Parameter Estimates

Figure 1. Parameter estimates
Table with parameters (factors and covariates) in the rows and B, standard error, t, significance, and confidence interval in the columns

The Parameter Estimates table shows the usual, non-bootstrapped, parameter estimates for the model terms. The significance value of 0.105 for [minority=0] is greater than 0.05, suggesting that Minority Classification has no effect on salary increases.

Figure 2. Bootstrap parameter estimates
Bootstrap parameter estimates

Now look at the Bootstrap for Parameter Estimates table. In the Std. Error column, you see that the parametric standard errors for some coefficients, like the intercept, are too small compared to the bootstrap estimates, and thus the confidence intervals are wider. For some coefficients, like [minority=0], the parametric standard errors were too large, while the significance value of 0.006 reported by the bootstrap results, which is less than 0.05, shows that the observed difference in salary increases between employees who are and are not minorities is not due to chance. Management now knows this difference is worth investigating further to determine possible causes.