> Who can help me to solve this problem?
> est.chi[i,]<-c( fitdistr(as.numeric(data2[,i]),"chi-squared",start=list(df=1))$estimate)
> Warning message:In optim(x = c(7.86755, 7.50852, 7.86342, 7.70589, 7.70153, 7.58272, : one-diml optimization by
> Nelder-Mead is unreliable: use "Brent" or optimize() directly
The warning message tells you to use "Brent" rather than the default Nelder-Mead. So do that.