quantitative research presentation (1)
TRANSCRIPT
Participants, Biases, Statistical Rationale and Use of Theory
Quantitative Methods
DVIV Survey Design
Experimental
DesignIV
IV
Moderator
DV
DV
Mediator
Self-concept
Self-efficacySelf-confidenceSelf-conscious
Self-esteem
Measurement of perceived self-schemas
1 5
2
Survey and Experimental Designs
Quantitative Methods
[S] Survey Design•Generalized results from a sample to the general population•Economic procedure: Efficient yet effective technique•Survey can be either cross-sectional or longitudinal to control for temporal effects•Survey distribution via mail, internet, phone•Sampling can be random, convenient or stratified
Experimental Design•A causal variable, the independent variable (IV), is manipulated•Control group present to compare effects•Takes place in a lab•Variables are controlled systematically to reduce errors•Higher internal validity
[E]
3Validity in Survey DesignReport on validity of instruments established in past literature
Co
nten
t V
alid
ity
Co
nc
urre
nt
Va
lidity
Co
nst
ruc
t V
alid
ity
Co
nve
rge
nt
Va
lidity
Disc
rimin
an
t V
alid
ity
Instrument items represent the completeness of a construct
Ñ
Results concur or correspond with respondent’s existing characteristic to predict a criterion
Instrument measures exclusively a construct it intends to measure
Measures of various instruments correlate to represent a construct
Measures of an instrument negatively correlate or do not relate with each other to represent a construct
F M 18-25 26-30
When using already developed surveys, obtain permission from the developers first.
4Statistical ValuesPower, statistical significance level and effect size
Descriptive AnalysisIndicate the means, standard deviations, and range of scores
Set the values before the study
Power 80%
Significance Level 95%
Effect Size 50%
ScaleCategorical
F M 18-25 26-30
ContinuousVery strong Very weak
Alpha (α) level, Effect size, power
Determining Sample Size
5
6Non-respondent biasNon-respondents would have answered differently
• Compare respondents and non-respondents traits
• Contact non-respondents to see how they answer
i q
a
1 Infomedia Social Media Be Creative Be Selfi
7
Response Biasesand the strategies to counteract them
Acquiescence bias
Tendency to agree or select ‘yes’/conforming answers
Demand characteristics
Responses or behaviors adjusted to the purpose of the research
Extreme responding
Tendency to choose continuously either extreme or neutral answers
Social desirability bias
Tendency to adopt a socially desirable behavior
8Experimental MethodsParticipants, materials, procedures and measures
ParticipantsIndicate how participants were recruited
aRandom
Non-random
True Experiment
Quasi-experiment
• Match participants
Materials
Procedures Measures
RandomTrue Experiment
Performance
Intervention Effectiveness
Information Processing
Organizational Success
Learning effects
9Variables in Experimental DesignNeed to be specified before the experiment
r s q E a c
Control Variable
Variable held constant
Mediator Variable
Explains the intervening
process between IV and DV
Manipulated or Controlled Variable
Independent Variable (IV)
Measured Variable
Dependent Variable (DV)
Confounding Variable
Moderator Variable
Moderates the strength and direction of a relationship
Interacting variable that is not measured
IV DV
10Experimental Design: Notation SystemQuasi and True Experimental Design Notations
Group A
Non-random Quasi-experimental
Group B
R
Group B
Group AObservation Post-test
Observation Pre-test
ObservationPre-test
ObservationPost-test
R
Random True experimental
Observation Pre-test
Observation Pre-test
Observation Post-test
Observation Post-test
11
Discussion Question
Experimenter’s Dilemma:
Discuss the trade-off between internal and external (ecological) validity.
Which is more important? Explain.
Internal validity= highly controlled setting, artificialbut strong results
but
Specificity of the study lowers external/ecological validity or generalizability
12
References
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Curabitur elementum posuere pretium. Quisque nibh dolor, dignissim ac dignissim ut, luctus ac urna. Aliquam aliquet non massa quis tincidunt. Mauris ullamcorper justo tristique dui posuere
tincidunt. In nec lacus laoreet orci varius imperdiet sit amet in augue.
Creswell, J. W. (2014). Research Design: Qualitative, Quantitative and Mixed Methods Approaches (4th ed.). Thousand Oaks, CA: Sage Publications, Inc.
Leary, M. (2012). Introduction to Behavioral Research Methods (6th ed.). Boston, MA: Pearson Education, Inc.
Thanks for Coming