Resource Library

This article describes data from a drug interaction study of a new drug and a standard oral contraceptive therapy. Both normal theory and distribution-free statistical analyses are provided along with a notable amount of graphical insight into the dataset.

This article describes a dataset on the readability of booklets about cancer and the reading levels of patients with cancer. Students should be familiar with scales of measurement, data reduction, measuring center, constructing and interpreting displays, and reaching conclusions in real problems. Key Words: Ordinal data, Means, Medians, Histograms

This article addresses a dataset on public school expenditures and SAT performance. Key Words: Multiple regression; Omitted variable bias; Partial correlation; Scatterplot.

This article describes a dataset on life expectancies, densities of people per television set, and densities of people per physician in various countries of the world. The example addresses correlation versus causation and data transformations. Key Word: Prediction.

This site provides applets, lessons, and objectives for learning about conditional probability. The applet activity introduces multiple-outcomes events and computing probabilities.

This short article discusses the difference between "important" and "statistically significant." The data used come from a study comparing male faculty salaries to female faculty salaries.

This excerpt from Engineering Statistics Handbook gives a definition for and examples of outliers. A sub-page also discusses Grubbs' Test for Outliers

A short discussion of what outliers are and their helpfulness in analyzing data.

This text document lists detailed learning objectives for introductory statistics courses. Learning objectives are brief, clear statements of what learners will be able to perform at the end of a course. These objectives were developed for a one semester general education introductory statistics course. The objectives cover the broad categories of Graphics, Summary Statistics, The Normal Distribution, Correlation and Scatterplots, Introduction to Regression, Two way Tables, Data Collection and Surveys, Basic Probability, Sampling Distributions, Confidence Intervals, Tests of Hypothesis, and T-distributions.

Pseudo random number generators (PRNG) start with a seed value and will eventually repeat all the numbers they generate in exactly the same order. Putting in the same seed value will give precisely the same set of random numbers. On large scale Monte Carlo simulations (depends on generation of multiple random numbers), care has to be taken to make sure that the PRNG cycle is significantly longer than the quantity of random numbers needed or the pattern in the PRNG cycle can show up as an error producing pattern in the simulation results.