Work

Inferential Statistics: Definition, Types and Examples

Year: 2026
Type: article
Abstract: Inferential statistics allow a researcher to draw conclusions about a population from a sample, but the logic behind them is misread more often than the arithmetic. A result can be overstated, or a real effect dismissed because a p-value fell just above .05. This article defines inferential statistics and sets out how they differ from descriptive statistics. It explains the idea on which all inference rests, sampling error and the central limit theorem, and the two tasks that inference performs: estimation with confidence intervals, and hypothesis testing with p-values, including the two misreadings of p-values that are most common. It then describes five common inferential tests (the t-test, analysis of variance, the chi-square test, correlation and regression), each with a worked or simulated example and, for three of them, an extract from a doctoral study showing how the result was reported. Throughout, it distinguishes what a test can show from what only the research design can establish. It is intended for students and early-career researchers analyzing or reporting quantitative data, and for the educators who teach research methods and statistics.This is the formal edition of an article first published by Grad Coach at https://gradcoach.com/inferential-statistics/.
Language: English
Open Access status: green
OpenAlex ID: W7225894931
FWCI:
Cites: 4
Cited by:
Related to: 10