Population - correct answer Entire set of individuals of interest
Sample - correct answer -- Set of individuals selected from a population
-- Intended to represent the population in all respects that are potentially relevant to the study
-- No one is over or under represented
Sort in order of smallest to largest: Population, Sample, Accessible Population - correct answer
Sample < Accessible Population < Population
Sampling Terminology - correct answer -- Element: who or what are we studying
-- Population: Whole group
-- Study population: Where the sample is selected
-- Sampling frame: Actual list of units to be selected
-- Parameter: Summary description of a given variable in a population
-- Statistic: Summary description of a given varialbe in a sample; we use sample statistics to make
estimates or inferences about population parameters
Sampling Error - correct answer -- Difference between the characteristics of a
sample and characteristics from which it was drawn
-- When sampling error is larger, the sample will be less representative of the population
Two general categories of sampling - correct answer 1. Probability: A method of
selection in which each member of a population has a known chance or probability of being selected
2. Non-probability: A method of selection other than a probability sample
Five methods of probability sampling - correct answer 1. Simple Random
2. Systematic
, 3. Stratified
4. Disproportionate Stratified
5. Multistage Cluster
Simple random sampling - correct answer Every member of a population is listed
and members are then randomly selected for questioning
Systematic sampling - correct answer Every member of a population is listed and
every kth member is then selected
Ex. Every 4th name on a list of students is selected
Stratified sampling - correct answer The total population is divided into groups (or
strata) and then members of each group are randomly selected
Ex. Political surveys say they have a representative sampling by making sure to sample percentages of
gender, race, and state of residence that match the national average (if US is 30% African Americans,
30% of the sample must be African American)
Disproportionate stratified sampling - correct answer -- Deliberately drawing a
sample that over- or underrepresents some characteristics of a population
-- Why? To ensure that we obtain a sufficient number of uncommon cases in our sample
-- Ex. Violent crime in rural areas v. large cities (oversample rural areas b/c there might not be very much
crime there in general, but we're interested to see what kinds of crime are being committed)
Multi-stage cluster sampling - correct answer -- The entire population is divided into
groups
-- A random sample of these clusters is selected and all units within selected clusters are measured
-- May do this because it is sometimes cheaper and more convenient to sample the entire population
randomly, especially when population elements are spread over a wide area