Statistical Package for the Social Sciences (SPSS)

IBM SPSS Statistics 19.0

Yupaporn Siribut

Objectives

to provides some training in the use of a powerful software package to relieve students of computational drudgery

to help you understand the concepts and techniques of statistical analysis

to provide practice exercises on SPSS

The research process

MINZAS ??

Contents

1

2

3

4

Session I: Introduction

The usefulness of SPSS/ PASW

What we need to prepare?

Introduction to descriptive statistics

Exploring data by Graphs

Contents

1

2

3

4

Session II: Practice exercises

Doing basic statistics on SPSS

Doing regression on SPSS

Interpreting the result

Cont.

An Overview

Statistical Package for the Social Sciences (SPSS) software, since 2009 known as Predictive Analysis Software (PASW)

Statistical software used by commercial, government, and academic organizations around the world to solve business and research problems

Session I:

An Overview

Quickly and easily discover new insights from data, test hypotheses, and build powerful predictive models

Even if you have little or no statistical or mathematical background, PASW Statistics will show you how to generate statistical support and decision-making information quickly and easily

Session I:Cont.

Usefulness of SPSS

SPSS/ PASW provide followings; Descriptive statistics (Mean, Median, Mode, Standard

deviation, Range) Discrete probability distributions (Binomial, Poisson,

Geometric, Hyper geometric) Continuous probability distributions (Normal, T, Chi

Square, F) Correlation (Rank correlation, Pearson’s correlation) Linear regression (Simple and Multiple linear

regression) Logistic regression Market research

Session I:

Applied research

• Factors influencing the adoption of OVF ---Logistic Regression

• Factors influencing the extent of OVF by individual farm households---

Linear Regression

Session I:

Applied research

t-tests for individual measures assessed attitudinal differences between participants and non-participants of each group

Session I:

Applied research

Simple linear regression model can be designed to analyze factors influencing adoption of land management

Session I:

How the output of SPSS presents?Session I:

How the output of SPSS presents?Session I:

How the output of SPSS presents?

Figure 1 Daily calories intake (kcal/capita/day) compared with MDER (1,850 Kcal) across lowland, upland and highland ecosystems.

Session I:

How the output of SPSS presents?Session I:

The research processSession I:

What we need to prepare?Session I:

1.Preparing a codebook

Preparing the codebook involves deciding about; defining and labeling each of the variables assigning numbers to each of the possible responses

Session I:

1.Preparing a codebookSession I:

1.Preparing a codebook

1.Preparing a codebook Output

2.Creating a data file

To prepare a data file, three key steps are covered in; Step 1. The first step is to check and modify,

where necessary, the options that SPSS uses to display the data and the output that is produced

Step 2. The next step is to set up the structure of the data file by ‘defining’ the variables

Session I:

2.Creating a data file

Step 3. The final step is to enter the data that is, the values obtained from each participant or respondent for each variable “ Data entry”

Session I:

3.Data entrySession I:

A First Look at SPSS Statistics 19

If you start up SPSS for the first time, it presents a screen similar to Fig 2

Fig 2

Session I:

Let everyone take look at program….

Data editor for entering dataSession I:

3.1 What to measure?

---Things to think about before entering data---

Session I:

a) Independent and dependent variables Independent --- Predictor variable Dependent variables--- outcome variable

Variables

3.1What to measure? Session I:

Cont.

Things to think about before entering data Cont.

3.1What to measure?

b) Levels of measurementThe relationship between what is being

measured and the numbers that represent what is being measured is known as the level of measurement.

Variables can be split into categorical and continuous, and within these types there are different levels of measurement

VariablesSession I:

Things to think about before entering data Cont.

3.1What to measure?

Categorical (entities are divided into distinct categories): Binary variable: There are only two categories (e.g.

dead or alive) Nominal variable: There are more than two categories

(e.g. whether someone is an omnivore, vegetarian, vegan, or fruitarian)

Ordinal variable: The same as a nominal variable but the categories have a logical order

(e.g. whether people got a fail, a pass, a merit or a distinction in their exam)

Things to think about before entering data Cont.

Session I:Variables

3.1What to measure?

Continuous (entities get a distinct score):Interval variable: Equal intervals on the variable

represent equal differences in the property being measured (e.g. the difference between 6 and 8 is equivalent to the difference between 13 and 15)

Ratio variable: The same as an interval variable, but the ratios of scores on the scale must also make sense (e.g. a score of 16 on an anxiety scale means that the person is, in reality, twice as anxious as someone scoring 8)

Things to think about before entering data Cont.

Session I:Variables

Time to Break !!! ^__^

Session I:

4. Screen for errors

Common sources of error are: missing data coded as “999” 'not applicable' or 'blank' coded as “0” typing errors on data entry Column shift “made up” coding errors measurement and interview error

Session I:

Detection

Most errors will be detected using three procedures: Descriptive statistics (exp. Standard deviation higher than

the mean value)

Scatter plot Histograms

SPSS output – Scatter plot

SPSS output - Histogram

Detection

HistogramLook at the tails of the distribution. Are there

data points sitting on their own, out on the extremes?

If so, these are potential outliers. If the scores drop away in a reasonably even slope, there is probably not too much to worry about.

Session I:3. Screen for errors

Correction

There are slightly different ways to deal with error in DEPENDENT and INDEPENDENT variables.

Dependent Variables• When there are a minimal number of errors, the

values are generally recoded to "missing".• Take a look then recoding a variable

Independent variables• set the error values to the data set mean or the

group mean

5. Exploring Data

a) Descriptive statistics describe the characteristics of your sample in

the method section of your report check your variables for any violation of the

assumptions underlying the statistical techniques that you will use to address your

research questions address specific research questions

Descriptive statistics

The differences types of descriptive statistics (Mooi and Sarstedt , 2011)

Descriptive statisticsSession I:

Frequency Command The Frequency command allows you to

analyses a full range of descriptive statistics including the measures of central tendency, percentile values, dispersion and distribution

Frequency Command

SPSS output

Time to have a Lunch !!!

^__^

Session I:

5.Exploring Data

Statistical tests t-test, ANOVA, correlation

Session I:

Correlation

Pearson correlation or Spearman correlation is used when you want to explore the strength of the relationship between two continuous variables.

This gives you an indication of both the direction (positive or negative) and the strength of the relationship.

Correlation

Example of research question: Is there a relationship between the amount of

control people have over their internal states and their levels of perceived stress? Do people with high levels of perceived control experience lower levels of perceived stress?

Total perceived stress: tpstress, Total PCOISS: tpcoiss

Correlation

Interpretation

In the example given here, the Pearson correlation coefficient (–.58) is negative, indicating a negative correlation between perceived control and stress.

The more control people feel they have, the less stress they experience.

Interpretation

Pearson correlation is .581, which when squared indicates 33.76 per cent shared variance.

Perceived control helps to explain nearly 34 per cent of the variance in respondents’ scores on the Perceived Stress Scale

Interpretation

The results of the above example using Pearson correlation could be presented in a research report as follows.

t-test

T-tests are used when you have only two groups (e.g. males/females) or two time points (e.g. pre-intervention, post-intervention)

The rationale of the t test is to test for significant differences in the means of two samples, therefore choose Compare Means

t-test

2 types of its; Independent-samples t-test, used when you

want to compare the mean scores of two different groups of people or conditions

paired-samples t-test, used when you want to compare the mean scores for the same group of people on two different occasions, or when you have matched pairs.

t-test

Example of research question: Is there a significant difference in the mean

self-esteem scores for males and females?What you need: Two variables:

one categorical, independent variable (e.g. males/females)

one continuous, dependent variable (e.g. self-esteem scores)

SPSS out put

t-test

Are the N values for males and females correct?If your Sig. value for Levene’s test is larger

than .05 (e.g. .07, .10) you should use the first line in the table, which refers to Equal variances assumed.

If the significance level of Levene’s test is p=.05 or less (e.g. .01, .001), this means that the variances for the two groups (males/females) are not the same.

Therefore your data violate the assumption of equal variance.

ANOVA

One way ANOVAExample of research question: What is

the impact of age and gender on optimism?

Does gender moderate the relationship between age and optimism?

Contents

Session II: Practice exercises1

Doing basic statistics on SPSS2

Doing regression on SPSS3

Interpreting the result4

Practice exercises

Part 1: Getting started

Practice exercises

Part 2: Preparing the data file

Practice exercises

Part 3: Preliminary analyses

References

Carver, R. H., & Nash, J. G. (2011). Doing data analysis with SPSS version 18.0. Boston, MA: Brooks/Cole Cengage Learning.

Mooi, E., & Sarstedt, M. (2011). A concise guide to market research: The process, data, and methods using IBM SPSS statistics. Berlin: Springer.

Pallant, J. (2010). SPSS survival manual. Maidenhead: McGraw Hill.