Resource Library

This program visualizes the effects of outliers to regression lines. The user may pick up a point with the mouse and move it across the chart. The resulting regression line is automatically adjusted after each movement, showing the effect in an immediate and impressive way. The program Leverage allows one to experiment with the leverage effect. You can create a random sample of data noisy points on a line. Dragging one of the points away from the regression line immediately shows the effect, as the regression line is recalculated and moves according to the current data set. Not online: user has to download the program.

How can we accurately model the unpredictable world around us? How can we reason precisely about randomness? This course will guide you through the most important and enjoyable ideas in probability to help you cultivate a more quantitative worldview.

By the end of this course, you’ll master the fundamentals of probability and random variables, and you’ll apply them to a wide array of problems, from games and sports to economics and science.  This course includes 62 interactive quizzes and more than 400 probabilty-based problems with solutions.  Access to this course requires users to sign up for a free account.

This presentation is a part of a series of lessons on the Analysis of Categorical Data.  This lecture overs the following: covariance patterns and generalized estimating equations (GEE). 

This presentation is a part of a series of lessons on the Analysis of Categorical Data.  This lecture overs the following: conditional logistic regression, conditional likelihood for matched pairs, the non-central hypergeometric, the conditional maximum likelihood estimator (CMLE), conditional confidence interval for odds ratios, and McNemar's statistic.

This presentation is a part of a series of lessons on the Analysis of Categorical Data.  This lecture overs the following:  odds ratio, dependent proportion, marginal homogeneity, McNemar's Test, marginal homogeneity for greater than 2 levels, measures of agreement, and the kappa coefficient (weighted vs. unweighted).

This presentation is a part of a series of lessons on the Analysis of Categorical Data. This lecture covers the following: sparse tables, sampling zeros, structural zeros, and log-linear model (and limitations).

This presentation is a part of a series of lessons on the Analysis of Categorical Data. This lecture covers the following: partial/conditional tables, confounding, types of independence (mutual, joint, marginal, and conditional), identifiability constraints, partial odds ratios, hierarchical log-linear model, pairwise interaction log-linear model, conditional independence log-linear model, goodness of fit, and model building.

This presentation is a part of a series of lessons on the Analysis of Categorical Data. This lecture covers the following: conditional independence, log-linear models for 2x2 tables, expected counts, logistic regression, odds ratio, parameters of interest for different designs and the MLEs, poisson log-linear model, double dichotomy, the multinomial, and the multinomial log-linear model.

This presentation is a part of a series of lessons on the Analysis of Categorical Data. This lecture covers the following: ordinal regression models, cumulative probabilities, non-proportional odds, score stat for proportionl odds, MLEs, the adjacent categories logit, and proportional odds model.

This presentation is a part of a series of lessons on the Analysis of Categorical Data. This lecture covers the following: generalized odds ratio, collapsed categories, polytomous (or multinomial) logistic regression, and maximum likelihood using the multinomial.