Quiz #4

Question 1

The functions that govern how disagreements among the predictions of ensemble models are reconciled are known as \_\_\_\_\_\_\_\_\_ functions.
  A. stacking
  B. sigmoid
  C. allocation
  D. combination

Answer 1

D. combination

Question 2

The recall of a model is a measure of the completeness of the results of its predictions. This measure has the same value as the \_\_\_\_\_\_\_\_\_\_\_\_ of the model.
  A. sensitivity
  B. specificity
  C. precision
  D. kappa

Answer 2

A. sensitivity

Question 3

Which of these is not a problem with the partitioning approach of the holdout method?
A. It’s not always possible to create representative partitions of a data set.
B. Some samples may have too many or too few difficult cases, easy-to-predict cases, or outliers.
C. Each partition may have a larger or smaller proportion of some classes.
D. Substantial portions of data must be reserved to test and validate the model.

Answer 3

A. It’s not always possible to create representative partitions of a data set.

Question 4

The ROC curve is a measure of the True Positive Rate against the \_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_ of a model.
  A. False Positive Rate
  B. False Negative Rate
  C. Specificity
  D. True Negative Rate

Answer 4

A. False Positive Rate

Question 5

One of the weaknesses of a Random Forest model is that unlike a decision tree, the model is not easily interpretable.
True
False

Answer 5

True

Question 6

One of the limitations to using the F-score is that it assumes that ________________________.
A. recall is always more important than precision
B. precision is always more important than recall
C. equal weight should be given to both precision and recall
D. the harmonic mean of precision and recall is zero

Answer 6

C. equal weight should be given to both precision and recall

Question 7

The sampling approach that creates a training set of equal length as the original data, using sampling with replacement, is known as \_\_\_\_\_\_\_\_\_\_\_\_\_\_\_.
  A. cross-validation
  B. stratified sampling
  C. bootstrapping
  D. equal length sampling

Answer 7

C. bootstrapping

Question 8

The AUC for a classifier with no predictive value is ___

Answer 8

0.5

Question 9

Classification algorithms usually have parameters that need to be set before the learning process begins. These parameters are known as \_\_\_\_\_\_\_\_\_\_\_\_\_.
  A. hyperparameters
  B. tuning grids
  C. supervised parameters
  D. parametric parameters

Answer 9

A. hyperparameters

Question 10

The error generated by a classifier during the training stage is know as the \_\_\_\_\_\_\_\_\_\_\_\_ error.
  A. validation
  B. holdout
  C. bootstrap
  D. resubstitution

Answer 10

D. resubstitution

Question 11

One of the major disadvantages of the leave-one-out cross-validation approach is that it _______________.
A. uses too much data
B. violates the holdout principle
C. is not a good predictor of future performance
D. is computationally expensive

Answer 11

D. is computationally expensive

Question 12

The AUC metric and ROC curve can be used interchangeably because if two models have the same or identical AUC values, they will always have the same ROC curve.
True
False

Answer 12

False

Question 13

The technique that sequentially builds strong learners as a linear combination of weak learners is known as \_\_\_\_\_\_\_\_\_\_.
  A. bumming
  B. bagging
  C. boosting
  D. bootstrap aggregation

Answer 13

C. boosting

Question 14

The meta-learning approach that utilizes the principle of creating a varied team of experts is known as an \_\_\_\_\_\_\_\_.
  A. bagged learner
  B. assemble
  C. meta-learner
  D. ensemble

Answer 14

D. ensemble

Question 15

The process of conducting a search to identify the optimal combination of hyperparameters to use for the learning process using a choice of evaluation methods and metrics is known as \_\_\_\_\_\_\_\_\_\_\_\_\_\_\_ tuning.
  A. automated parameter
  B. model settings
  C. search space
  D. automatic hyper

Answer 15

A. automated parameter

Question 16

One of the disadvantages of the random cross-validation approach is that some instances may not be used and others may be used more than once.
True
False

Answer 16

True

Question 17

The AUC for a perfect classifier is ____

Answer 17

1.0

Question 18

The kappa statistic is an adjustment of accuracy by accounting for the possibility of a correct prediction by chance alone.
True
False

Answer 18

True

Question 19

The goal of cross-validation is to \_\_\_\_\_\_\_\_\_\_\_\_\_ across the iterations.
  A. choose the coolest model
  B. improve the performance of a model
  C. evaluate future performance
  D. eliminate bad models

Answer 19

C. evaluate future performance

Question 20

Occam’s Razor states that when presented with competing hypothetical answers to a problem, one should select the answer that makes the most assumptions.
True
False

Answer 20

False