Survey Research

1
SurveyResearch

• Passer Chapter 7

• Slides Prepared by Alison L. OMalley

2
Surveys An Introduction

• Surveys rely on interviews and questionnaires to
  gather info about people
• What is the last survey you took?

Take Our Survey!
3
Populations and Samples

• Operationally defined by
  sampling frame

Population
Sample
Representative or biased?
Whats the difference between representative and
nonrepresentative samples?
4
Surveys Can we trust the data?

• Participants responses may be distorted by
  social desirability bias, or perhaps theyre
  misremembering
• Response Truth ?
• Fret not. High quality survey research is doable!
  

5
Selecting the Sample

• Probability sampling
• Every member of the population has chance of
  being sampled
• Probability of selection can be specified
• Nonprobability sampling
• Probability sampling conditions do not apply

6
Probability Sampling

• Simple random sampling
• Build a sampling frame containing all population
  members
• Stratified random sampling
• Sampling frame divided into groups (based on
  demographic characteristics)
• Random sampling applied to each group

7
Probability Sampling
What if theres no sampling frame?

• Cluster sampling
• Units (e.g., schools) containing population
  members are identified
• Essentially, this step creates the sampling frame
  
• These clusters are then randomly sampled
• May not represent the entire population

8
Nonprobability Sampling

• Convenience sampling
• Grab whomever you can
• Likely to generate a nonrepresentative sample
• Quota sampling
• Sample designed to mirror population
  characteristics (e.g., of females)
• Uses convenience sampling to create sample within
  each quota group (e.g., males and females)

9
Nonprobability Sampling

• Self-selected samples
• Participants elect to participate (as opposed to
  being sought out by researcher)
• A form of convenience sampling
• Likely to generate a large sample size, but keep
  in mind that representativeness matters more than
  sample size!

10
Nonprobability Sampling

• Purposive sampling
• Sample created in line with study goals (e.g.,
  focus only on students in Top 10 graduate
  programs in research on the work habits of
  successful graduate students)
• Two common strategies
• Expert sampling
• Snowball sampling participants recruit others
  to participate

11
Sampling Check Your Understanding

• What is the difference between quota sampling and
  stratified random sampling?

12
Margin of Sampling Error

• Sample results are estimates of the true
  population value
• Sampling variability captures how sample
  characteristics fluctuate
• If you roll two dice 100 times and encounter this
  5 and 2 pattern 13 times, its extremely
  unlikely youll see this pattern 13
  more times in the next 100 rolls

13
Margin of Sampling Error

• Thus, sampling error acknowledges that our
  population estimates vary depending on the sample
  
• Survey data are then accompanied by a margin of
  sampling error, a range of values within which
  the true population value falls
• Keeping in mind that we can never be 100 certain
  in our results, we also report confidence levels
  (typically 95)

14
Sample Reporting

• For results based on the total sample of
  national adults, one can say with 95 confidence
  that the margin of sampling error is 2
  percentage points.
• Gallup Economy Poll - May 28, 2013
• http//www.gallup.com/poll/162797/economic-confide
  nce-holds-steady-high-level.aspx

15

• Taking the following data into account, why dont
  researchers aim for more precise estimates?

16
Constructing Questionnaires

• Write a survey item asking participants about
  their exercise habits
• Now, ask a classmate for feedback on your item
• Developing a questionnaire takes a significant
  amount of time and effort, and typically several
  versions are piloted before the final version is
  rolled out.

17
Types of Questions

• Open-Ended and Closed-Ended

• Closed-ended questions provide specific response
  options, whereas open-ended questions do not,
  allowing participants to answer in whatever form
  they choose
• Was your item about exercise behavior open- or
  closed-ended?
• Open-ended questions generally are more difficult
  to work with. Why?

18
Closed-Ended Question Types

• Multiple choice
• Ranking scales

19
Closed-Ended Question Types

• Forced choice
• Rating scales

Describe the signature features of Likert
response formats.
20
Question Wording

• Common Pitfalls to Avoid

• Leading questions
• Loaded questions
• Double-barreled questions
• Double negatives

Are you or are you not in favor of terrorists in
our country corrupting our young people and
threatening our core values?
Help! Identify whats wrong with this question
and rewrite it.
21
Putting the Survey Together

• General Rules of Thumb

• Group related questions together
• Place open-ended questions before closed-ended
  questions
• Move from more general to more specific questions
  
• Place personally sensitive questions at or near
  the end

22
Administering Surveys

• Supplements to ongoing behavioral observations

• Face-to-face (in-person) interviews
• Achieve higher response rates
• Facilitate establishment of rapport
• Enable standardized approach
• Interviewer can clarify any participant confusion
  
• But, theyre pricey!

23
Administering Surveys

• What can interviewers do to aid each of the
  following?
• Limitations in participant memory
• Response distortion due to interviewer bias or
  other interviewer effects

24
Other Ways to Administer Surveys

• Telephone
• Mail
• Online
• Discuss the strengths and limitations of each
  mode of data collection.

25
Additional Survey Considerations

• Nonresponse bias occurs when participants who
  declined to participate would have responded
  differently than participants did
• Introduces more error into population estimates
• Although lower response rates do not appear to
  drive nonresponse bias, declining participation
  rates are of concern
• Many researchers offer incentives to encourage
  participation

26
Be a Smart Survey Consumer

• What survey design features enable you to have
  greater confidence in the results?
• Be on the lookout for bogus surveys!

Think Critically