Exam SRM - Qualitative Questions
Supervised statistical learning involves building a statistical model for predicting ________ based on one
or more inputs.
A. an output
B. a qualitative output
C. a quantitative output - correct answer ✔✔A
Problems with a ________ are referred to as classification problems.
A. quantitative target
B. qualitative target
C. quantitative predictor
D. qualitative predictor - correct answer ✔✔B
f explains the relationship between the dependent variable and the independent variables. What are the
two main reasons we may want to estimate f?
A. accuracy and inference
B. accuracy and interpretability
C. prediction and inference
D. prediction and interpretability
E. flexibility and interpretability - correct answer ✔✔C
k-fold cross-validation has a computational advantage over ________.
A. Leave-one-out cross-validation
,B. Validation set
C. Both (A) and (B) are correct
D. Both (A) and (B) are incorrect - correct answer ✔✔A
Brad has a dataset with n observations and p predictors. He uses k-fold cross-validation to estimate the
test error.
How many times is the first observation used to validate a model? - correct answer ✔✔1
As the tuning parameter λ increases, the ________ of a ridge regression model increases.
A. variance
B. squared bias
C. flexibility
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔B
Fill in the blank with the correct answer.
As the budget parameter a decreases, the ________ of a lasso regression model decreases.
A. flexibility
B. squared bias
C. variance
D. (A) and (B) are correct
E. (A) and (C) are correct - correct answer ✔✔E
Using a greater number of directions increases the ________ of a partial least squares model.
A. variance
B. squared bias
,C. training error
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔A
In k-nearest neighbors, increasing k decreases the ________ of the model.
A. squared bias
B. variance
C. irreducible error
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔B
You are given the following statements about different resampling methods:
I. Leave-one-out cross-validation (LOOCV) is a special case of k-fold cross-validation.
I. k-fold cross-validation has higher variance than LOOCV when k<n<.
II. LOOCV tends to overestimate the test error rate in comparison to the validation set approach.
Determine which of the above statements are correct. - correct answer ✔✔I
Consider the following statements regarding the tuning parameter λ in the lasso model-fitting procedure:
I. As λ increases, the number of predictors in the chosen model will increase.
II. As λ increases, the bias of the coefficient estimates in the chosen model will increase.
III. As λ increases, the variance of the predictions made by the chosen model will increase.
Determine which of the above statements are true. - correct answer ✔✔II
Determine which of the following statements about hierarchical clustering is/are true.
, I. The method may not assign extreme outliers to any cluster.
II. The resulting dendrogram can be used to obtain different numbers of clusters.
III. The method is not robust to small changes in the data. - correct answer ✔✔II, III
Determine which of the following statements about tree pruning is/are true.
I. Overfitting is likely an issue in an unpruned decision tree created using recursive binary splitting.
II. A pruned tree likely has a lower bias compared to an unpruned tree.
III. In cost complexity pruning, if the tuning parameter, α, is zero, the algorithm results in the largest
decision tree - correct answer ✔✔I, III
Determine which of the following approaches can be used to detect multicollinearity.
I. Inspect the correlation matrix
II. Calculate variance inflation factors
III. Inspect the residuals versus fitted values plot - correct answer ✔✔I, II
Consider the following statements:
I. The proportion of variance explained by an additional principal component never decreases as more
principal components are added.
II. The cumulative proportion of variance explained never decreases as more principal components are
added.
III. Using all possible principal components provides the best understanding of the data.
IV. A scree plot provides a method for determining the number of principal components to use.
Determine which of the statements are correct. - correct answer ✔✔II, IV
You are given the following three statistical learning tools:
Supervised statistical learning involves building a statistical model for predicting ________ based on one
or more inputs.
A. an output
B. a qualitative output
C. a quantitative output - correct answer ✔✔A
Problems with a ________ are referred to as classification problems.
A. quantitative target
B. qualitative target
C. quantitative predictor
D. qualitative predictor - correct answer ✔✔B
f explains the relationship between the dependent variable and the independent variables. What are the
two main reasons we may want to estimate f?
A. accuracy and inference
B. accuracy and interpretability
C. prediction and inference
D. prediction and interpretability
E. flexibility and interpretability - correct answer ✔✔C
k-fold cross-validation has a computational advantage over ________.
A. Leave-one-out cross-validation
,B. Validation set
C. Both (A) and (B) are correct
D. Both (A) and (B) are incorrect - correct answer ✔✔A
Brad has a dataset with n observations and p predictors. He uses k-fold cross-validation to estimate the
test error.
How many times is the first observation used to validate a model? - correct answer ✔✔1
As the tuning parameter λ increases, the ________ of a ridge regression model increases.
A. variance
B. squared bias
C. flexibility
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔B
Fill in the blank with the correct answer.
As the budget parameter a decreases, the ________ of a lasso regression model decreases.
A. flexibility
B. squared bias
C. variance
D. (A) and (B) are correct
E. (A) and (C) are correct - correct answer ✔✔E
Using a greater number of directions increases the ________ of a partial least squares model.
A. variance
B. squared bias
,C. training error
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔A
In k-nearest neighbors, increasing k decreases the ________ of the model.
A. squared bias
B. variance
C. irreducible error
D. (A) and (C) are correct
E. (B) and (C) are correct - correct answer ✔✔B
You are given the following statements about different resampling methods:
I. Leave-one-out cross-validation (LOOCV) is a special case of k-fold cross-validation.
I. k-fold cross-validation has higher variance than LOOCV when k<n<.
II. LOOCV tends to overestimate the test error rate in comparison to the validation set approach.
Determine which of the above statements are correct. - correct answer ✔✔I
Consider the following statements regarding the tuning parameter λ in the lasso model-fitting procedure:
I. As λ increases, the number of predictors in the chosen model will increase.
II. As λ increases, the bias of the coefficient estimates in the chosen model will increase.
III. As λ increases, the variance of the predictions made by the chosen model will increase.
Determine which of the above statements are true. - correct answer ✔✔II
Determine which of the following statements about hierarchical clustering is/are true.
, I. The method may not assign extreme outliers to any cluster.
II. The resulting dendrogram can be used to obtain different numbers of clusters.
III. The method is not robust to small changes in the data. - correct answer ✔✔II, III
Determine which of the following statements about tree pruning is/are true.
I. Overfitting is likely an issue in an unpruned decision tree created using recursive binary splitting.
II. A pruned tree likely has a lower bias compared to an unpruned tree.
III. In cost complexity pruning, if the tuning parameter, α, is zero, the algorithm results in the largest
decision tree - correct answer ✔✔I, III
Determine which of the following approaches can be used to detect multicollinearity.
I. Inspect the correlation matrix
II. Calculate variance inflation factors
III. Inspect the residuals versus fitted values plot - correct answer ✔✔I, II
Consider the following statements:
I. The proportion of variance explained by an additional principal component never decreases as more
principal components are added.
II. The cumulative proportion of variance explained never decreases as more principal components are
added.
III. Using all possible principal components provides the best understanding of the data.
IV. A scree plot provides a method for determining the number of principal components to use.
Determine which of the statements are correct. - correct answer ✔✔II, IV
You are given the following three statistical learning tools:
