I want an interpretation of this BP test result:
Breusch-Pagan / Cook-Weisberg test for heteroskedasticity
Ho: Constant variance
Variables: fitted values of envdisc
chi2(1) = 0.02
Prob > chi2 = 0.8829
Best Answer
Take your OLS regression of $y_i$ against your independent variables to get fitted values of $\hat{y}_i$
Find your residuals $u_i=y_i-\hat{y}_i$. You want to know whether the variance of the residuals is constant
So regress the squares of the residuals $u_i^2$ against the same independent variables and find the $R^2$. Under the null hypothesis of homoscedasticity, this should be close to zero
Under the null hypothesis $nR^2$ is asymptotically distributed as $\chi^2_1$: your (Stata?) run gives $0.02$, so find the probability of this or a higher value on that distribution, which is about $0.8829$
Since this presumably is greater than your personal significance level ($0.05$?), you cannot reject the null hypothesis of homoscedasticity on the basis of this data and test