Generation of parametric bootstrap samples
This function allows to generate parametric bootstrap samples in order to check the optimal dimension number of three-way correspondence analysis. The boostrap samples have the same marginal proportions and the total number of the original table. The adopted sampling scheme is simple.
simulabootsimple(Xtable,nboots=100,resamptype=1)
Xtable: The three-way data array. It must be an R object array. When non-symmetrical analysis for one response variable is performed, the response mode is the row variable.nboots: The number of bootstrap samples to generate when boots = T. By default nboots = 0.resamptype: Set value of resamptype according to two methods: resamptype=1 corresponds to multinomial distribution and resamptype=2 to Poisson distribution.Beh EJ and Lombardo R (2014) Correspondence Analysis, Theory, Practice and New Strategies. John Wiley & Sons.
Michel van de Velden, Rosaria Lombardo and Eric J Beh.