I agree with Ian Pearson's ...
Published by Peter Muiruri, Drilling Solutions Field Engineer at MI SWACO
I agree with Ian Pearson's perspective and approach. Meteorological/climatic data is not normally distributed as it varies spatially and temporally. Thus, for parametric testing, the data need to be normalized by fitting the data into a suitable PDF/CDF before transformation to a standard Gaussian multivariate. Otherwise, you may consider the non-parametric tests such as Spearman Rank correlation and Mann-Kendall trend test; although parametric statistical models are superior.
1 Comment
can i email data to check? as i have some confusion. when i apply power tranfirmation some data is skewed some is normal.
Published by Engr. Salah Ud Din, Deputy Director at Pakistan Council of Research in Water Resources