We suspect that the regression error variance might be larger for household with two children than one. We estimate the budget share equation by OLS separately for households with on and two children. From the 489 households with one child, the sum of squared residuals is 465.83. For the 789 households with two children, the sum of squared residuals is 832.77. Test the null hypothesis that there is no difference between the regression error variances for these two groups, against the alternative that there is a difference. Use the Goldfeld- Quandt test at the 5% level of significance. ln(????) = −1.956 + 0.837?????? − 0.228??? − 0.251??
(0.166) (0.516) (0.039) (0.058)
Answer:
Given Data
Goldfeld test statistic :
Here, statistic
At 5% alpha,
So, F calculated is not greater than 1.172 or we can say that we fail to Ho or can say that there is no difference in the regression variances of the two
****Please like it.. It is important to me
Thank you ... For supporting me..
Get Answers For Free
Most questions answered within 1 hours.