Recently a student asked about the difference between confint() and confint.default() functions, both available in the MASS library to calculate confidence intervals from logistic regression models. The following example demonstrates that they yield d...

Read more »

Tags: clodds statement, confidence intervals, confint(), logistic regression, MASS library, ods system, proc logistic, profile likelihood, SAS formats

Posted in SAS | Comments Off on Example 9.14: confidence intervals for logistic regression models

Recently a student asked about the difference between confint() and confint.default() functions, both available in the MASS library to calculate confidence intervals from logistic regression models. The following example demonstrates that they yield d...

Read more »

Tags: clodds statement, confidence intervals, confint(), logistic regression, MASS library, ods system, proc logistic, profile likelihood, SAS formats

Posted in SAS | Comments Off on Example 9.14: confidence intervals for logistic regression models

Recently a student asked about the difference between confint() and confint.default() functions, both available in the MASS library to calculate confidence intervals from logistic regression models. The following example demonstrates that they yield d...

Read more »

Tags: clodds statement, confidence intervals, confint(), logistic regression, MASS library, ods system, proc logistic, profile likelihood, SAS formats

Posted in SAS | Comments Off on Example 9.14: confidence intervals for logistic regression models

While skewness and kurtosis are not as often calculated and reported as mean and standard deviation, they can be useful at times. Skewness is the 3rd moment around the mean, and characterizes whether the distribution is symmetric (skewness=0). Kurtos...

Read more »

Tags: central moments, descriptive statistics, kurtosis, moments package, ods system, proc univariate, skewness

Posted in SAS | Comments Off on Example 8.42: skewness and kurtosis and more moments (oh my!)

While skewness and kurtosis are not as often calculated and reported as mean and standard deviation, they can be useful at times. Skewness is the 3rd moment around the mean, and characterizes whether the distribution is symmetric (skewness=0). Kurtos...

Read more »

Tags: central moments, descriptive statistics, kurtosis, moments package, ods system, proc univariate, skewness

Posted in SAS | Comments Off on Example 8.42: skewness and kurtosis and more moments (oh my!)

While skewness and kurtosis are not as often calculated and reported as mean and standard deviation, they can be useful at times. Skewness is the 3rd moment around the mean, and characterizes whether the distribution is symmetric (skewness=0). Kurtos...

Read more »

Tags: central moments, descriptive statistics, kurtosis, moments package, ods system, proc univariate, skewness

Posted in SAS | Comments Off on Example 8.42: skewness and kurtosis and more moments (oh my!)

Tim Hesterberg has effectively argued for a larger role for resampling based inference in introductory statistics courses (and statistical practice more generally). While the Central Limit Theorem is a glorious result, and the Student t-test remarkabl...

Read more »

Tags: cat(), central limit theorem, coverage probabilities, end, file print, normality assumption, numeric(), ods system, Put, retain, rexp(), rnorm(), robustness, SAS macro, t-test, Tim Hesterberg

Posted in SAS | Comments Off on Example 8.34: lack of robustness of t test with small n

In recent weeks, we've explored methods to fit logistic regression models when a state of quasi-complete separation exists. We considered Firth's penalized likelihood approach, exact logistic regression, and Bayesian models using Markov chain Monte Ca...

Read more »

Tags: by statement, Markov Chain Monte Carlo, MCMCpack package, merge, Monte Carlo experiments, names(). events/trials syntax, ods system, random number generation, sapply(), saving output from SAS, seeds

Posted in SAS | Comments Off on Example 8.18: A Monte Carlo experiment