Dear Members,
I try to create a generic test function for distribution error for
binomial negative, Poisson and normal. But my function doesn't work
(NA's produced and don't realize the test) and I don't know why, any
member can help me? My function is:
require(MASS)
BD<-rpois(1000,10) ### Data set for test
Dist<-c("negative binomial","normal","Poisson")
for(typeD in 1:Dist){
k <- fitdistr(BD,typeD[Dist])
par <- k$estimate
size <- par[1]#Parameter
mu <- par[2]#Mean
SD<-sd(BD)
N <- length(BD)
if (typeD[Dist]=='negative binomial'){ ### For binomial negativa
est <-N*dnbinom(BD,size=size,mu=mu) ## Estimates
fecdf <- ecdf(BD) ###ecdf- Empiric cumulative function
knotsX <- knots(fecdf)
emp <- fecdf(c(knotsX,Inf)) # Empiric
chisq.test(table(emp),table(est),correct=TRUE) ##Chi test
}
if (typeD[Dist]=='normal'){ ### For normal
est <-N*dnorm(BD,mean=mu, sd=SD) ## Estimates
fecdf <- ecdf(BD) ###ecdf- Empiric cumulative function
knotsX <- knots(fecdf)
emp <- fecdf(c(knotsX,Inf)) # Empiric
chisq.test(table(emp),table(est),correct=TRUE) ##Chi test
}
if (typeD[Dist]=='Poisson'){ ### For Poisson
est <-N*dpois(BD,lambda=mu) ## Estimate
fecdf <- ecdf(BD) ###cdf- Empiric cumulative function
knotsX <- knots(fecdf)
emp <- fecdf(c(knotsX,Inf)) # Empiric
chisq.test(table(emp),table(est),correct=TRUE) ## Chi test
}
}
#
Thanks,
======================================================================
Alexandre dos Santos
Prote??o Florestal
IFMT - Instituto Federal de Educa??o, Ci?ncia e Tecnologia de Mato Grosso
Campus C?ceres
Caixa Postal 244
Avenida dos Ramires, s/n
Bairro: Distrito Industrial
C?ceres - MT CEP: 78.200-000
Fone: (+55) 65 8132-8112 (TIM) (+55) 65 9686-6970 (VIVO)
alexandre.santos at cas.ifmt.edu.br
Lattes: http://lattes.cnpq.br/1360403201088680
======================================================================
[[alternative HTML version deleted]]