1. Statistical Learning

Question 1

What is the difference between supervised and unsupervised learning

Answer 1

Supervised: has response variable

Unsupervised: analyzes the observations or the variables without a response variable. Main idea is to identify patterns that may exist in the data.

Question 2

What is the difference between a parametric method and a non-parametric method?

Answer 2

Parametric: specifies a functional form for f that includes free parameters (parameters that we estimate).

Non-parametric: makes no assumption about f’s functional form, f is then mainly algorithmic

Question 3

What are the two main objectives to supervised learning?

Answer 3

Inference and prediction

Question 4

A methods predictive strength coincides with its _______

Answer 4

Flexibility

Question 5

What does one’s ability to make inferences depend on?

Answer 5

The interpretability of the model

Question 6

Why are flexibility and interpretability inversely related?

Answer 6

Because if a model is very flexibly (fits the data too well), then it is likely that the model is complicated (not easily interpreted)

Question 7

Methods that are less flexible, but more interpretable?

Answer 7

Lasso and subset selection

Question 8

Methods that are moderately flexible and interpretable?

Answer 8

Least squares
Regression trees
Classification trees

Question 9

Methods that are very flexible, but not interpretable?

Answer 9

Bagging

Boosting

Question 10

Do flexibility and predictive accuracy go hand in hand? Why or why not

Answer 10

They do not. When a method is highly flexible, that means that it is flexible on the training data, not the test data.

Highly flexible = perfect predictions on past data

Question 11

What does the bias of a model speak to?

Answer 11

The bias relates to the average closeness between f-hat and f.

Question 12

What is the difference between prediction and inference?

Answer 12

Prediction: output of f-hat
Inference: comprehension of f

Question 13

In KNN regression, which of the following are true as k increases?
A. Flexibility increases
B. Squared bias increases
C. Variance decreases

Answer 13

As k increases, the model becomes less flexible (worse at predicting)
A. False
B. True
C. True

Question 14

Rank these three in terms of flexibility, in decreasing order.
Linear regression
Ridge regression
Regression tree

Answer 14

Most flexible: regression tree
Linear regression
Least flexible: Ridge regression

Question 15

Rank in decreasing order of flexibility.
Linear regression
Lasso regression
Boosting

Answer 15

Boosting
Regression
Lasso

Question 16

Which of these modelling techniques perform variable selection?
Lasso 
Partial least squares
PCA
ridge

Answer 16

Only lasso

PCA and partial least squares: both use all variables in determining the partial least squares directions and the PCs

Question 17

Is unsupervised learning used to draw inferences from datasets withoIt a specified response variable?

Answer 17

Yes

Question 18

Does the accuracy of a prediction for Y depend on the irreducible and reducible error?

Answer 18

Yes

Question 19

Correlation and covariance formula. What are the boundaries for each of these values?

Answer 19

Formula

Question 20

Which statements are true regarding scatter plots?
A. If it shows a quadratic relationship, the variables’ sample correlation will be around 0.
B. They are not ideal for detecting non-linear relationships between two variables

Answer 20

Both false.

The quadratic curve could be anywhere within the scatter plot, therefore making it possible to have a negative/ positive correlation.

They are ideal for detecting any relationship between two variables.

Question 21

True or false. Categorical variables can take on an unlimited number of values.

Answer 21

False. Limited number of values.