This website serves as an online textbook for introductory statistics, covering topics such as summarizing and presenting data, producing data, variation and probability, statistical inference, and control charts.
I am not accustomed to saying anything with certainty after only one or two observations. is a quote by Flemish anatomist Andreas Vesalius (1514-1564). The quote is found in "Epistola rationem modumque propinandi radicis Chynae decocti".
This Department of Energy website provides weekly average gasoline prices for several regions, states and cities. The averages are produced from a weekly survey of around 800 retail gasoline stations. The site includes information on data collection methods, survey methodology and historical data.
This article presents a dataset containing physical measurements for 507 physically active individuals. These data can be used to demonstrate simple descriptive statistics, least squares and multiple regression, or discriminant and classification analysis. The data are in .dat format.
This article describes a dataset containing information for 25 brands of domestic cigarettes. The dataset can be used to illustrate multiple regression, outliers, and collinearity.
This article presents a dataset based on an industrial case study using design of experiments. It can be used to discuss sample size, power, statistical significance, interaction terms, Type I and Type II errors, the role and importance of the error term, design of experiments, and analysis of variance.
The dataset presented in this article contains information on respiratory function and smoking. The data can be used to explore descriptive statistics, graphical analysis, regression, and observational studies. The data are in .dat format.
This article presents a dataset from an experiment designed to test if increased reproduction reduces longevity for male fruitflies. The data are in .dat format. Key Words: Analysis of variance; Contrasts; Experimental design; Regression; Precision; Statistical interaction; Survival analysis.
This article presents data from 1997 Big Ten Conference men's basketball games involving the University of Iowa Hawkeyes. The data can be used to demonstrate bivariate statistical inference techniques such as confidence regions, paired comparisons, and simultaneous confidence intervals. Key Word: Bivariate data; Scatterplot.
This article presents data for examining the ability of individuals to choose numbers randomly. Three datasets of six-tuples selected by a lottery game, generated by S-Plus, and chosen by college students can be compared using descriptive statistics and goodness of fit tests to explore bias and randomness. Key Words: Boxplots; Chi-squared tests; Minimum gap; QQ plots.