Free SOA Exam SRM (Statistics for Risk Modeling) Basics of Statistical Learning Practice Questions
Statistical learning concepts on SOA Exam SRM cover the bias-variance tradeoff, model complexity, cross-validation, and the distinction between supervised and unsupervised learning methods. This topic provides the theoretical framework for all predictive modeling on the exam.
Sample Questions
Question 1
Easy
Which of the following is an example of unsupervised learning?
Solution
E is correct.
Identifying natural groups (clustering) without predefined labels is unsupervised learning. The algorithm discovers patterns and structure in the data without a response variable to guide it.
Identifying natural groups (clustering) without predefined labels is unsupervised learning. The algorithm discovers patterns and structure in the data without a response variable to guide it.
Question 2
Medium
In the bias-variance tradeoff, bias refers to:
Solution
E is correct.
Bias measures the systematic error introduced by the modeling assumptions. It is the difference between the expected prediction (averaged over many training sets) and the true function value . A high-bias model makes strong assumptions that may not match the true relationship (underfitting).
Bias measures the systematic error introduced by the modeling assumptions. It is the difference between the expected prediction (averaged over many training sets) and the true function value . A high-bias model makes strong assumptions that may not match the true relationship (underfitting).
Question 3
Hard
In statistical learning, variance of a model refers to:
Solution
B is correct.
In the bias-variance tradeoff, variance refers to how much the estimated function changes across different training datasets. A model with high variance is very sensitive to the particular training data used: fitting it on different training sets produces substantially different predictions.
In the bias-variance tradeoff, variance refers to how much the estimated function changes across different training datasets. A model with high variance is very sensitive to the particular training data used: fitting it on different training sets produces substantially different predictions.