Exam PA Study Manual
Video lessons
1
Welcome
1.1
How to access the practice exams
1.2
About the author
1.3
Contribute
2
The Exam
3
Learning
4
Getting started
4.1
Download the data
4.2
Download ISLR
4.3
New users
5
R programming
5.1
Notebook chunks
5.2
Basic operations
5.3
Lists
5.4
Functions
5.5
Data frames
5.6
Pipes
6
Data manipulation
6.1
Look at the data
6.2
Transform the data
6.3
Exercises
6.4
Answers to exercises
7
Visualization
7.1
Create a plot object (ggplot)
7.2
Add a plot
7.3
Data manipulation chaining
8
Introduction to Modeling
8.1
Model Notation
8.2
Ordinary least squares (OLS)
8.3
Example
9
Generalized linear models (GLMs)
9.1
Model form
9.2
Example
9.3
Reference levels
9.4
Interactions
9.4.1
Poisson Regression
9.4.2
Tweedie regression
9.4.3
Stepwise subset selection
9.4.4
Advantages and disadvantages
10
Logistic Regression
10.1
Model form
10.2
Example
10.3
Classification metrics
10.3.1
Area Under the ROC Curv (AUC)
11
Penalized Linear Models
11.1
Ridge Regression
11.2
Lasso
11.3
Elastic Net
11.4
Advantages and disadvantages
12
Tree-based models
12.1
Decision Trees
12.1.1
Model form
12.1.2
Advantages and disadvantages
12.2
Ensemble learning
12.2.1
Bagging
12.2.2
Boosting
12.3
Random Forests
12.3.1
Model form
12.3.2
Example
12.3.3
Variable Importance
12.3.4
Partial dependence
12.3.5
Advantages and disadvantages
12.4
Gradient Boosted Trees
12.4.1
Parameters
12.4.2
Example
12.4.3
Advantages and disadvantages
12.4.4
Exercises
13
A Mini-Exam Example
13.1
Project Statement
13.1.1
Describe the data (1 point)
13.1.2
Create a histogram of the claims and comment on the shape (1 point)
13.1.3
Fit a linear model (1 point)
13.1.4
Describe the relationship between age, sex, and claim costs (1 point)
13.1.5
Write a summary of steps 1-4 in non-technical language (1 point)
14
Practice Exam
15
Prior Exams
Published with bookdown
Exam PA Study Manual
15
Prior Exams
There are the exams and solutions published by the SOA.