The maximum value distribution in a reverberation chamber

The maximum over mean distribution of received power in the FOI reverberation chamber is analyzed. The experimental results are compared with the theoretical distribution for a chi squared distributed power. For the theoretical distribution the confidence intervals are given as functions of the number of independent measurements for the maximum over mean values. The minimum number of required samples to obtain an acceptable estimate of the maximum over mean is discussed. It turns out that the number of samples should be at least greater than 20. Further the relation between statistical independence and linear correlation coefficients of measured data are discussed and analyzed. The authors make a chi square goodness of fit test to reject data that are statistically dependent. These results are compared with linear correlation coefficient evaluations.