Fisher’s p-value and local FDR are considered essential methods of statistical analysis in research hypothesis testing. Yet, these tools quickly become suboptimal when dealing with large scale, multiple comparisons of variables.
To overcome their limitations, Zhigen Zhao proposes a new method of statistical analysis, called the Cdf and Local fdr Assisted multiple Testing method (CLAT).
The CLAT surpasses the p-value by retaining accuracy when dealing with data with unequal variability across predictor variables, and surpasses the local FDR in ease and practicality of estimation.
Whether they may be geneticists studying expressions among genes or stockbrokers analyzing different stock options, academics and practitioners alike can benefit from CLAT analysis.