محمود افشاری

In this thesis, we introduce a new distribution-free Shewhart-type control chart that takes into account the location of a single order statistic of the test sample as well as the number of observations in that test sample that lie between the control limits.\\ A key advantage of the chart is that, due to its nonparametric nature, the false alarm rate and incontrol run length distribution are the same for all continuous process distributions, and so will be naturally robust.It also introduces distribution-free Shewhart-type control chart based on a single observation (such as the median ) and we obtain alarm rate exact formule in both control charts and we show that distribution-free control chart based on order statistcs in every sigth has superiority in compared to a classical Shewhart-type chart and distribution-free control chart based on observation