Non-Experimental Designs I: Survey Methods Flashcards
_________ sampling is most likely to be used in survey research
probability
What is self-selection bias and where does it usually occur?
When the sample is composed only of those who voluntarily choose to response, thus the results are a bias sample.
Usually occurs in newspapers and magazines
A good use of open-ended questions in a survey is in a ________ study as a way of identifying alternatives for a subsequent survey to be composed of closed items.
pilot
Surveys with closed questions often use an interval scale for measuring responses. The most common interval scale used in surveys is…
the Likert scale
Response acquiescence
a tendency to agree with statements
How do surveys with a Likert scale avoid response acquiescence?
They will balance favourable and unfavourable statements, forcing respondents to read each item carefully.
Including too much in an item resulting in one that actually asks two responses at once is sometimes referred to as a _________-________ question
double-barreled
Advantages and disadvantages of in-person interviews
Advantages: comprehensive, highly detailed, reduction of unclear questions
Disadvantages: interview bias, cost, sampling issues (some people may not be included)
What is nonresponse bias and when can it occur?
Occurs when the people who do complete and return the survey differ in some important ways from those who did not return the survey
Can occur with mailed written surveys
Social desirability bias
When people respond to a survey question in a way that doesn’t reflect what they truly feel but how they think they should respond
How can researchers avoid social desirability bias?
By ensuring anonymity
______ surveys combine the efficiency of a mailed survey with the personal contact of an interview.
Phone
What is the main advantage of online surveys?
A large amount of data can be collected in a short amount of time and with minimal cost
A correlation exists when…
two variables are associated or related
Positive correlation
A high score on one variable is associated with a high score on the second variable; similarly a low score on one variable is associated with a low score on the second variable