Statistical Appraisal of the Pima Indians Diabetes Dataset: A Review and Empirical Re-analysis of Risk Factors and Predictive Models

Diabetes mellitus is a major chronic disease, and statistical risk modelling of its onset has been studied forseveral decades. The Pima Indians Diabetes Database, comprising 768 women aged 21 years and above, hasbecome one of the most frequently reused benchmark datasets in the biomedical statistics and machinelearning (ML) literature, yet the statistical properties of the data and the validity of results derived from it arerarely examined together. This review combines a narrative synthesis of the literature with a full statisticalre-analysis of the supplied dataset (268 diabetic, 500 non-diabetic; prevalence 34.9%). We examine dataquality, descriptive and distributional properties, univariate group comparisons with effect sizes, categoricalassociation tests, correlation structure, multivariable logistic regression and a ten-fold cross-validatedcomparison of seven classifiers. Our synthesis finds that (i) five physiological variables encode missingmeasurements as zero, so that only 392 of 768 records (51.0%) are complete; (ii) all eight predictors differsignificantly between groups (Benjamini-Hochberg adjusted p < 0.001), with plasma glucose showing by farthe largest standardised effect (Cohen’s d = 1.19); (iii) after mutual adjustment, only glucose, BMI, number ofpregnancies and the diabetes pedigree function remain independent predictors (McFadden R2 = 0.282); and(iv) seven classifiers achieve cross-validated AUCs of 0.813-0.837 and accuracies of 74.6%-77.2%, with nomodel significantly better than plain logistic regression. We propose a short reporting checklist for studiesusing this dataset and identify six priority research directions.