Resource Library

The dataset presented in this article provides the salary and performance data for non-pitchers for the 1992 Major League Baseball season. Exploratory data analysis is used to determine a suitable regression model for the data. Key Words: Model selection and validation; Stepwise model selection.

The data presented in this article refer to the reliability of ball bearings in manufacturing. Rather than exploring the data to obtain a multiple linear regression solution, a theoretically derived equation is given and the data is used to test it. Key Words: Failure times; Percentiles; Weighted least squares.

This article describes a dataset containing information on 308 diamond stones, which is useful when studying concepts in multiple linear regression analysis. Key Words: Categorical variables; Data transformation; Standardized residuals.

This article provides a data collection and analysis activity for illustrating simple linear regression and outlier analysis. The activity was designed to involve students in the process of data collection and to motivate studying the relationship between two quantitative variables. Students collect data on occurrences of letters in English text. These data are used to study the relationships between how often a letter occurs in English text, and: (1) the letter's Morse Code units and (2) the relative frequency of Scrabbleä‹¢ game tiles for the letter. Worksheets and answers to the activities are provided.

This section of an online textbook discusses the correlation coefficient and illustrated it visually through graphs. It explains calculations as well as how scatter plots can describe data. It covers significance tests for relationships, the Spearman rank correlation and the regression equation. Exercises and answers are included.

This Flash applet provides an introduction to simple linear regression for introductory statistics students. It combines a brief narrated animation with an interactive scatterplot function. Students are able to place points on the scatterplot by clicking with a mouse or typing X-Y coordinates. Students use these points to learn about the best fit line by placing a guess on the plot and comparing it with the least squares line. Students also learn about the value of the correlation coefficent and points that would be considered outliers. Students may also specify a value of x (within the range of the data) and obtain the resulting predicted value.

This lesson describes bootstrapping in the context of a statistics class for psychology students.

This correlation and regression example compares performance on reading comprehension questions to performace on the SAT. It also compares those who read the passage referred to by the questions to those who did not. Exercise questions and answers are also provided.

Residual plots and other diagnostics are important to deciding whether or not linear regression is appropriate for a set of data. Many students might believe that if the correlation coefficient is strong enough, these diagnostic checks are not important. The data set included in this activity was created to lure students into a situation that looks on the surface to be appropriate for the use of linear regression but is instead based (loosely) on a quadratic function. Key words: regression, residuals

This text document is a detailed index of the Against All Odds video series. This detailed index allows instructors to quickly find stories that can be used in the classroom. The author also includes the his ratings of which video segments are useful in the classroom. The actual videos are viewable online and are also indexed in CAUSEweb.