Resource Library

This applet generates dotplots for different data sets and allows users to guess the location of various measures of center and spread. Clicking "Resample" produces a dotplot of random data generated by the applet. A dotplot of user-input data can be generated by clicking "Edit Data" and typing or copy and pasting the data in the textbox. To guess the mean, median, standard deviation, and interquartile range (IQR) users check the "Guess Mean/Median", "Guess Deviation", or "Guess IQR" box and slide the relevant marker along the horizontal axis. When "Guess Deviation" is selected, users can also select "Show Percentages" to display the percentage of data points within the user's current guess for standard deviation. Clicking "Show Actual" displays the actual position of the selected measure on the dotplot. Clicking on an individual data point shows its value. Users can edit the data under "Edit Data" or by clicking and dragging the data points on the graph.

This applet generates a histogram for two provided datasets, or by clicking "Edit Data", users can input their own data. Users can also manipulate the axes and bin width.

This applet allows users to play several probability games like Monty Hall, Gambler's Ruin, Galton's Board, etc. Select a game from the drop down menu and click "About" to read its background. Users can manipulate the parameters for each game. Graphs of the theoretical and empirical distributions are shown. Requires JAVA.

This applet allows users to run experiments such as Ball and Urn, Buffon's Needle, Craps, Monty Hall, and many more. Select an experiment from the drop down menu and click "About" to read its description. Then, set the parameter values. Set the sample size using the "Update" box and the number of samples using the "Stop" box. The single arrow button takes one sample and the double arrow button takes the number of samples selected. Graphs of the theoretical and empirical distributions are shown. Requires JAVA

This scatterplot lets users plot a number of demographic variables and see the log transformation of those variables for numerous countries and income groups. Users can also see the information for any year from 1975 to 2004.

This collection of datasets was compiled by the Biostatistics Department at Vanderbilt University. They come in R, S, Excel, and ASCII formats. Each also has a description in html format.

This module provides an activity were students will attempt to explain how each of the following variables is related to child poverty within the United States: Race, Age, Family Type, Family Size, and Immigrant Status.

This collection of datasets covers many application areas, but are all for time series analysis. The data are in text format.

This module is designed to illustrate the effects of selection bias on the observed relationship between premarital cohabitation and later divorce. It also serves as a review of key methodological concepts introduced in the first part of the course.

How are earnings determined? Why do some people earn more than others? Does a better job necessarily mean a better salary? In this module, students will attempt to answer these questions and many others by examining factors such as education and occupation in terms of the role they play in determining earnings. Students will also look at the earnings of whites and compare them to the earnings of blacks, Latinos, and Asians. Another consideration will center on the effect of gender. Finally, students will turn their attention to the age of workers in terms what role it plays in determing earnings. Aside from earnings, students will also take a brief look at poverty with respect to the effect race-ethnicity and family structure has on creating and sustaining it.