Generalized Monte Carlo significance tests

摘要: SUMMARY Simple Monte Carlo significance testing has many applications, particularly in the preliminary analysis of spatial data. The method requires value test statistic to be ranked among a random sample values generated according null hypothesis. However, there are situations which can only conveniently using Markov chain, initiated by observed data, so that independence is violated. This paper describes two methods overcome problem dependence and allow exact tests carried out. applied Rasch model, finite lattice Ising model association between processes. Power discussed simple case.