Table of Content
Introduction.....................................................................................................2
Sampling and generalisability...........................................................................3
Non-response and weighting.............................................................................5
Anseel et al. (2010): what explains response rates in organisational science.....................6
Scale development and assessment, incl. validity and reliability.........................8
Data quality and reproducibility of results.......................................................10
Interpretation of statistical analyses from survey research, incl. moderation and
mediation......................................................................................................10
Hulland et al. (2018): Current best practices in survey research in marketing.................11
Specific issues in survey research in a cross-cultural context: (1) equivalence, (2)
translation issues, (3) measurement invariance...............................................13
, Introduction
Survey: systematic method for gathering information from a sample of entities for
the purpose of constructing quantitative descriptors of attributes of a larger
population of which the entities are members
It is hypothesis generating and testing
Focuses on external validity (generalizable)
Medium to high generalisability
Medium to large representativeness of the large population
Elements of an academic survey
Measurement Instrument (items):
One dependent variable
Several independent variables
Covariates
Measured with validated multi-item scales
Sample:
Sample representative of the target population
Sample large enough to enable the appropriate statistical methods
Seven classification criteria
1. Who: the target population
2. What: the topic
3. Whom: survey agency and sponsor
o Response rate higher for government than commercial agency
o Government uses probability sampling
o Commercial agencies use non-probability sampling
4. How: survey mode (interview or self-completion)
5. When
o Cross-sectional design (data collected once)
o Longitudinal design
Repeated-cross sectional survey (different sample each time)
Fixed-sample panel design (same sample each time at regular
time intervals)
Cohort study (same people over longer period of time)
Rotating panel design: new panel member participate in fixed
number of waves, overlapping samples
6. Where: regional, national, cross-national, international
o If you stratify per region, then both regional and national statistics can
be published
o Cross-national: independent sample drawn from each country and later
combined
7. Why: fit for purpose
o Trade-off between accuracy, speed and cost
Four functions of survey research
1. Knowledge: predict and understand human behaviour
2. Product development and improvement
3. Influence: decision makers, public
4. Entertainment
Introduction.....................................................................................................2
Sampling and generalisability...........................................................................3
Non-response and weighting.............................................................................5
Anseel et al. (2010): what explains response rates in organisational science.....................6
Scale development and assessment, incl. validity and reliability.........................8
Data quality and reproducibility of results.......................................................10
Interpretation of statistical analyses from survey research, incl. moderation and
mediation......................................................................................................10
Hulland et al. (2018): Current best practices in survey research in marketing.................11
Specific issues in survey research in a cross-cultural context: (1) equivalence, (2)
translation issues, (3) measurement invariance...............................................13
, Introduction
Survey: systematic method for gathering information from a sample of entities for
the purpose of constructing quantitative descriptors of attributes of a larger
population of which the entities are members
It is hypothesis generating and testing
Focuses on external validity (generalizable)
Medium to high generalisability
Medium to large representativeness of the large population
Elements of an academic survey
Measurement Instrument (items):
One dependent variable
Several independent variables
Covariates
Measured with validated multi-item scales
Sample:
Sample representative of the target population
Sample large enough to enable the appropriate statistical methods
Seven classification criteria
1. Who: the target population
2. What: the topic
3. Whom: survey agency and sponsor
o Response rate higher for government than commercial agency
o Government uses probability sampling
o Commercial agencies use non-probability sampling
4. How: survey mode (interview or self-completion)
5. When
o Cross-sectional design (data collected once)
o Longitudinal design
Repeated-cross sectional survey (different sample each time)
Fixed-sample panel design (same sample each time at regular
time intervals)
Cohort study (same people over longer period of time)
Rotating panel design: new panel member participate in fixed
number of waves, overlapping samples
6. Where: regional, national, cross-national, international
o If you stratify per region, then both regional and national statistics can
be published
o Cross-national: independent sample drawn from each country and later
combined
7. Why: fit for purpose
o Trade-off between accuracy, speed and cost
Four functions of survey research
1. Knowledge: predict and understand human behaviour
2. Product development and improvement
3. Influence: decision makers, public
4. Entertainment
