Statistical Learning Inmas workshop
Welcome
0.1
Goals
0.2
Schedule
0.3
License
1
Pre-work
1.1
Installation
1.1.1
Create a project
1.2
Getting started in R
1.2.1
Learn about the “panels” or “panes” in RStudio
1.2.2
Arithmetic in R
1.2.3
R packages
1.2.4
Debugging and anti-frustration tips
1.3
Exploratory data analysis
1.3.1
Graphics in R
1.3.2
Single-variable plots in ggplot2
1.3.3
Quantitative variables
1.3.4
Categorical variables
1.3.5
ggplot2 syntax
1.3.6
Multiple-variable plots in ggplot2
1.3.7
Bells and Whistles
1.3.8
Summary statistics
1.4
RMarkdown and reproducible research
1.5
Practice
1.5.1
Load some data
2
Visualizing and characterizing variability
2.1
Pre-bootcamp review
2.1.1
Variable types, redux
2.1.2
Visualizing variability (in breakout rooms)
2.2
Modeling: choose, fit, assess, use
2.3
Linear models
2.4
Linear models in R
2.4.1
Linear model with one categorical predictor
2.5
Multiple linear regression
2.5.1
Models with 2 quantitative predictors
2.5.2
Models with 2 categorical predictors
2.5.3
Lots of variables
2.6
Homework
3
Data wrangling for model assessment
3.1
dplyr verbs
3.1.1
select()
3.1.2
filter()
3.1.3
arrange()
3.2
%>%, the pipe
3.3
Modeling conditions
3.3.1
Least squares
3.4
More dplyr verbs
3.4.1
summarize()
3.4.2
group_by()
3.4.3
mutate()
3.5
More model analysis
3.6
Bonus: comment on theory!
4
Inference using simulation methods
4.1
Reading in external data
4.1.1
Joining data
4.2
Fitting a model
4.3
Testing and training data
4.4
Inference based on distributional approximations
4.5
Simulation-based inference
4.6
Randomization (Permutation) Tests
4.7
Further Reading
4.8
Homework
5
More complex models
5.1
Wrapping up linear regression
5.2
Logistic regression
5.3
“Spaces”
5.3.1
Log-odds space
5.3.2
Odds space
5.3.3
Probability space
5.4
Fitting a logistic model
5.4.1
Interptetation
5.5
Visualizing the model
5.5.1
Probability space
5.5.2
Odds space
5.5.3
Log-odds space
5.6
Binning
5.7
Checking conditions
5.8
Comparing to a null model
5.9
Multiple logistic regression
5.10
strings and factors
5.11
More models
6
Homework
6.1
Understanding the basics
6.2
Visualize and describe
6.3
Formulate a research question
6.4
Try some models!
6.5
Communicate your findings
6.6
Places to find data
6.6.1
Inside R!
6.6.2
On the web
7
Learn more
7.1
Books
7.1.1
R/data science
7.1.2
Statistics/modeling
7.2
Online learning/courses
7.3
Videos
7.4
Blogs, etc
7.5
Twitter!
7.6
Communities
7.6.1
Online
7.6.2
“Physical”
References
I Post workshop notes
8
Visualizing and characterizing variability
8.1
Pre-bootcamp review
8.1.1
Variable types, redux
8.1.2
Visualizing variability (in breakout rooms)
8.2
Modeling: choose, fit, assess, use
8.3
Linear models
8.4
Linear models in R
8.4.1
Linear model with one categorical predictor
8.5
Multiple linear regression
8.5.1
Models with 2 quantitative predictors
8.5.2
Models with 2 categorical predictors
8.5.3
Lots of variables
8.6
Homework
9
Data wrangling for model assessment
9.1
dplyr verbs
9.1.1
select()
9.1.2
filter()
9.1.3
arrange()
9.2
%>%, the pipe
9.3
Modeling conditions
9.3.1
Least squares
9.4
More dplyr verbs
9.4.1
summarize()
9.4.2
group_by()
9.4.3
mutate()
9.5
More model analysis
9.6
Bonus: comment on theory!
10
Inference using simulation methods
10.1
Reading in external data
10.1.1
Joining data
10.2
Fitting a model
10.3
Testing and training data
10.4
Inference based on distributional approximations
10.5
Simulation-based inference
10.6
Randomization (Permutation) Tests
10.7
Further Reading
10.8
Homework
11
More complex models
11.1
Wrapping up linear regression
11.2
Logistic regression
11.3
Recall, probability and odds
11.4
“Spaces”
11.4.1
Log-odds space
11.4.2
Odds space
11.4.3
Probability space
11.5
Fitting a logistic model
11.5.1
Interptetation
11.6
Visualizing the model
11.6.1
Probability space
11.6.2
Odds space
11.6.3
Log-odds space
11.7
Binning
11.8
Checking conditions
11.9
Comparing to a null model
11.10
Multiple logistic regression
11.11
strings and factors
11.12
More models
Published with bookdown
Statistical Learning Inmas workshop
References