|
Abstract:
|
Most data in practical applications of statistics and machine learning are not independently and identically distributed (IID) according to normal distributions, as many basic linear models assume. This workshop aims to present theory and share hands-on experiences with IBM SPSS Statistics to perform appropriate statistical analyses on data with errors that exhibit unequal variances, correlations and/or non-normal distributions. We will handle these data using several approaches, including Bayesian analyses, regression algorithms and mixed models. The Bayesian features in SPSS Statistics include various models for binomial, Poisson and multinomial data. In some scenarios, the desired posterior distributions are simulated by Monte Carlo methods. In regression algorithms, we are modeling data, possibly correlated, with various distributions and estimation methods. Mixed models include various target distributions and link functions, random effects and repeated measures, and various types of covariance structures, including spatial and Kronecker product structures. Tips for teaching the approaches to students will be provided. Some familiarity with statistics is expected. The attendees will get better understanding of several statistical techniques for non-IID and/or non-normally distributed data and learn how to apply and teach the techniques using IBM SPSS Statistics.
|
