Statistical Inference (Part 3): Statistical Hypothesis Testing and Confidence Interval Estimation.

An association between an independent and a dependent variable found in a study may have several explanations, including chance (i.e., random error). This article presents two approaches to assess the role played by chance in an association: confidence interval estimation and statistical hypothesis testing. Statistical hypothesis testing estimates the probability (i.e., the P value) of getting a difference as large or larger than the one observed in a specific study assuming the absence of association. Confidence intervals are estimates of the range of values that are expected to include the actual parameter with a certain probability, or confidence level (often 0.95 or 95%).