Survey Research

Survey Research

Uses questionnaires and interviews to ask people to provide information about themselves
1. Response set
  1. Tendency to respond to all questions from a particular perspective
  2. Social desirability response
    1. Most common - answers in the most socially acceptable way
Constructing questions
1. Types of questions
  1. Attitudes and beliefs
  2. Demographic questions
  3. Behaviours
2. Question wording
  1. No unfamiliar terms
    1. Vague terms
      1. Embedding the sentence with misleading information
  2. Unnecessary complexity
  3. Double barrelled questions
    1. Asks two things at once
  4. Loaded questions
    1. Written to lead people a certain way
  5. Negative wording
  6. Yea saying and nay saying
    1. Word the questions so that consistent agreement is unlikely
    2. Do not want people to get used to one answer
What kind of data are you seeking?
1. Closed ended questions
  1. Limited number of responses
  2. Easier to code
  3. Rating scales
    1. Characteristics
      1. Ask people to provide "how much" judgments
      2. Fully labelled scales are more reliable
      3. 5 and 7 point scales are more common
    2. Types of scales
      1. High frequency scale
        Alternatives assume a high frequency
      2. Low frequency scale
        Alternatives assume a low frequency
      3. Graphic rating scale
        Requires a mark along a continuous line that is anchored with descriptions at each end
      4. Semantic differential scale
        Measures the meaning people ascribe to concepts
        Put a checkmark on different lines
      5. Non verbal scale
2. Open ended questions
  1. Respondents can answer any way they like
  2. Harder to code
Administering surveys
1. Questionnaires
  1. Personal administration
  2. Mail surveys
    1. Low response rates
  3. Internet surveys
2. Interviews
  1. Face to face interviews
    1. Time consuming and expensive
  2. Telephone interviews
  3. Focus group interviews
    1. Interview with 6-10 people for 2-3 hours.
3. Panel study
  1. People are surveyed at multiple points in time
Sampling from a population
1. Confidence intervals
  1. Range of plausible values for the population
2. Sample error
  1. Error that comes from not measuring the entire population
3. Sampling frame
  1. The actual population from which a random sample is drawn
4. Response rate
  1. Percentage of people who actually completed the survey
5. Sampling techniques
  1. Probability sampling
    1. Simple random sampling
      1. Every member has an equal chance of being selected
    2. Stratified random sampling
      1. Population is divided into subgroups, simple random sampling is used after
    3. Cluster sampling
      1. Identifying clusters of individuals and sampling from there
  2. Non probability sampling
    1. Convenience sampling
    2. Purposive sampling
      1. Obtain a sample of people that meet a predetermined criterion
    3. Quota sampling
      1. Choose a sample that reflects the numerical composition of subgroups

Next up

Description

Resource summary

Similar

	Created by andreaarose over 10 years ago