New software for computation sensitivity analysis to detect hidden bias for partially order set test statistic in observational studies

In observational studies, subjects are not randomly assigned to treatment or control, so they may differ in their chances of receiving the treatment. In this study we designed new software for a method is developed and demonstrated for displaying the sensitivity of conventional two-unmatched group permutation inferences to departures from random assignment of treatments for partially order set test statistic in observational studies. We designed an algorithm with visual FORTRAN (SENPOSET) program for calculating the sensitivity analysis for detects hidden biases in observational studies. The method embeds the usual randomization reference distribution in a one-parameter family of departures involving an unobserved covariate that would have been controlled by adjustments had it been observed. As this parameter is varied, the sensitivity of permutation significance levels and confidence intervals is displayed. This program indicates that the proposed algorithm performs well in identifying sensitivity to unobserved biases and comparisons vary considerably in their degree of sensitivity.