Which of the following are required assumptions in a multiple linear regression model?
There are 5 correct choices.
•
The mean of the error term has a normal distribution.
•
The error term has a normal distribution.
•
The errors are not correlated.
•
The mean of the residuals is zero.
•
The variance of the residuals is the same constant.
•
The mean of the error term is zero.
•
The residuals are not correlated.
•
The errors are independent.
•
The variance of the error term has a normal distribution.
•
The mean of the error term is the same constant.
•
The mean of the residuals is not correlated with the variance of the residuals.
•
The mean of the error term is not correlated with the variance of the error term.
•
The residuals are independent.
•
The variance of the error term is the same constant.
You made all of the correct selections.
You received a raw score of 100% on this question.
Question #2
In multiple regression, the residual degrees of freedom is given by: nk1, where n is the
total sample size and k is the number of independent variables. So, if a multiple
regression model includes 6 independent variables, and 57 observations on the y variable,
the residual df should be:
•
51
•
50
•
49
•
6
•
57
.
You received a raw score of 100% on this question.
Question #3
All Canadians have governmentfunded health insurance, which pays for any medial care
they require. However, when travelling out of the country, Canadians usually require
supplementary health insurance to cover the difference between the costs incurred for
emergency treatment and what the government program pays. To cover for the
difference, private insurance companies charge flatrate weekly rates, regardless of age.
Question #1
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentHowever, they realized that older people frequently incur greater medial emergency
expenses and decided to offer rates based on the age of the customer. To help determine
the new rates, one insurance company gathered data covering the age and mean daily
medical expenses of a random sample of 1348 Canadians. Answer the following
questions of
this
dataset.
First run a regression where AGE is the independent variable and EXPENSE is the
dependent variable.
(Note:in the regression window, you should see Residuals and there
should be four boxes. Make sure you check all four of them before you click ok. You
should notice that you will be given addition output besides the usual regression output)
.
1.
Even before you analyze the residuals you know that this is
cross sectional
data and therefore, it
cannot
suffer from autocorrelation.
To check whether the assumption of normality of the error term is satisfied, create
a histogram of the standardized residuals. Go to Tools > Data Analysis >
Histogram. Then select the Standardized Residuals you got in the regression
output as the Input Range. Also, check the Chart Output option in the bottom of
the dialog box.
2.
This is the end of the preview. Sign up
to
access the rest of the document.
 Spring '08
 Petry
 Regression Analysis, multicollinearity, independent variables

Click to edit the document details