Statistics for Data Science and Business Analysis - A3. Normality and Homoscedasticity

Why is normal distribution important in regression analysis?

• It ensures the model has a zero mean.

• It prevents heteroscedasticity.

• It helps in making inferences from the model.

• It is required for creating the regression model.

What does the zero mean assumption imply in regression?

• The error terms should have equal variance.

• The model has no intercept.

• The regression line is the best fitting one.

• The error term is normally distributed.

What is homoscedasticity in the context of regression?

• Error terms have equal variance.

• Error terms are normally distributed.

• Error terms are independent.

• Error terms have a zero mean.

How can heteroscedasticity be identified in a dataset?

• By checking if the error terms have a zero mean.

• By observing a pattern in the variance of error terms.

• By ensuring the error terms are normally distributed.

• By confirming the model has an intercept.

Which method can help address heteroscedasticity in regression?

• Increasing the sample size.

• Ensuring a zero mean of error terms.

• Using a log transformation.

• Adding more independent variables.

What is a semi-log model in regression?

• A model with no transformations applied.

• A model where only the Y variable is transformed to log scale.

• A model where only the X variable is transformed to log scale.

• A model where both X and Y are transformed to log scale.

What does a log-log model imply in regression analysis?

• Neither X nor Y is transformed.

• Only Y is transformed to log scale.

• Only X is transformed to log scale.

• Both X and Y are transformed to log scale.