Chapter 10: Data Collection Flashcards
Types of Error
sampling error noncoverage error nonresponse error response error office error
Sampling Error
Difference between results obtained for a sample and the results we would have obtained had we gathered info from the whole population.
easy to reduce: increase sample size or calculate the margin of sampling error
most manaageable
Noncoverage Error
error due to the failure to include some elements of the defined target population in the sampling frame
a sampling frame problem.
ways to reduce: improve quality of sampling frame.
Nonresponse Error
error from failing to obtain information from some elements of the population that were selected and designated for the sample.
when data is not collected from all respondents selected for sample.
Two main sources: refusals & not-at-homes.
refusals
nonresponse error resulting because some designated respondents refuse to participate in the study
ex. cultural differences, lack of time, contacting respondents at inappropriate time, and lack of interest in subject matter.
not at homes
nonresponse error that arises when respondents are not at home when the interviewer calls.
ex. movement of landline to cellphone and caller ID
use callbacks
Response Error
error that occurs when an individual provides an inaccurate response, consciously or subconsciously, to a survey item.
Questions useful for considering the different ways response errors can affect individuals’ responses.
does the respondent understand the question.
does the respondent know the answer to the question.
is the respondent willing to provide the true answer to the question?
is the wording of the question or the situation in which it is asked likely to bias the response.
Office Errors
after data is collected.
error due to data editing,coding, or analysis errors.
Total error
total error, rather than any single type of error is the key in a research question.
Response rate
the number of completed interview with responding units divided by the number of eligible responding units in the sample.
two functions:
1allows an assessment of the potential influence of nonresponse error
2. response rate serves as an indicator of the overall quality of a data collection effort.
calculate response rate
number of completed interviews with responding units divided by number of eligible responding units in the sample
Web Based and Mail Surveys Response Rate
straightforward response rate,
take number of usable surveys divided by sample element attempted minus those addresses that were invalid.
Telephone Surveys with no eligibility requirement Response Rate
little more complicated
no eligibility requirement
attempted contacts into three groups: completed interviews, refusals, and not at homes.
RR= number of completed interviews divided by number of completed interviews+number of refusals+ number of not at homes
wrong numbers and non working numbers do not count
Telephone Surveys with eligibility requirement response rate
some householders are ineligible.
count completed interviews, refusals, not at homes and ineligible response units.
need to adjust the response rate to account for this ineligibility
RR= number of completed interviews divided by number of completed interviews + E% * (number of refusals + number of not at homes)
