ISYE 6414-REGRESSION ANALYSIS
PROJECT REPORT COMPREHENSIVE STUDY
GUIDE 2026 FULL QUESTIONS AND
SOLUTIONS GRADED A+
◍ Model with many predictors have high bias but low variance..
Answer: False - low bias and high variance
◍ The Box-Cox transformation is commonly used to improve upon the
linearity assumption..
Answer: False
◍ We can use residual analysis to conclusively determine the assumption
ofindependence.
Answer: False - we can only determine uncorrelated errors.
◍ Residual analysis can only be used to assess uncorrelated errors..
Answer: False
◍ In ANOVA, the objective of residual analysis is to.
Answer: evaluate departures from the model assumptions.
◍ Assuming that the data are normally distributed, under the simple linear
model, the estimated variance has the following sampling distribution:.
Answer: Chi-squared with n-2 degrees of freedom.
◍ Time series data typically results in violations of what assumption?.
Answer: Independence
◍ In regression, predicting variables are random variables..
Answer: False
◍ The Mean Squared Error in SLR is an estimator for what?.
, Answer: Sample Variance.
◍ The slope of a linear regression equation is an example of a correlation
coefficient..
Answer: False - the correlation coefficient is the r value. Will have the same
+ or - sign as the slope.
◍ Linear regression can have terms where the predicting variable is raised to
some exponential power..
Answer: True
◍ Explanatory variable is one that explains changes in the response variable.
Answer: TRUE
◍ In a multiple regression problem, a quantitative input variable x is replaced
by x −mean(x). The R-squared for the fitted model will be the same.
Answer: True
◍ The mean sum of square errors in ANOVA measures the variability between
groups?.
Answer: False
◍ We detect departure from the assumption of constant variance.
Answer: when the residuals vs fitted values are larger in the ends but smaller
in the middle.
◍ If p is larger than n, stepwise is feasible.
Answer: TRUE - for forward, but not backward
◍ Multiplying a variable by 10 in LASSO regression, decreases the chance
that thecoefficient of this variable is nonzero..
Answer: False - I am not sure why anyone would think this would be true.
◍ If the outcome variable is quantitative and all explanatory variables take
values 0 or1, a logistic regression model is most appropriate..
Answer: False - More research is necessary to determine the correct model.
◍ Violation of the linearity/mean 0 assumption in SLR can lead to problems
with what?.
, Answer: Intercepts
◍ The larger K is, the larger the number of folds, the less bias the estimate of
the classification the error is but has higher variability..
Answer: True
◍ The regression coefficient corresponding to one predictor in MLR is
interpreted in terms of the estimated expected change in the response
variable when there is a change of one unit in the corresponding predicting
variables holding all other predictors fixed..
Answer: True
◍ For large sample size data, the distribution of the test statistic, assuming the
null hypothesis, is a chi-squared distribution.
Answer: True
◍ In ANOVA number of degrees of freedom of the chi-square distribution for
the pooled variance estimator is N-k where k is the number of groups?.
Answer: True
◍ Least Square Elimination (LSE) cannot be applied to GLM models..
Answer: False - it is applicable but does not use data distribution
information fully.
◍ In evaluating a simple linear model.
Answer: there is a direct relationship between the coefficient of
determination and the correlation between the predicting and response
variables.
◍ The estimators fo the linear regression model are derived by?.
Answer: Minimizing the sum of squared differences between the observed
and expected values of the response variable.
◍ What equation is SSE/(n-2).
Answer: Mean squared error
◍ If the Cook's distance for any particular observation is greater than one, that
datapoint is definitely a record error and thus needs to be discarded..
PROJECT REPORT COMPREHENSIVE STUDY
GUIDE 2026 FULL QUESTIONS AND
SOLUTIONS GRADED A+
◍ Model with many predictors have high bias but low variance..
Answer: False - low bias and high variance
◍ The Box-Cox transformation is commonly used to improve upon the
linearity assumption..
Answer: False
◍ We can use residual analysis to conclusively determine the assumption
ofindependence.
Answer: False - we can only determine uncorrelated errors.
◍ Residual analysis can only be used to assess uncorrelated errors..
Answer: False
◍ In ANOVA, the objective of residual analysis is to.
Answer: evaluate departures from the model assumptions.
◍ Assuming that the data are normally distributed, under the simple linear
model, the estimated variance has the following sampling distribution:.
Answer: Chi-squared with n-2 degrees of freedom.
◍ Time series data typically results in violations of what assumption?.
Answer: Independence
◍ In regression, predicting variables are random variables..
Answer: False
◍ The Mean Squared Error in SLR is an estimator for what?.
, Answer: Sample Variance.
◍ The slope of a linear regression equation is an example of a correlation
coefficient..
Answer: False - the correlation coefficient is the r value. Will have the same
+ or - sign as the slope.
◍ Linear regression can have terms where the predicting variable is raised to
some exponential power..
Answer: True
◍ Explanatory variable is one that explains changes in the response variable.
Answer: TRUE
◍ In a multiple regression problem, a quantitative input variable x is replaced
by x −mean(x). The R-squared for the fitted model will be the same.
Answer: True
◍ The mean sum of square errors in ANOVA measures the variability between
groups?.
Answer: False
◍ We detect departure from the assumption of constant variance.
Answer: when the residuals vs fitted values are larger in the ends but smaller
in the middle.
◍ If p is larger than n, stepwise is feasible.
Answer: TRUE - for forward, but not backward
◍ Multiplying a variable by 10 in LASSO regression, decreases the chance
that thecoefficient of this variable is nonzero..
Answer: False - I am not sure why anyone would think this would be true.
◍ If the outcome variable is quantitative and all explanatory variables take
values 0 or1, a logistic regression model is most appropriate..
Answer: False - More research is necessary to determine the correct model.
◍ Violation of the linearity/mean 0 assumption in SLR can lead to problems
with what?.
, Answer: Intercepts
◍ The larger K is, the larger the number of folds, the less bias the estimate of
the classification the error is but has higher variability..
Answer: True
◍ The regression coefficient corresponding to one predictor in MLR is
interpreted in terms of the estimated expected change in the response
variable when there is a change of one unit in the corresponding predicting
variables holding all other predictors fixed..
Answer: True
◍ For large sample size data, the distribution of the test statistic, assuming the
null hypothesis, is a chi-squared distribution.
Answer: True
◍ In ANOVA number of degrees of freedom of the chi-square distribution for
the pooled variance estimator is N-k where k is the number of groups?.
Answer: True
◍ Least Square Elimination (LSE) cannot be applied to GLM models..
Answer: False - it is applicable but does not use data distribution
information fully.
◍ In evaluating a simple linear model.
Answer: there is a direct relationship between the coefficient of
determination and the correlation between the predicting and response
variables.
◍ The estimators fo the linear regression model are derived by?.
Answer: Minimizing the sum of squared differences between the observed
and expected values of the response variable.
◍ What equation is SSE/(n-2).
Answer: Mean squared error
◍ If the Cook's distance for any particular observation is greater than one, that
datapoint is definitely a record error and thus needs to be discarded..
