Search
Create
Log in
Sign up
Log in
Sign up
Sampling Basics: Probability & Nonprobability
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (17)
Sampling Methods
1-Probability
2-Nonprobability
Probability
(Sampling Methods)
Odds of selecting a particular individual are known (exact population size must be known)
-Each individual must have a specifiable probability of selection
Each individual is equally likely to be selected.
-Random process - unbiased method or selection; outcome must be unpredictable each time
Nonprobability
(Sampling Methods)
Odds of selecting a particular individual are not known (exact population size unknown).
Sampling method is based on factors such as common sense or ease, with an effort to maintain representativeness and avoid bias
-Greater risk of producing a biased sample (psy 101 stus are not always interested, gen ed req)
Simple Random Sampling
Equality: Each person has equal chance being selected
Independence: Observations are independent among raters
(Pick name at random in phone book on one page, then pick one random person on next page. No equality b/c only 1 person per page).
Simple Random Sampling
(Probability Samples)
Sampling with replacement: Individual selected for the sample, data recorded, then individual is returned to the population before the next selection is made.
-Guarantees that no individual will appear more than once in a single sample
Systematic Sampling
(Probability Samples)
Identical to random sampling for selection of the first participant; after that, researcher selects every nth case from the list
-Random process does not continue after 1st participant is selected; violates principle of independence
Stratified Random Sampling
(Probability Samples)
Divide population into 2+ segments or strata (income, political affiliation, diff ethnic groups, diff age groups)
Select randomly from each subgroup or strata (Limit: could produce a distorted picture of the overall population)
Use proportionate stratified random sampling (Determine what proportion of the population corresponds to each subgroup; political party)
Cluster Sample
(Probability Samples)
Used when the studied population is spread across a wide area,
Multistage Sampling: Sample smaller clusters within large clusters then sample even smaller clusters to obtain sample (state -> city -> town -> school -> students)
Probability Samples limitation:
Can introduce violations of independence.
Probability Samples
Simple Random Sampling
Systematic Sampling
Stratified Random Sampling
Cluster Sample
Nonprobability Samples
Convenience Sampling
Quota Sampling
Snowball Sampling
Purposive Sampling
Expert Sampling
Modal Instance Sampling
Convenience Sampling
(Nonprobability Samples)
Easy to get selected based availability and willingness to respond.
Quota Sampling
(Nonprobability Samples)
Want 20 males & 20 females
Negative: Might bias true ratio of group
Snowball Sampling
(Nonprobability Samples)
Identify someone who meets your criteria, ask him or her to recommend someone for your study.
(friend tells friend, tells friend, etc.)
Purposive Sampling
(Nonprobability Samples)
Researchers use their own judgment when selecting participants. (shopping mall market research studies: pick someone who fits the researcher's subject want--white middle aged female)
-Weakest, worst forms b/c BIAS
Expert Sampling
(Nonprobability Samples)
Panel of experts
Modal Instance Sampling
(Nonprobability Samples)
Typical video game user (male, 18-25)
-Only sample from this group
;