Indicator variables: indicate how much variation exists in a multiple regression
ID: 3256376 • Letter: I
Question
Indicator variables:
indicate how much variation exists in a multiple regression model.
allow nominal variables to be used in a regression model.
create multicollinearity within a model.
can take on any value between 0 and 5.
A multiple regression model has the form y = 7 + 6 x1 + 3 x2 As x1 increases by 1 unit (holding x2 constant), y is expected to:
decrease by 3 units.
increase by 6 units.
decrease by 6 units.
increase by 3 units.
The residuals represent:
the difference between the actual Y values and the mean of Y.
the difference between the actual Y values and the predicted Y values.
the predicted value of Y for the average X value.
the square root of the slope.
a.indicate how much variation exists in a multiple regression model.
b.allow nominal variables to be used in a regression model.
c.create multicollinearity within a model.
d.can take on any value between 0 and 5.
Explanation / Answer
Indicator variables:
b. allow nominal variables to be used in a regression model.
Nominal variables are categorical variables such as Gender(Male, Female); Opinion(Good, Moderate, Bad) etc.. These variables cannot be used in a regression model as such as they are not numarical values. So we convert them into numerical values by assigning values 0, 1 2 etc to them. This allows it to be used as numerical values in regression.
A multiple regression model has the form y = 7 + 6 x1 + 3 x2 As x1 increases by 1 unit (holding x2 constant), y is expected to:
b. increase by 6 units.
This is beacuse the x1 has a positive coefficient of 6. So any subsequent increase in x1 will only increase the value of y (as the coefficient sign is positive). The magnitude by which this increase happens in 6 as we hold x2 a constant.
The residuals represent:
b. the difference between the actual Y values and the predicted Y values.
The residuals is the difference between the actual Y values and the values of Y which is predicted by the fitted model. It helps us to get an idea about how large the difference is between the actual and predicted value.