# How to interpret results of stationary phase approximation in GW case?

As time increases, the amplitude and frequency of the GW signal also increase. But after using the stationary phase approximation, the signal is proportional to $${1/f^{7/6}}$$, where $$f$$ is the GW frequency. Which means as you increase the frequency, the signal amplitude will decrease. This seems opposite to time domain signal behavior.

Can somebody please tell me what I am missing?