For extremely large populations, a sample may describe the population more accurately than a census.

Constructing a sampling frame often amounts to finding an adequate list of all cases in the population

Probability sampling theory enables researchers to calculate the margin of random sampling error.

Given the same standard error, a 99 percent confidence interval is smaller than a 95 percent confidence interval.

A stratified random sample always has a smaller margin of error than a simple random sample.

Multistage cluster sampling is most appropriate for small, geographically concentrated populations.

Probability sampling is always preferable to nonprobability sampling.

Referral sampling may be used to study very small populations.

Increasing the size of a sample from 100 to 500 will increase sample accuracy more than increasing the size from 1000 to 5000.

Probability sampling designs eliminate coverage error and nonresponse bias.