With the below information please explain how you would test your model for viol

Question

With the below information please explain how you would test your model for violations of the classical assumptions? reg sold price approx sqft Source I MS Number of obs = F( 1, 3847)=9700.39 Prob> F R-squared Adj R-squared = 0.7160 Root MSIE df 3849 -0.0000 -0.7160 Model 6.5211e+14 1 6.521le+14 Residual 2.5861e+14 3847 6.7225e+10 Ttall 9.1072e+14 3848 2.3667e+11 - 2.6e+05 sold_price I Coef. Std. Err [95% Conf. Interval] approx sqft I 287.304 2.917071 98.49 0.000 293.0231 -299686 281.5848 cons -318043.9 9363.475 -33.97 0.000 -336401.7

Explanation / Answer

Solution:

The number of total observations for the given model is given as 3849. The sample size is adequate for making predictions or inference. The F test statistic for the ANOVA table is given as 9700.39 with the p-value of 0.00. Given P-value is less than the level of significance or alpha value 0.05, so we reject the null hypothesis that there is no any statistical significant linear association exists between the given two variables such as sold price and approximate square foot. This means there is sufficient evidence to conclude that there is statistically significant linear relationship or association exists between the given dependent and independent variable. The coefficient of determination or the value of R square is given as 0.7160, this means about 71.60% of the variation in the dependent variable sold price is explained by the independent variable. The regression equation for the model is given as below:

Sold Price = 287.304 – 318043.9*approximate sqft.

Where y-intercept for the regression equation is given as 287.304 and slope is given as – 318043.9. The negative slope indicate the negative linear relationship or association between the given two variables. Both y-intercept and slope are statistically significant as the p-values are given as 0.00.

For checking the above model for the violations of the classical assumptions, we will use Durbin – Watson test for 0. Also, we will check the Heteroskedasticity. Also, it is important to check the model for multicollinearity. Sometimes there would be a strong relationship or association possible between the two independent variables. We can use variance inflation factor to identify the collinearity. Also, it is important to avoid Mis-specification.

Related Questions

Navigate

• Browse (All)
• Browse W
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.