MBA613 Final Exam UPDATED ACTUAL Exam Questions and CORRECT Answers

MGRADES



MBA613 Final Exam UPDATED ACTUAL
Exam Questions and CORRECT Answers
n-1 - CORRECT ANSWER✅✅- It's standard practice to create ____ columns instead of n
(where n is the number of unique categories)


Linear Regression - CORRECT ANSWER✅✅- statistical model used to predict a continuous
numeric value by finding the best-fitting straight line through the data


Linear Regression - CORRECT ANSWER✅✅- Used to predict things like revenue, price,
scores


Linear Regression - CORRECT ANSWER✅✅- Calculates the weighted Sum of input
features, where each feature has a coefficient that reflects its impact on the outcome


Strength for Linear Regression - CORRECT ANSWER✅✅- Simple and Interpretable: Easy to
explain and visualize


Strength for Linear Regression - CORRECT ANSWER✅✅- Coefficients show feature
importance: When inputs are standardized, you can compare their influence


Strength for Linear Regression - CORRECT ANSWER✅✅- Fast to train and evaluate: Useful
for large datasets or as a baseline model


Limitation for Linear Regression - CORRECT ANSWER✅✅- Assumes linearity: Not suited
for curved or complex patterns


Limitation for Linear Regression - CORRECT ANSWER✅✅- Sensitive to outliers and
multicollinearity: Large deviations or strong correlated features can distort results

,MGRADES


Limitation for Linear Regression - CORRECT ANSWER✅✅- Requires numeric inputs:
Categorical variables must be encoded numerically.


Linear Regression - CORRECT ANSWER✅✅- There is a linear relationship between input
variables and the output


Linear Regression - CORRECT ANSWER✅✅- The independent variables are not highly
correlated (no multicollinearity)


Linear Regression - CORRECT ANSWER✅✅- Features must be numeric



R-squared (R²) - CORRECT ANSWER✅✅- Proportion of variance in the dependent variable
explained by the model.


R-squared (R²) - CORRECT ANSWER✅✅- Closer to 1 means better fit



MAE (Mean Absolute Error) - CORRECT ANSWER✅✅- Average absolute difference
between actual and predicted values


MSE (Mean Squared Error) - CORRECT ANSWER✅✅- Average of the squared differences.



MSE (Mean Squared Error) - CORRECT ANSWER✅✅- Penalizes larger errors more heavily



Linear Regression - CORRECT ANSWER✅✅- Hyperparameters for ________: None
directly, but the choice and scaling of features affect performance


Yes, especially if comparing coefficients. You can not scale if your primary goal is to interpret
coefficients in their original units. - CORRECT ANSWER✅✅- Should you scale the data for
Linear Regression?

, MGRADES


Yes, but you must convert them to numeric. One-hot encoding is preferred for linear regression
because it avoids assigning arbitrary numeric values that can distort relationships - CORRECT
ANSWER✅✅- Can you use Categorical Variables for Linear Regression?



Logistic Regression - CORRECT ANSWER✅✅- A statistical model used for binary
classification problems


Logistic Regression - CORRECT ANSWER✅✅- e.g. yes/ no, win/lose



Logistic Regression - CORRECT ANSWER✅✅- It outputs probabilities between 0 and 1
using the SIGMOID FUNCTION and classifies based on a threshold (usually 0.5)


Strength for Logistic Regression - CORRECT ANSWER✅✅- Interpretable coefficients:
Explain how features affect the odds of an event


Strength for Logistic Regression - CORRECT ANSWER✅✅- Predicts probability: Useful for
scoring and risk evaluation


Strength of Logistic Regression - CORRECT ANSWER✅✅- Efficient: Performs well on
large datasets


Limitations of Logistic Regression - CORRECT ANSWER✅✅- Assumes linearity in log-
odds: Cannot capture complex relationships unless features are transformed


Limitation of Logistic Regression - CORRECT ANSWER✅✅- Limited expressiveness: Not
suited for problems that need complex decision boundaries


Assumption of Logistic Regression - CORRECT ANSWER✅✅- Features are numeric and
relatively independent