.1
0
0.1
0.2
0.3
0.4
0.5
0.6
Age
(With
in−
Coh
ort)
Cro
ss−
sect
iona
l Var
ianc
e of
Log
Inco
me
PSID (before−tax income)PSID (after−tax income)CEX all yearsCEX drop<80
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 41 / 42
![Page 124: InferringIncomeRiskfromEconomicChoices · 2014. 5. 17. · InferringIncomeRiskfromEconomicChoices: AnIndirectInferenceApproach FatihGuvenen AnthonySmith MinnesotaandNBER YaleUniversity](https://reader034.vdocuments.net/reader034/viewer/2022052007/601c0181edc69e334e3c4c19/html5/thumbnails/124.jpg)
Change in Precision of Beliefs about β i
Missing in the file
Guvenen and Smith (2009) Inferring Income Risk from Choices July 29, 2009 42 / 42