Comprehensive Linear Modeling with R

Learn to model with R: ANOVA, regression, GLMs, survival analysis, GAMs, mixed-effects, split-plot and nested designs

4.35 (142 reviews)
Udemy
platform
English
language
Data Science
category
Comprehensive Linear Modeling with R
2,351
students
14.5 hours
content
Sep 2020
last update
$39.99
regular price

What you will learn

Understand, use and apply, estimate, interpret and validate: ANOVA; regression; survival analysis; GLMs; smoothers and GAMs; longitudinal, mixed-effects, split-plot and nested model designs using their own data and R software.

Achieve proficiency using the popular no-cost and versatile R Commander GUI as an interface to the broad statistical and graphical capabilities in R.

Know and use tests for simple, conditional, and simultaneous inference.

Apply various graphs and plots to validate linear models.

Be able to compare and choose the 'best' among multiple competing models.

Why take this course?

Comprehensive Linear Modeling with R provides a wide overview of numerous contemporary linear and non-linear modeling approaches for the analysis of research data. These include basic, conditional and simultaneous inference techniques; analysis of variance (ANOVA); linear regression; survival analysis; generalized linear models (GLMs); parametric and non-parametric smoothers and generalized additive models (GAMs); longitudinal and mixed-effects, split-plot and other nested model designs. The course showcases the use of R Commander in performing these tasks. R Commander is a popular GUI-based "front-end" to the broad range of embedded statistical functionality in R software. R Commander is an 'SPSS-like' GUI that enables the implementation of a large variety of statistical and graphical techniques using both menus and scripts. Please note that the R Commander GUI is written in the RGtk2 R-specific visual language (based on GTK+) which is known to have problems running on a Mac computer.

The course progresses through dozens of statistical techniques by first explaining the concepts and then demonstrating the use of each with concrete examples based on actual studies and research data. Beginning with a quick overview of different graphical plotting techniques, the course then reviews basic approaches to establish inference and conditional inference, followed by a review of analysis of variance (ANOVA). The course then progresses through linear regression and a section on validating linear models. Then generalized linear modeling (GLM) is explained and demonstrated with numerous examples. Also included are sections explaining and demonstrating linear and non-linear models for survival analysis, smoothers and generalized additive models (GAMs), longitudinal models with and without generalized estimating equations (GEE), mixed-effects, split-plot, and nested designs. Also included are detailed examples and explanations of validating linear models using various graphical displays, as well as comparing alternative models to choose the 'best' model. The course concludes with a section on the special considerations and techniques for establishing simultaneous inference in the linear modeling domain.

The rather long course aims for complete coverage of linear (and some non-linear) modeling approaches using R and is suitable for beginning, intermediate and advanced R users who seek to refine these skills. These candidates would include graduate students and/or quantitative and/or data-analytic professionals who perform linear (and non-linear) modeling as part of their professional duties.


Content

Data Analysis with R Commander Graphical Displays

Introduction to Course
Notes About: (1) R and (2) R Commander and (3) Materials
Don't Overlook Sectional Exercises !
Materials and Agenda Topics
Graphical Displays using R Commander (part 1)
Graphical Displays using Rcmdr (part 2)
Graphical Displays using Rcmdr (part 3)
Graphical Displays using Rcmdr (part 4)
Graphical Displays using Rcmdr (part 5)
Graphical Displays using Rcmdr (part 6)
Graphical Displays using Rcmdr (part 7)
Graphical Displays using Rcmdr (part 8)

Simple and Conditional Inference

What is Inference ? (slides)
Inference about Roomwidth using Rcmdr
Roomwidth Inference Continued
Simple Inference: Waves Data
Simple Inference: Waves Non-Parametric
Simple Inference: Piston Rings
Conditional Inference: Roomwidths Revisited
Conditional Inference: Roomwidths Continued
Conditional Inference: Gastrointestinal Damage
Conditional Inference: Birth Defects
Inference Exercises
Inference Exercise Answers (part 1)
Inference Exercise Answers (part 2)

Analysis of Variance (ANOVA)

Partial Exercise Solution (part 1)
Partial Exercise Solution (part 2)
Analysis of Variance (ANOVA) Studies (slides)
Weight Gain in Rats (Rcmdr)
Finish Weight Gain then Foster Feeding in Rats
Water Hardness Revisited
Male Egyptian Skulls (part 1)
Male Egyptian Skulls (part 2)
More Exercises

Linear Modeling

What is Linear Modeling? (slides)
Estimating the Age of the Universe (slides and script, part 1)
Estimating the Age of the Universe (script, part 2)
Age of the Universe (script, part 3)
Cloud Seeding (slides and script, part 1)
Cloud Seeding (script, part 2)
Cloud Seeding (script, part 3)
Cloud Seeding Diagnostic Plots (part 4)

Validating Linear Models (aka 'Model Checking')

Model Checking (part 1)
Model Checking (part 2)
Model Checking (part 3)
Model Checking (part 4)
Model Checking (part 5)
Model Checking (part 6)

Generalized Linear Modeling (GLMs)

Generalized Linear Models (slides)
ESR and Plasma Proteins (part 1)
ESR and Plasma Proteins (part 2)
ESR and Plasma Proteins (part 3)
Women's Role in Society (part 1)
Women's Role in Society (part 2)
Women's Role in Society (part 3)
Colonic Polyps
Driving and Back Pain

Survival Analysis

What is Survival Analysis? (slides)
Glioma Radioimmunotherapy
Breast Cancer Survival

Smoothers and Generalized Additive Modeling (GAMs)

Smoothers and GAMs (slides, part 1)
Smoothers and GAMs (slides, part 2)
Air Pollution in U.S. Cities
Kyphosis (part 1)
Kyphosis (part 2)
Non-Parametric Smoothers (part 1)
Lowess Smoothers (part 2)
Lowess Smoothers (part 3)
GAM with Binary Isolation Data
GAM Examples using mgcv Package (part 1)
GAM Examples using mgcv Package (part 2)
GAM Examples using mgcv Package (part 3)
Strongly Humped Data (part 1)
Strongly Humped Data (part 2)

Linear Mixed-Effects Models

Linear Mixed-Effects Models (slides, part 1)
Linear Mixed-Effects Models (slides, part 2)
Beat the Blues Slides and Data
Beat the Blues Study (part 2)
Beat the Blues Study Boxplots and Data Transformation (part 3)
Run Beat the Blues Models (part 1)
Run Beat the Blues Models (part 2)

Generalized Estimating Equations (GEE)

Generalized Estimating Equations (GEE) (slides, part 1)
Generalized Estimating Equations (GEE) (slides, part 2)
GEE with Beat the Blues as Binomial GLM (part 1)
GEE with Beat the Blues as Binomial GLM (part 2)
Respiratory Illness with Binary Response Variable (part 1)
Respiratory Illness with Binary Response Variable (part 2)
Respiratory Illness with Binary Response Variable (part 3)
Respiratory Illness with Binary Response Variable (part 4)

Split-Plot and Nested Designs

Irrigation Study Split-Plot Design (part 1)
Irrigation Study Split-Plot Design (part 2)
Comparing the Irrigation Split-Plot Models
Hierarchical Variance Components (part 1)
Hierarchical Variance Components (part 2)
Mixed-Effects Temporal Pseudo-Replication and Exercises
Farms Domain: Comparing Mixed versus Linear Intercepts and Slopes (part 1)
Farms Domain: Comparing Mixed versus Linear Intercepts and Slopes (part 2)
Farms Domain: Comparing Models (part 3)
Childhood Diseases Revisited: Model Checking

Simultaneous Inference and Multiple Comparisons

Simultaneous Inference for Multiple Comparisons (part 1)
Simultaneous Inference for Multiple Comparisons (part 2)
Deer Browsing (part 1)
Deer Browsing (part 2)
Cloud Seeding Revisited

Screenshots

Comprehensive Linear Modeling with R - Screenshot_01Comprehensive Linear Modeling with R - Screenshot_02Comprehensive Linear Modeling with R - Screenshot_03Comprehensive Linear Modeling with R - Screenshot_04

Reviews

Tim
November 10, 2022
This is a good course and excellent value for money. Unfortunately, unlike other courses the tutor does not work through the exercises.
Alberto
September 13, 2022
Simply terrible. Impossible to follow, very unclear explanations. The course focusses to heavily on R Commander, leaving aside important matters. I wish I could have my money back...
Michael
October 29, 2021
Professor Hubona courses and lectures are the most comprehensive and thorough I have found. Thanks to his content, I have expanded my skillsets and advanced in my job position at work. People ask me how to improve their skills and I direct them to these courses.
Eric
December 5, 2020
Videos are cut in half for no apparent reason. It makes the course feel choppy and disconnected. Examples feel very rushed. Also, since the decision was made to use R Commander (presumably to abstract away some of the overhead of having to learn how to code in R), I would have assumed that there would have been a much larger emphasis placed on the theoretical foundations behind the statistical techniques presented in the course, because again, since we are using R Commander to lighten the programming load, it would have made sense to really focus on the theory and then use R Commander to make it easy to see how the theory is actually applied with minimal coding overhead. I already have a strong background in Python and am comfortable enough in R to not need R Commander, but I was really looking for both the theoretical background in GLMs and how to implement the theoretical concepts in a programming language. I got some decent code for running GLMs/Statistical Tests however, so the course at least wasn't a total waste.
James
January 6, 2018
I am a little confused when we move back and forth between the commander and the standard R script. I think I'll get it after I practice.
Edgar
December 13, 2017
The best thing about this course is that the lecturer provides more than one example for each topic. However, you do need to use "The R Book" and "A Handbook of Statistical Analysis using R" to fully follow along.
DAVid
March 29, 2017
porque veo que me entero de los contenidos...explica muy claro y en todo momento se ve el código utilizado.
Jessica
January 10, 2017
Easy to follow, understand and I like that the Professor gives helpful hints along the way about what to look for to help interpret data graphs.
John
September 19, 2016
Seems more like a demonstration of R Commander than actual regression modeling. Plus, the other courses by Prof. Hubona use R Studio. Not sure why the switch?
Henri
August 19, 2016
Lots of great content, but a bit difficult to capture key points as he move along so fast. I have stop and copy the screen repeatedly.
Matt
July 25, 2016
I wish I could get my money back. Simply terrible. Zero programming. He uses Rcmdr which is all point and click. If you're using R who wants point and click? You can look at the code Rcmdr generates so I guess that's something. He's SO LONG WINDED. I love data science and his lectures had me falling asleep. Plus I'm not 100% in love with a lot of his explanations. He spends a lot of time doing menial tasks. Not a fan. Maybe a good class for a super beginner, but even that is a huge maybe.
William
April 29, 2016
This is really unique material presented by a very knowledgeable guy. The videos can kind of drag and I wish that he would buy a different mouse (or just stop using it so much), and just get to the point already, but hey, where else are going to find content like this?
Matt
February 25, 2016
Somewhat wish R commander wasn't used so heavily as it appears outdated and not completely necessary. Like multiple examples in each section, though, which helps understanding.
Jose
February 23, 2016
The quality of the presentation diminishes as the course progresses and the stitching of the lectures becomes somewhat sloppy towards the end. I still think it is a very good intro to the subject.
Shankha
January 4, 2016
The course covers all important topics. However, this course is not for building concepts but to get a hands-on training of applying the concepts using R. A brief reading up on the section (either online or a text book) before starting a section will help a lot.

Charts

Price

Comprehensive Linear Modeling with R - Price chart

Rating

Comprehensive Linear Modeling with R - Ratings chart

Enrollment distribution

Comprehensive Linear Modeling with R - Distribution chart

Related Topics

690278
udemy ID
12/6/2015
course created date
11/22/2019
course indexed date
Bot
course submited by