Название: Applications of Regression for Categorical Outcomes Using R
Автор: David Melamed, Long Doan
Издательство: CRC Press
Год: 2024
Страниц: 239
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

This book covers the main models within the GLM (i.e., logistic, Poisson, negative binomial, ordinal, and multinomial). For each model, estimations, interpretations, model fit, diagnostics, and how to convey results graphically are provided. There is a focus on graphic displays of results as these are a core strength of using R for statistical analysis. Many in the social sciences are transitioning away from using Stata, SPSS and SAS, to using R, and this book uses statistical models which are relevant to the social sciences. Social Science Applications of Regression for Categorical Outcomes Using R will be useful for graduate students in the social sciences who are looking to expand their statistical knowledge, and for Quantitative social scientists due to it’s ability to act as a practitioners guide.

R is a free, comprehensive, and inclusive computing environment. On the one hand, this means that it is flexible, more efficient than many alternatives, and does things that stand-alone statistics packages do not do (e.g., natural language processing or web scraping). On the other hand, it means that there are no computer programmers who develop graphical user interfaces that account for what users want from their statistical packages. That is to say, there is a trade-off between flexibility and user-friendliness, and R certainly prioritizes flexibility over ease of use.

We implement R in the context of RStudio. RStudio is an integrated development environment (IDE) that functions as a wrapper for base R. Although base R includes many statistical procedures, including many used in this book, it is closer to a calculator than it is to standard statistics packages (e.g., SAS or Stata). RStudio includes base R as part of the environment, but it also includes scripts to maintain and execute your code, integrated help files, and the ability to manage larger projects.

Key Features:

Applied - in the sense that we will provide code that others can easily adapt
Flexible - R is basically just a fancy calculator. Our programs will enable users to derive quantities that they can use in their work
Timely - many in the social sciences are currently transitioning to R or are learning it now. Our book will be a useful resource
Versatile - we will write functions into an R package that can be applied to all of the regression models we will cover in the book
Aesthetically pleasing - one advantage of R relative to other software packages is that graphs are fully customizable. We will leverage this feature to yield high-end graphical displays of results
Affordability - R is free. R packages are free. There is no need to purchase site licenses or updates.