In order to investigate the presence of regime changes in the effects of real and nominal uncertainty on inflation and output growth, bivariate normal mixture GARCH-in-mean models are developed for monthly data of inflation and output growth in USA. Overall, we find significant evidence in favor of and against four hypotheses depending on regimes. The key idea in this paper is that the model embeds two different regimes of a usual volatility, which occurs most of the time, and an extreme volatility, which occurs rarely.