Lecture 6 Flashcards
What are surveys?
all respondents complete the same items. Used to obtain data about feelings and preferences and things :)
What is an important thing to remember when using surveys?
They are descriptive, not experimental/
Anscombe’s quartet is?
a cautionary demonstration
What is the most important thing when sampling?
Well, if it’s at Costco, go back for seconds. JK.
You need a representative sample for data to be generalizable to a population.
Define population
Set of all cases of interest
Define sampling frame?
specific list of subset of the population (the operation definition of the pop.)
Define sample?
the subset of the population drawn from the sampling frame that is included in the study.
Define element?
an individual member of a population.
A specific group within a population us under or over represented is known as a…?
selection bias
What is probability sampling?
a random sampling of the population, this is always preferred.
What is simple random sampling?
each element has the same probability of inclusion
What is stratified random sampling?
Population is divided into stratified subpopulations (like college students by grad class)
When a sample is not random, usually done out of convenience and is prone to bias is known as?
non-probability sampling (ex. call in shows)
What is response bias?
some people may be more likely to respond to surveys than others.
Name 4 common survey methods?
Mail, in-person, telephone, internet
What is a cross-sectional type sample?
Done all at once (voting patterns by age groups)
A snapshot, can’t assess change
What is a successive independent sample?
Done over multiple time points but uses different samples
Good for describing changes in public opinion
Questions and sampling must remain consistent
What is longitudinal sampling?
Same sample, multiple time points– changes in individuals
Problem with sample attrition
What is sample attrition?
When individuals drop out of the study over time.
What are validity scales?
questions to catch liars.
What is internal consistency?
Do all the questions measure the same thing?
Test-retest reliability is?
Do the items measure the same thing each time?
What is inter-rater reliability?
Do different people rate the same behavior in the same way?
What is face validity?
Is it obvious what the items are intended to measure?
What is convergent validity?
Is the measure correlated with valid measure of the same construct?
What is discriminant validity?
Does it distinguish between groups?
What is criterion prediction validity?
Is the measure associated with real world examples of the construct.