- Self reports
- Self reports can be thought of as a kind of written
interview. They can be an effective means of measuring the behaviour,
attitudes, preferences, opinions and intentions of relatively large numbers of
subjects more cheaply and quickly than other methods.
- If respondents are anonymous their answers may be more honest. Reduces interviewer bias.
- The sample of people may not be representative of the population so generalisation is risky.
- Social desirability-people may respond in ways they think are socially acceptable rather than say what they really think.
- Open ended questions
- Enable the respondent to answer in as much detail as he/she likes in her own words.
- Produce in depth responses relating to what the participant actually thinks rather than being restricted by categories
- Can be difficult to analyse.
- Closed ended questions
- Require the respondent to choose from a number of pre-set alternatives
- Easy to score and analyse.
- Restricted range of answers available (e.g. may force respondent to choose between ‘yes’ or ‘no’ when they may wish to answer ‘sometimes’)
- With ‘yes/’no’ answers may be prone to acquiescence response set (ARS) always responding with a ‘yes’ –it is easier to do this tan say no as they may be asked why.
- Opportunity sample
- People who are available at the time of study, fit criteria and are willing to take part.
- it allows a larger quantity of sampling much more easily and quickly. It is convenient as it takes very little time.
- it is not representative and biased. You will have a certain type of participant-those who are there at the time.
- Random sample
- Every person in the target population has an equal chance of being selected to take part.
- it is unbiased as all members of the target population have an equal chance of taking part.
- it is time consuming and can be expensive. Also when you identify participants they may not always want to take part.
- Volunteer or self selected sample
- This is where the participants volunteer to take part in response to an advertisement, e-mail or a leaflet. Maybe monetary incentive.
- can generate a wide variety of participants sometimes. Also people who volunteer are less likely to drop out.
- biased and not representative because only a certain type of person volunteers to take part in a study.
- . Also can be expensive to advertise and time consuming to test that volunteers are suitable.
to the consistency of the questionnaire, (do you get the same results every
time).Internal reliability refers to
how consistent the actual questionnaire is within itself.
- Usually measured by checking weather people tend to answer each item in the same way as they answer all the others. Checking for ARS.
- External reliability looks at whether the test produces similar
results on different occasions.
- This can be measured by giving a group of people a test and then at a later date giving the same test and correlating the results.
- Refers to the consistency of the questionnaire, (do you get the same results every time).Internal reliability refers to how consistent the actual questionnaire is within itself.
- Refers to whether the test measures what it is suppose to measure.
- Predictive validity is a check whether the test results are a good predictor for future performance.
- Validity can be tested by concurrent validity which is comparing the test with an already well established one.
- Self reports can be thought of as a kind of written interview. They can be an effective means of measuring the behaviour, attitudes, preferences, opinions and intentions of relatively large numbers of subjects more cheaply and quickly than other methods.