[R] Marg.fct function

[James Henson]

Greetings Peter and Jeff,

Thanks for this information.  Will try these type of analyses in SAS.
Sure they are doable in R, but developing a procedure is difficult.
Alan Agresti gives a cookbook SAS method in An Introduction to
Categorical Analysis.

Thanks,
James

On Sun, Feb 5, 2017 at 3:47 PM, Jeff Newmiller <jdnewmil at dcn.davis.ca.us> wrote:
> It is not part of "R". You can dig through all of the packages that the author mentions,  or send an email to the author.
> --
> Sent from my phone. Please excuse my brevity.
>
> On February 5, 2017 11:44:40 AM PST, James Henson <jfhenson1 at gmail.com> wrote:
>>Greetings R Community,
>>
>>An attempt to reproduce the results from code in the source below
>>fails.  R cannot find the function ‘Marg.fct’. An Internet search for
>>the ‘Marg.fct’ function was not fruitful.  I appreciate your help.
>>Best regards, James F. Henson.
>>
>>R (and S-PLUS) Manual to Accompany Agresti’s Categorical Data Analysis
>>(2002) 2nd edition Laura A. Thompson, 2009©
>>
>>http://www.stat.ufl.edu/~aa/cda/Thompson_manual.pdf  page 181
>>
>>The code is:
>>
>># Code from Manual to Accompany Agresti’s Categorical Data Analysis
>>(2002) 2nd edition Laura A. Thompson, 2009
>>
>>y <- c(144, 33, 84, 126, 2, 4, 14, 29, 0, 2, 6, 25, 0, 0, 1, 5)
>>
>>ZF <- Z <- matrix(1,16,1)
>>
>>#
>>
>>M1 <- Marg.fct(1,rep(4,2)) # used to get m1+, etc
>>
>>Error: could not find function "Marg.fct"
>>
>>
>>
>>M2 <- Marg.fct(2,rep(4,2)) # used to get m+1, etc
>>
>>#
>>
>>C.matrix <- matrix(c(
>>
>>  1, 0, 0, 0, -1, 0, 0, 0, # y1+ = y+1
>>
>>  0, 1, 0, 0, 0, -1, 0, 0, # y2+ = y+2
>>
>>  0, 0, 1, 0, 0, 0, -1, 0), # y3+ = y+3
>>
>>  3,8,byrow=T)
>>
>>h.fct <- function(m) { # constraint function
>>
>> marg <- rbind(M1%*%m, M2%*%m) # y1+, y2+, y3+, y4+, y+1, y+2, y+3, y+4
>>
>>  C.matrix%*%marg # y1+ = y+1, y2+ = y+2, etc
>>
>>}
>>
>>#
>>
>>a <- mph.fit(y=y,Z=Z,ZF=ZF,h.fct=h.fct)
>>
>>mph.summary(a)
>>
>>______________________________________________
>>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>>https://stat.ethz.ch/mailman/listinfo/r-help
>>PLEASE do read the posting guide
>>http://www.R-project.org/posting-guide.html
>>and provide commented, minimal, self-contained, reproducible code.