Home / Summaries / Statistical Methods for the Social Sciences / sample-subjects-error

Sampling and Measurement - Sampling Variability and Potential Bias

5 important questions on Sampling and Measurement - Sampling Variability and Potential Bias

What is the sampling error and why should we know it?

The sampling error shows how much the statistic differs from the parameter it predicts because of the way results naturally exhibit variation from sample to sample. The sampling error for estimating percentages for sample sizes of about 1000, is usually no greater than plus or minus 3%. This is also known as the margin of error.

What is the difference between probability sampling and nonprobability sampling?

With probability sampling, each possible sample of n subjects has the same probability of selection. With nonprobability sampling, it is not possible to determine the probabilities of the possible samples. An example of nonprobability sampling is volunteer sampling.

What are the 3 types of biases in sampling?

Sampling bias: a sample which is not randomly selected and does not represent the population. It is also known as selection bias.
Response bias: the result of poorly worded or confusing question or when the subjects gives an incorrect response.
Nonresponse bias: occurs when some sampled subjects cannot be reached, refuse to participate or fail to answer some questions.

What is undercoverage in case of a sampling frame?

Undercoverage means that a sample lacks representation from some groups in the population, like for example prison inmates.

What does it mean that many studies have a problem with missing data?

In case of missing data, some subjects do not provide responses for some of the measured variables. This problem is especially common in longitudinal studies.

The question on the page originate from the summary of the following study material:

Statistical Methods for the Social Sciences | 9780471094531 | Alan Agresti, et al

View summary