Multivariate Categorical Relationships

Research has shown that marital status and employment are correlates of desistance. That is, adolescents involved with crime were more likely to discontinue offending in adulthood if they were married and had a good job. Most of what criminologists know about the process of desistance from crime is based on a sample of adult males in the 1950's. There is no question that life in America has changed drastically in the past fifty years. Given the importance of examining historical change inherent in the life course perspective, it is important to determine how changes in the social structure over time impact individuals. Therefore, the goals of this data analysis exercise are to examine changes in marriage and employment over the last fifty years. The purposes are to identify the changes that have taken place, and to hypothesize how these changes may affect the process of desistance from crime today.

This applet shows a scatterplot of height versus foot length. Users can add or delete points and then guess the regression line by clicking "Your Line" and moving the blue regression line. By clicking "Regression Line" users can see the actual regression line. The applet also shows the correlation and R-square for the data as well as the residuals and squared residuals for the guessed regression line and the actual regression line.

This paper presents rules for determining whether an index variable in such a table is part or whole depending on whether the associated margin value is an average, a sum or a 100% sum. Tables with missing margin values -- date-indexed tables, half tables and control tables -- are analyzed. Recommendations are made to improve reader understanding of any table involving rates or percentages.

This activity discusses probability topics, such as: sample space, independent events, Law of Large Numbers, deviation percentage. A Excel program is required for this activity, which can be reached via the website.