During research, all individuals sharing a certain characteristic, or the entire population, are rarely available. Therefore, research is most often conducted on a sample, or a subset of the population.

The purpose of statistical inference is to draw conclusions about the population, which are based on data obtained from the sample.

Since conclusions move from the specific (the sample) to the general (the population), statistical inference is classified as inductive inference. Since such a conclusion is not certain, probability is used to assess the quality of the conclusion and to quantify the risk that an incorrect conclusion has been made.

Statistical inference is used when analyzing quantitative or qualitative variables measured on a representative sample, in order to estimate population parameters such as the mean, variance, or proportions. A sample may be subjected to an experimental treatment or sampled from a subgroup of the population, and the aim is to determine whether the sample differs significantly from the target population, or whether it was drawn from a population with a different arithmetic mean.

Estimating population parameters and hypothesis testing are two methods used in inferential statistics.