Lecture 1:
Good survey:
- Good processed data before analysis
- Questions = items
- Likert scale, always from positive to negative or the other way around, same
length
- Code Book
- Keeping track of how you coded, collected and analysed data
- Clear goal to know what should be included/excluded
- Guiding respondents
- Pushing them towards and answer
- Length!
- Too long, people quit mid way
- How difficult are the questions
- 5- 10 min
- Depending on the respondents, are they willing to spend more time?
- Attention check
- Who?
- Do they fit your goal and target group?
Social desirability: response behaviour based on how you want to be perceived.
If we know that everyone will have the same answer, the question is useless, you want to have
variety to gain insights
Experiment vs Survey
Experiment Survey
2 conditions- manipulation No manipulation
Causality No causality
Narrow Broad
Specific More general
What is a survey?
A survey is a systematic method for gathering information with standardized questionnaires from
(a sample of) entities for the purpose of constructing quantitative descriptors of the attributes of
the larger population of which the entities are members. (Groves et al. 2009)
A survey is a structured way of collecting information from a group of people using the same
set of questions to understand characteristics of a larger population.
Systematic and Standardized
- Distinguishes itself from other techniques such as qualitative research
- Systematic- the survey follows a structured process, consistent, clear interpretation
- Standardized- every participant receives the same set of questions in the same format
and order. Uniform response options- reduces variation caused by different
interpretations
1
,(A Sample of) Entities
- Mostly a selection of the population is included in the survey
- All entities can be included as well (e.g., employee survey)
Quantitative Descriptors
- Statistics needed to analyze the responses
Surveys are roughly 100 years old
Sampling procedure
- Can't ask the whole population but only a part - the sample
Probability sampling
Selection of sampling techniques in which the chance of each case
(e.g., individual) being selected from the population is known and not
zero.
→ Randomization is used instead of deliberate choice
European Social Survey with a sampling frame and exact data on
background of all individuals in the sample
Nonprobability sampling
Selection of sampling techniques in which the chance of each case (e.g., individual) being
selected is NOT known.
→ The researcher deliberately picks the sample
- Non probability, you can’t conclude what you found in your sample to be true for the
whole population
Time horizon of survey research
Cross-Sectional Design
- Opinion polls (e.g., to predict electoral results)
- Typical thesis survey (e.g., to understand consumer
preferences or attitudes)
Longitudinal Design
- Repeated cross-sectional (different sample each time)
- Fixed-sample panel design (the same sample each
time)
- Cohort study (follow the same people over a longer
period of time, usually after an event;
Administration Methods of Survey Research:
Interview surveys: personal or telephone surveys
Self- Completion Surveys: Written Surveys or Online surveys
2
,Why is the Research Survey so popular?
Structure to follow
3
, The role of Surveys in Research
What is Survey data good for?
Key Takeaways:
- A survey is a systematic method for gathering information
- With standardised questionnaires
- From (a sample of ) entities and individuals
- For the purpose of constructing qualitative descriptors
- Of the attributes of the larger population of which the entities are members
4
Good survey:
- Good processed data before analysis
- Questions = items
- Likert scale, always from positive to negative or the other way around, same
length
- Code Book
- Keeping track of how you coded, collected and analysed data
- Clear goal to know what should be included/excluded
- Guiding respondents
- Pushing them towards and answer
- Length!
- Too long, people quit mid way
- How difficult are the questions
- 5- 10 min
- Depending on the respondents, are they willing to spend more time?
- Attention check
- Who?
- Do they fit your goal and target group?
Social desirability: response behaviour based on how you want to be perceived.
If we know that everyone will have the same answer, the question is useless, you want to have
variety to gain insights
Experiment vs Survey
Experiment Survey
2 conditions- manipulation No manipulation
Causality No causality
Narrow Broad
Specific More general
What is a survey?
A survey is a systematic method for gathering information with standardized questionnaires from
(a sample of) entities for the purpose of constructing quantitative descriptors of the attributes of
the larger population of which the entities are members. (Groves et al. 2009)
A survey is a structured way of collecting information from a group of people using the same
set of questions to understand characteristics of a larger population.
Systematic and Standardized
- Distinguishes itself from other techniques such as qualitative research
- Systematic- the survey follows a structured process, consistent, clear interpretation
- Standardized- every participant receives the same set of questions in the same format
and order. Uniform response options- reduces variation caused by different
interpretations
1
,(A Sample of) Entities
- Mostly a selection of the population is included in the survey
- All entities can be included as well (e.g., employee survey)
Quantitative Descriptors
- Statistics needed to analyze the responses
Surveys are roughly 100 years old
Sampling procedure
- Can't ask the whole population but only a part - the sample
Probability sampling
Selection of sampling techniques in which the chance of each case
(e.g., individual) being selected from the population is known and not
zero.
→ Randomization is used instead of deliberate choice
European Social Survey with a sampling frame and exact data on
background of all individuals in the sample
Nonprobability sampling
Selection of sampling techniques in which the chance of each case (e.g., individual) being
selected is NOT known.
→ The researcher deliberately picks the sample
- Non probability, you can’t conclude what you found in your sample to be true for the
whole population
Time horizon of survey research
Cross-Sectional Design
- Opinion polls (e.g., to predict electoral results)
- Typical thesis survey (e.g., to understand consumer
preferences or attitudes)
Longitudinal Design
- Repeated cross-sectional (different sample each time)
- Fixed-sample panel design (the same sample each
time)
- Cohort study (follow the same people over a longer
period of time, usually after an event;
Administration Methods of Survey Research:
Interview surveys: personal or telephone surveys
Self- Completion Surveys: Written Surveys or Online surveys
2
,Why is the Research Survey so popular?
Structure to follow
3
, The role of Surveys in Research
What is Survey data good for?
Key Takeaways:
- A survey is a systematic method for gathering information
- With standardised questionnaires
- From (a sample of ) entities and individuals
- For the purpose of constructing qualitative descriptors
- Of the attributes of the larger population of which the entities are members
4
