Linear regression in R for Data Scientists

Name: Linear regression in R for Data Scientists
Rating: 3.4 (15 reviews)

Learn the most important technique in Analytics with lots of business examples. From basic to advanced.

Created byFrancisco Juretig

Last updated 1/2016

English

What you'll learn

Model basic and complex real world problem using linear regression
Understand when models are performing poorly and correct it
Design complex models for hierarchical data
How to properly prepare the data for linear regression
When linear regression is not sufficient
Understand how to interpret the results and translate them to actionable insights

Course content

4 sections • 30 lectures • 7h 2m total length

Introduction2:25
Quick intro. Brief overview. What you will learn, and what you should learn before taking this course
Getting the data/code for this course0:03
Use the attached link resource for all the code/data used in this course.
What is linear regression, and what is this course about?6:11
A more complete overview of this course.
Why R?1:37
Advantages of R. Why it is the main statistical software nowadays? What are the advantages and disadvantages?
Setting up R. Understanding the basics7:36
Basic concepts in R. Installing packages. Vectors. Matrices. Working with dataframes and dates. Basic mathematical operations
Preparing the data in R19:41
Working with read.csv(). How to load csv files. We will review the basic data-processing techniques we will use in this course

Mathematical preliminaries (OPTIONAL)20:00
A quick overview of what are we doing when using OLS and the lm() function in R. Projection matrices. Residuals. Geometrical interpretation. Formulas for coefficients.
A first example in R17:49
Running our first example in R. Using the lm() function. How to interpret the coefficients, pvalues, ANOVA. F statistics
The likelihood - Ordinary least squares equivalence20:47
The equivalence between doing ML and OLS. Why these estimates are equal? We review an example done via the optim() function in R. Minimizing the sum of squares numerically
Linear regression assumptions
PValues17:32
How to interpret pvalues in the context of linear regression.
PValue hacking6:55
When are our pvalues contaminated? How can we avoid this?
A more realistic example19:49
A much more complex example of OLS.
Model Selection19:20
How to choose the best model? Why do we want models with few variables? How can we use the stepAIC() function and the AIC() function. What happens when we remove variables from our model?
Practical Quiz - Explaing Co2 Emissions
Choosing the best model
Residuals and plots14:09
We need our residuals to verify our OLS assumptions. How can we check: normality, homocedasticity, non-autocorrelation. How to read the qqplot() and some normality tests.
Influence plots and outlier detection19:17
The relationship between leverage, outliers, influence. How to use CookD statistic? How can we read the last chart that lm() produces?
Log transformations - Price Elasticities5:05
When do we need models with variables in logs()? Log-log models.
Residuals
Overfitiing13:58
Models with lots of variables might end up adjusting not to the true response, but to "noise". We use the DAAG package for cross-validation mean square error.
Prediction4:38
Using the predict() function in R. The difference between confidence intervals and prediction intervals. The difference between the variances of both predictions
Multicollinearity18:46
The consequences of multicollinearity. How can we detect it, and what are the options to deal with it? VIFs, and condition indexes
Heteroscedasticity, and how to solve it17:10
The problem of non constant variance. How can we identify it using the R plots. Using robust sandwich matrices via the sandwich() package
Autocorrelation, and how to solve it11:22
Detecting auto-correlation. Using the robust HAC matrix from the sandwich package. The ACF() function
Linear Regression
Monte Carlo18:44
Monte Carlo in Excel. Monte Carlo simulation in R creating our own function. Creating synthetic datasets
Monte Carlo

Hierarchical Models and linear regression19:58
An introduction to mixed models. What are the conceptual differences between mixed models, and fixed effects models. Simulating datasets with random effects via Monte Carlo in R.
Random effects - A philosophical discussion14:02
The possible definitions about random effects: A) the effects we don't care about B) the effects we can treat as becoming from an infinite population C) the effects not estimated by least squares D) the unobserved effects that change through time
A better mixed model example15:58
Simulating random effects for the intercept and the independent variables. The different slopes per group, and what is the interpretation
Computational Method behind the lmer() function19:39
We create our own function for maximizing the log-likelihood, and we compare this to lmer().
Mixed effects linear regression
Model results and residuals19:30
How to analyse the residuals from an lmer() object? Using the plots that R produces
Random vs Fixed effects
Advanced random effects modelling and nested effects19:27
Nested effects, crossed effects. The different operators we can use in lmer(). The different ways of defining the random effects
Multiple Comparisons19:59
The problem of multiple comparisons. Using the lmertest() package. Checking for significative differences. Comparing different levels of our categorical variables.

Requirements

Ideally some basic statistics and R, though neither is strictly necessary
Some previous experience manipulating Excel files

Description

Linear regression is the primary workhorse in statistics and data science. Its high degree of flexibility allows it to model very different problems. We will review the theory, and we will concentrate on the R applications using real world data (R is a free statistical software used heavily in the industry and academia). We will understand how to build a real model, how to interpret it, and the computational technical details behind it. The goal is to provide the student the computational knowledge necessary to work in the industry, and do applied research, using lineal modelling techniques. Some basic knowledge in statistics and R is recommended, but not necessary. The course complexity increases as it progresses: we review basic R and statistics concepts, we then transition into the linear model explaining the computational, mathematical and R methods available. We then move into much more advanced models: dealing with multilevel hierarchical models, and we finally concentrate on nonlinear regression. We also leverage several of the latest R packages, and latest research. We focus on typical business situations you will face as a data scientist/statistical analyst, and we provide many of the typical questions you will face interviewing for a job position. The course has lots of code examples, real datasets, quizzes, and video. The video duration is 4 hours, but the user is expected to take at least 5 extra hours working on the examples, data , and code provided. After completing this course, the user is expected to be fully proficient with these techniques in an industry/business context. All code and data available at Github.

Who this course is for:

People pursuing a career in Data Science
Statisticians needing more practical/computational experience
Data modellers
People pursuing a career in practical Machine Learning

Linear regression in R for Data Scientists

What you'll learn

Explore related topics

Course content

Introduction6 lectures • 38min

Linear regression: Ordinary Least Squares16 lectures • 4hr 5min

Linear regression: Mixed Effects Regression7 lectures • 2hr 9min

Robust linear regression1 lecture • 11min

Requirements

Description

Who this course is for: