Two detection systems having multiple inputs each consisting of nonstationary noise and a stationary random signal are analyzed and compared on a signal‐to‐noise ratio basis. In both systems the inputs are divided into two groups and the sum of each group is formed. In the first system the resulting two wave forms are multiplied directly and the product averaged. In the second system the two wave forms are strongly clipped prior to multiplication, forming a polarity‐coincidence correlator. Previous studies have shown the latter system to be slightly inferior for stationary noise. The results of this paper show that the latter system may be quite superior in certain types of nonstationary noise.