اريبي هاي مخفي در مطالعات مشاهده اي و كارآزماييهاي باليني تصادفي نشده و آناليز حساسيت براي شناسايي و كنترل آنها

HIDDEN BIASES IN OBSERVATIONAL STUDIES AND NON RANDOMIZED CLINICAL TRIALS; A SENSITIVITY ANALYSIS FOR THEIR RECOGNITION AND CONTROL

In observational studies or non-randomized clinical trials, treated and control groups may differ in their outcomes even if the treatment or exposure has no effect. This may happen if the groups were not comparable before the start of treatment. The groups may not be comparable in two respects; they may differ with respect to variables that have been measured in which ease there is an overt bias, or that they may differ in ways that have not been measured, in this case there is a hidden bias . Overt biases are controled though adjustments such as maching or grouping. Hidden bias is more difficult to address because the relevant variables are not available. In this paper we used sensitivity analysis that have been represented and first we introduced software for difficult calculations of sensitivity analysis. This applied for a true observational study.