ABSTRACT
Chapter 3 is about Monte Carlo methods for testing data. The idea is then to assess the significance of an observed test statistic by comparing it with a sample of test statistics obtained by generating random samples using some assumed model. The chapter also describes generalized Monte Carlo tests where an observed set of data is one of many sets that could have occurred, all possible sets of data can be generated by a series of one step changes to the data, the null hypothesis of interest is that all possible sets of data were equally likely to occur, and each possible set of data is summarized by a test statistic S.
