We present a statistically robust approach based on probability weight
ed moments to assess the presence of simple scaling in geophysical pro
cesses. The proposed approach is different from current approaches whi
ch rely on estimation of high order moments. High order moments of sim
ple scaling processes (distributions) may not have theoretically defin
ed values and consequently, their empirical estimates are highly varia
ble and do not converge with increasing sample size. They are, therefo
re, not an appropriate tool for inference. On the other hand we show t
hat the probability weighted moments of such processes (distributions)
do exist and hence, their empirical estimates are more robust. These
moments, therefore, provide an appropriate tool for inferring the pres
ence of scaling. We illustrate this using simulated Levy-stable proces
ses and then draw inference on the nature of scaling in fluctuations o
f a spatial rainfall process.