My first RPubs

ANIMAL

Using SAS to process data of Pens & Printers project

CEA

Last week's analysis covered Generalized Linear Models (GLM), Transformations, and Logistic Regression, however this data dive will mostly be the continuation of Generalized Linear Models (GLM). As discussed earlier, Generalized Linear Models (GLM) are a broad class of statistical models that extend linear regression to accommodate response variables that are not well modeled by a normal distribution. As discussed in last week's class, this data dive will follow these statistical topics: Generalized Linear Models (GLMs): These are a class of models that extend linear regression to handle non-normally distributed response variables by using a link function. Maximum Likelihood Estimation (MLE) is a method used in GLMs to estimate the model parameters by maximizing the likelihood function, providing the most probable parameter values given the observed data. When comparing GLMs, metrics like Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), analysis of variance (ANOVA), and deviance help assess model fit, complexity, and predictive performance, aiding in model selection. Variable Expansion involves transforming predictors to fit the data distribution better, while Variable Selection aims to identify the most relevant predictors, enhancing model interpretability and predictive accuracy in GLMs. As discussed in last week's analysis, and a continuation in this part for the General Linear Models (GLM), the analysis journey continues with another deep dive into how it relates and informs our decisions, conclusions, and insights for the bike sale dataset.

New