I'm using the generalized linear models function in SPSS with a normal distribution and identity link function. If I choose the likelihood ratio $\chi^2$ statistic, I get the same results as the Univariate GLM, which is not surprising. However if I use the SPSS's default Wald $\chi^2$, I get vastly different $\chi^2$ and p-values in the "test of model effects" table.
What is the difference between what the two stats are telling me, and how can I tell which is appropriate to use?
My dataset is a continuous response variable with three factors, one including a nested term, and a covariate.