(See attached file for full problem description)
In a regression analysis, the variable that is being predicted
must have the same units as the variable doing the predicting
is the independent variable
usually is denoted by X
is the dependent variable
None of the above answers is correct.
2. Which of the following statements is NOT correct about R-square?
It is called coefficient of determination, and used to evaluate regression results.
The value of R-square increases as more independent variables are added to a regression equation.
It shows how well the variation of all explanatory (independent) variables account for the variation of a dependent variable.
The closer its value gets to 1.0, the closer the variation of the dependent variable is accounted for by the variation of a particular explanatory variable.
It the value is near zero, it is safe to say that the regression equation is not good.
Shown below is a partial computer output from a regression analysis.
Predictor Coefficient StdError
Constant 10.00 2.00
X1 3.00 1.50
X2 4.00 2.00
X3 -2.50 -1.00
At alpha = 0.05, if the critical value of t = 2.12, is X1 significant?
No, because 1.50 < 2.12
No, because 2.00 < 2.12
Yes, because 3.00 > 2.12
Yes, because 2.00 < 2.12
No, because 3.00 > 2,12
4. A simple linear regression model can be represented as follows:
Y = a + bX + u
What is NOT a correct statement about u?
It is referred to as the "random" or "error" term.
Is does not give any systematic impact on Y.
Once the model (equation) is estimated, u accounts for the deviation from the estimated equation.
It is represented by the distance from the estimated straight line.
It is an independent variable that affects the dependent variable.
5. Which of the following statements is NOT correct about OLS method?
It finds the line that maximizes the sum of the squared deviation of each data point from the line.
It finds the line that minimizes the sum of the squared deviation of each data point from the line.
It finds the line that maximizes the sum of the distance of each data point from the line.
It finds the line that minimizes the sum of the distance of each data point from the line.
6. F-test measures the statistical significance of each explanatory variable.
7. What is correct about t-test?
If the estimate of a coefficient is 14.2 and the standard error is 2.0, the t-value is 7.1.
t-test measures the fitness of a regression equation to the data.
If a t-value is very small - less than one, that means the variable is very significant.
In conducting a t-test, we hypothesize the regression coefficient to be zero, and test that the null hypothesis. If it is proved true, then the coefficient is meaningful.
All of above.
8. Click demand data and using the data estimate the coefficients of the following equation: (I don't have the Demand Data for this question)
Q = ( ) + ( ) P
9. A demand equation is provided as follows:
log Q = log a + b log P
What is NOT true about the relationship?
The demand has nonlinear relationship with price.
One percent change of P is associated with b percent change of Q.
b represents the point price elasticity of the demand.
If a > 0 and b > 0, the demand increases at an increasing rate with respect to price.
The greater is b, the greater the influence of P on Q.
10. A demand equation is estimated as follows:
log Q = 100 - 2.5 log P + 0.5 Y, where Y is household income.
What is the correct statement about the equation?
Price is more dominent variable than household income.
Price change affects the demand five times more significantly than household income change.
-2.5 represents the point price elasticity and 0.5 represents the point income elasticity.
One percent increase of household income increases the demand by 0.5 percent.
All of above.
Durbin-Watson test detects Autocorrelation.
When independent variables are related to each other, we have multicollinearity problem.