Ch 6 Sampling Flashcards
representative sample
accurately reflects the distribution of relevant variables in the target population
Should have all the same characteristics as the population
(considered a small reproduction of the population)
population
Refers to all possible cases of what we are interested in studying
Should specify four things: Content, Units, Extent, Time
sample
Consists of one or more elements selected from a population
sampling frame
a listing of all the elements in a population
to develop sampling frames for household-based surveys of populations that are large (like city or state), 2 listings should be considered …
telephone numbers and lists of addresses in a community (addressed based sampling)
example of poor sampling frames
literary digest - pulled sample from car owners and telephone numbers to see who would win election, but most voters didn’t own cars or phones. their prediction was wrong of who won
probability samples
samples in which each element in the population has a known chance of being selected into the sample
enables us to calculate sampling error
Probability sampling includes what 4 types of sampling?
simple random sampling
systematic sampling
stratified sampling
area sampling
sampling error
an estimate of the extent to which the values of the sample differ from those of the population from which it was drawn
Simple random sampling (SRS)
each element in the population has an equal probability of inclusion in the sample
treats the target population as a unitary whole
it is often impractical because of cost
usually limited to small scale projects
it is the basic sampling procedure and the standard for other sampling procedures
Systematic sampling
Involves taking every kth element listed in a sampling frame
Uses the table of random numbers to determine a random starting point in the sampling frame
Value of k is the sampling interval and is determined by dividing population size by desired sample size
We use this when we draw samples by hand rather than computer
Clerical efficiency
Can produce biased samples
Stratified sampling
Divides the population into smaller subgroups, called strata, before drawing the sample and then draws separate random samples from each of the data
It reduces sampling error
Makes each subsample more homogeneous
Proportionate sampling
Disproportionate sampling
Proportionate sampling
is where the size of the sample taken from each stratum is proportionate to the stratum’s presence in the population
Disproportionate sampling
is when each element of a stratum has an equal chance of appearing in the sample of that stratum, but the elements in some strata have a better chance of appearing in the overall sample than the elements of other strata
Area sampling
Also called cluster sampling OR multistage sampling
It’s a procedure in which we obtain the final units to include in the sample by first sampling among larger units, called clusters, that contain the smaller sampling units
Sampling from large to smaller units
Selected blocks within an area may contain different numbers of people
Estimation of sampling error
a key issue in selecting a sample is that it ….
represent the population from which it was drawn
what 5 things influence sample size?
research hypotheses - sufficient cases to study
precision - amount of sampling error you accept
population homogeneity - variability of sampled population
sampling fraction - number of elements in sample relative to the number of elements in population
sampling technique
what formula to determine sample size?
r^n x 20 = sample size
r = number of values on each variable
n = number of variables
NonProbability sampling includes what 5 types of sampling?
availability sampling
snowball sampling
quota sampling
purposive sampling
dimensional sampling
nonprobability samples
the investigator does not know the probability of each population element’s inclusion in the sample
useful when goal of research is to see whether a relationship exists
useful in some qualitative research to understand social process
useful when its impossible to develop sampling frame
limitations to non probability samples
make no real claim of representativeness
degree of sampling error remains unknown
statistical tests of significance
availability sampling
also called convenience sampling OR accidental sampling
researchers take whichever elements are readily available
popular for research that is difficult or impossible to develop complete sampling frame
often used in experimental or quasi-experimental research
less expensive
impossible to develop exhaustive sampling frame
snowball sampling
start with few cases of the type we want to study, which leads to more cases, and so on
depends on sampled cases being knowledgeable of other cases
used for sampling subcultures
useful in investigation of sensitive topics like that of child or drug abuse
allows for interactive sampling – people interact with each other
limitation: misses people who are isolated from such networks
quota sampling
divides a population into various categories and then sets quotas on the number of elements to select from each category.
Nonprobability technique that depends on availability
Has declined in popularity
Research have quotas for common demographic characteristics like age, sex, race
Interviewers do the actual selection of respondents - shortcoming
Cheaper and faster than probability sampling
Purposive sampling
Investigators use their judgement and prior knowledge to choose for the sample people who best serve the purposes of the study
Dimensional sampling
Technique for selecting small samples in a way that enhances their representativeness
Specify all important dimensions or variables
Choose sample that includes at least one case that represents each possible combo of dimensions
Its faster and less expensive
Valuable in exploratory studies
Provides more detailed knowledge of each case
Some research uses both probability and nonprobability samples in one project
Suggestive rather than conclusive
the key to selecting scientifically valid samples is…
to ensure their representativeness so we can make valid generalizations
human services practitioners do not routinely engage in sampling procedures. true or false?
true
