Statistics 101 for Radiologists

Abstract

Diagnostic tests have wide clinical applications, including screening, diagnosis, measuring treatment effect, and determining prognosis. Interpreting diagnostic test results requires an understanding of key statistical concepts used to evaluate test efficacy. This review explains descriptive statistics and discusses probability, including mutually exclusive and independent events and conditional probability. In the inferential statistics section, a statistical perspective on study design is provided, together with an explanation of how to select appropriate statistical tests. Key concepts in recruiting study samples are discussed, including representativeness and random sampling. Variable types are defined, including predictor, outcome, and covariate variables, and the relationship of these variables to one another. In the hypothesis testing section, we explain how to determine if observed differences between groups are likely to be due to chance. We explain type I and II errors, statistical significance, and study power, followed by an explanation of effect sizes and how confidence intervals can be used to generalize observed effect sizes to the larger population. Statistical tests are explained in four categories: t tests and analysis of variance, proportion analysis tests, nonparametric tests, and regression techniques. We discuss sensitivity, specificity, accuracy, receiver operating characteristic analysis, and likelihood ratios. Measures of reliability and agreement, including κ statistics, intraclass correlation coefficients, and Bland-Altman graphs and analysis, are introduced.