Midterm Exam sample questions
Psychology 2812B FW23
Multiple Choice (1 pt each)
- To grab certain rows of a data tibble, we can use the following dplyr command:
filter()
select()
slice()
arrange()
- In the figure shown below, there is a ______ correlation between X and Y:
- positive
- negative
- zero
- none of the above
- In multiple regression, variance inflation factors (VIFs) are a measure of:
- the influence of a single observation on heteroscedasticity
- whether or not the predictors are too highly correlated with each other
- the variance of the residuals
- the influence of a single observation on the estimate of the regression line
- In linear regression the line of best fit is found by:
- minimizing the sum of squared errors
- minimizing the sum of the residuals
- minimizing the slope and intercept of the regression line
- minimizing the sum of absolute errors
- In multiple regression with two predictor variables X_{1} and X_{2} we estimate:
- two slopes and two intercepts
- one slope and two intercepts
- two slopes and one intercept
- one slope and one intercept
Short Answer (2 pts each)
Jessie estimates a linear regression model to predict monthly spending on groceries (y) from monthly income (x). They find that the estimated regression equation is y = 0.5 + 0.2x and that the p-value for the slope is p=0.02. What does the slope coefficient 0.2 mean? What does the p-value 0.02 mean?
Explain why one might prefer to describe the goodness of fit of a regression model using the standard error of the estimate s_{est} instead of r^{2}.
Long Answer (5 pts each)
- Ripley esimates a multiple linear regression model to predict credit card spending (Y) from monthly income (X_{1}), age (X_{2}), and number of children (X_{3}). They find that the estimated regression equation is Y = 100 + 0.2X_{1} + 0.1X_{2} - 0.5X_{3}. Describe the steps you would take to refine the model and explain the rationale for each step.