Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
24 Cards in this Set
- Front
- Back
Population
|
Group we're interested in learning something about
i.e. more general |
|
target population
|
the pop. about which the information is actually desired
|
|
census
|
collect data from ENTIRE population
|
|
survey
|
collect data from only SOME members
|
|
poll
|
collect data from only SOME members by asking questions
|
|
sample
|
subgroup chosen to provide data
|
|
sampling frame
|
group from which sample will be chosen
|
|
Bias
|
systematic favoritism in data collection
|
|
Sampling variability
|
when different samples provide different statistics fro same population even when samples are chosen in exactly the same way
|
|
Response Rate
|
% of respondents out of total sample
|
|
Selection Bias
|
to exclude/include particular group w/in population
|
|
Non-response Bias
|
when response rate to survey is low
|
|
Quota sampling
|
Divide population into groups based on important characteristics proportionate to population
|
|
Convenience sampling
|
choose sample in a way that is easiest/fastest/cheapest
|
|
Simple Random Sampling (SRS)
|
Choose (n) people from population @ random. " Draw names from a hat."
|
|
Stratified Sampling (SS)
|
Divide population into strata (groups) sample. Select random # of strata to use as part of sample. Repeat as desired w/ subdivisions.
|
|
Parameter
|
estimate of some unknown measure based on statistic
|
|
Statistic
|
any kind of numerical info drawn from a sample
|
|
Sampling Error
|
The difference between parameter & a statistic used to estimate that parameter. (measures how much data from survey differs if census were to be used)
|
|
Sampling proportion
|
n/N (n=size of sample) (N=size of population)
[means (n) of sample is x% of population] |
|
Randomized controlled study
|
Where subjects are assigned to treatment group/control group randomly
|
|
Placebo
|
make believe form of treatment to control & judge results to real treatment
|
|
Blind study
|
study in which neither treatment group /or/ control group know which group they are in.
|
|
Double Blind study
|
study in which neither scientists/subjects know which group they are in
(Used to keep results of study totally objective) |