ISYE 6501 FINAL QUIZZES V1, V2 & V3
200 Practice Questions & Answers with Rationales | Georgia
Tech Intro to Analytics Modeling | A+ Guide
SECTION 1: MODEL SELECTION & PROBLEM TYPES (Questions 1–35)
1. For which type of problem is a fractional factorial design best suited?
A. Clustering
B. Classification
C. Prediction from timeseries data
D. Experimental design
E. Variable selection and/or prediction from feature data
Answer: D. Fractional factorial designs are used in experimental design to study the effects of multiple
factors efficiently by testing only a subset of all possible factor combinations.
2. For which type of problem is GARCH best suited?
A. Classification
B. Clustering
C. Experimental design
D. Prediction from timeseries data
E. Variable selection
Answer: D. GARCH (Generalized Autoregressive Conditional Heteroskedasticity) models are specifically
designed for timeseries data, especially to model and forecast changing volatility over time.
,3. Lasso regression is particularly useful for:
A. Increasing model bias
B. Handling time series seasonality
C. Variable selection
D. Creating clusters
Answer: C. Lasso (L1 regularization) shrinks some regression coefficients to exactly zero, effectively
selecting a subset of relevant features.
4. Which type of problem is linear regression best suited for?
A. Variable selection
B. Prediction from feature data
C. Experimental design
D. Clustering
E. Classification
Answer: B. Linear regression models the relationship between a dependent variable and one or more
independent variables, used for prediction and inference.
5. Principal Component Analysis (PCA) is classified under:
A. Supervised Classification
B. Feature Extraction / Dimensionality Reduction
C. Time Series Decomposition
D. Hypothesis Testing
,Answer: B. PCA is an unsupervised technique used for dimensionality reduction by transforming data
into a new set of uncorrelated variables (principal components).
6. McNemar's Test is used for:
A. Comparing means of two continuous variables
B. Paired categorical data
C. Clustering validation
D. Normality testing
Answer: B. McNemar's test is specifically applied to 2x2 contingency tables where subjects are paired or
matched, often used to compare classification models.
7. KNearest Neighbors (KNN) is best suited for which two problem types?
A. Clustering and Experimental Design
B. Classification and Prediction from feature data
C. Time series and Association Rules
D. Variable selection only
Answer: B. KNN is nonparametric. For classification, it votes on the nearest neighbors' labels; for
regression, it averages their values.
8. Which of the following is a nonparametric classification method?
A. Linear regression
, B. Logistic regression
C. kNearest Neighbors (kNN)
D. LASSO
Answer: C. kNN is nonparametric because it does not assume a specific functional form; the model is
defined by the data points themselves.
9. What is the primary purpose of A/B testing?
A. To test three or more alternatives simultaneously
B. To test two alternatives to see which one leads to better outcomes
C. To validate model assumptions before data collection
D. To determine the underlying distribution of data
Answer: B. A/B testing compares two alternatives (e.g., website designs, marketing strategies) to
determine which performs better.
10. Which type of analysis is GARCH best suited for?
A. Using feature data to predict the amount of something two time periods in the future
B. Using timeseries data to predict the amount of something two time periods in the future
C. Using timeseries data to predict the variance of something two time periods in the future
D. Using feature data to predict the probability of something happening
Answer: C. GARCH models the volatility (variance) of a time series over time, not the actual values of the
series.
200 Practice Questions & Answers with Rationales | Georgia
Tech Intro to Analytics Modeling | A+ Guide
SECTION 1: MODEL SELECTION & PROBLEM TYPES (Questions 1–35)
1. For which type of problem is a fractional factorial design best suited?
A. Clustering
B. Classification
C. Prediction from timeseries data
D. Experimental design
E. Variable selection and/or prediction from feature data
Answer: D. Fractional factorial designs are used in experimental design to study the effects of multiple
factors efficiently by testing only a subset of all possible factor combinations.
2. For which type of problem is GARCH best suited?
A. Classification
B. Clustering
C. Experimental design
D. Prediction from timeseries data
E. Variable selection
Answer: D. GARCH (Generalized Autoregressive Conditional Heteroskedasticity) models are specifically
designed for timeseries data, especially to model and forecast changing volatility over time.
,3. Lasso regression is particularly useful for:
A. Increasing model bias
B. Handling time series seasonality
C. Variable selection
D. Creating clusters
Answer: C. Lasso (L1 regularization) shrinks some regression coefficients to exactly zero, effectively
selecting a subset of relevant features.
4. Which type of problem is linear regression best suited for?
A. Variable selection
B. Prediction from feature data
C. Experimental design
D. Clustering
E. Classification
Answer: B. Linear regression models the relationship between a dependent variable and one or more
independent variables, used for prediction and inference.
5. Principal Component Analysis (PCA) is classified under:
A. Supervised Classification
B. Feature Extraction / Dimensionality Reduction
C. Time Series Decomposition
D. Hypothesis Testing
,Answer: B. PCA is an unsupervised technique used for dimensionality reduction by transforming data
into a new set of uncorrelated variables (principal components).
6. McNemar's Test is used for:
A. Comparing means of two continuous variables
B. Paired categorical data
C. Clustering validation
D. Normality testing
Answer: B. McNemar's test is specifically applied to 2x2 contingency tables where subjects are paired or
matched, often used to compare classification models.
7. KNearest Neighbors (KNN) is best suited for which two problem types?
A. Clustering and Experimental Design
B. Classification and Prediction from feature data
C. Time series and Association Rules
D. Variable selection only
Answer: B. KNN is nonparametric. For classification, it votes on the nearest neighbors' labels; for
regression, it averages their values.
8. Which of the following is a nonparametric classification method?
A. Linear regression
, B. Logistic regression
C. kNearest Neighbors (kNN)
D. LASSO
Answer: C. kNN is nonparametric because it does not assume a specific functional form; the model is
defined by the data points themselves.
9. What is the primary purpose of A/B testing?
A. To test three or more alternatives simultaneously
B. To test two alternatives to see which one leads to better outcomes
C. To validate model assumptions before data collection
D. To determine the underlying distribution of data
Answer: B. A/B testing compares two alternatives (e.g., website designs, marketing strategies) to
determine which performs better.
10. Which type of analysis is GARCH best suited for?
A. Using feature data to predict the amount of something two time periods in the future
B. Using timeseries data to predict the amount of something two time periods in the future
C. Using timeseries data to predict the variance of something two time periods in the future
D. Using feature data to predict the probability of something happening
Answer: C. GARCH models the volatility (variance) of a time series over time, not the actual values of the
series.
