version 1.1-2

.Rinstignore

@@ -0,0 +1,5 @@
+doc/Makefile
+doc/.*[.]tex
+doc/.*[.]bbl
+doc/Rplots.pdf
+doc/pp1.bbl

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: polyapost
-Version: 1.1-1
-Date: 2011-04-01
+Version: 1.1-2
+Date: 2012-03-20
 Imports: boot
 Title: Simulating from the Polya posterior
 Author: Glen Meeden <glen@stat.umn.edu> and Radu Lazar
@@ -9,6 +9,6 @@ Maintainer: Glen Meeden <glen@stat.umn.edu>
 Description: Generate dependent samples from a non-full dimensional
         polytope via a Markov Chain sampler
 License: GPL (>= 2)
-Packaged: 2011-04-01 20:29:19 UTC; glen
+Packaged: 2012-03-20 21:43:39 UTC; geyer
 Repository: CRAN
-Date/Publication: 2011-04-03 07:43:21
+Date/Publication: 2012-03-21 07:59:39

MD5

@@ -1,4 +1,4 @@
-e4022fef5870806939a1fc873e43a34e *DESCRIPTION
+6dfb3163322449f6682c7b130ccabcd6 *DESCRIPTION
 c76df6367ec5ce07212d916fcc833e16 *NAMESPACE
 af205ca09fab4fe4f460b9c4348eb85d *R/checkconstr.R
 a24b9132c8639e5deaee307bc7fe9e23 *R/constrmat.R
@@ -14,18 +14,16 @@ a1a00e355ceb163ef53365bfca339836 *R/polyap.R
 2be02f772609a4f9913e4bf2a30c876d *R/probvect.R
 d2d0660f39acf21c1149c4945c4c8b48 *R/probvect1.R
 be39dcf61a777387307071ea97d954aa *R/wtpolyap.R
-29087fe69e156c49e2c6d99b3ad427de *inst/doc/Makefile
-61d6d43b57b59b11a6a859d41bece14e *inst/doc/Rplots.pdf
+102bd55bba8f8b4ea8c0e7c76a2ffb8d *inst/doc/Makefile
 134ca7abd4d89854e6f9a5e4c4e57ff5 *inst/doc/pp1.Rnw
-50e24be4edb99c0d664dba4a5b8c5f59 *inst/doc/pp1.bbl
-94fa437f955b148e68f52a7530d3c10d *inst/doc/pp1.pdf
-0e923672b7bf7907f550f8cc5ade10d0 *inst/doc/pp1.tex
+60cf84f029be4a5325c1528e9e60e3ec *inst/doc/pp1.pdf
+806f3ce1d990b0032ff600dbc273a15c *inst/doc/pp1.tex
 4388f62ae698c61d4700c06f5e555ecc *inst/doc/ref.bib
 3b716132aa2bd8685f02914ffd67b2c1 *man/constrppmn.Rd
 bfe800f8e58196f92238b7c95ea743a1 *man/constrppprob.Rd
 5b6324e86f7901e956c84d1c78909919 *man/feasible.Rd
 70a66177a47ae41060719beac631cc0d *man/polyap.Rd
 f3306aed9f43d4ce80ac07816b69a2ed *man/wtpolyap.Rd
-98c43e79badf466e944c7eaa15f04f9b *src/cwpolya.c
-604cba68ca5c4315ae59cf46bb70a2f6 *src/means.c
-e6d55970077153a349b21108fb1da02e *src/probvect.c
+acc74c55459b9a9eeec62c095169c1cb *src/cwpolya.c
+d067003129a24718720d6524880cdf08 *src/means.c
+3210d9b6a13447a22754e5819e7cb2dc *src/probvect.c

inst/doc/Makefile

@@ -4,5 +4,11 @@ all: pp1.pdf clean
 pp1.tex: pp1.Rnw
 	$(R_HOME)/bin/R CMD Sweave pp1.Rnw
 
+pp1.pdf: pp1.tex ref.bib
+	pdflatex pp1
+	bibtex pp1
+	pdflatex pp1
+	pdflatex pp1
+
 clean: 
-	rm -f *.aux *.log *.dvi *.blg pp1-*.eps pp1-*.pdf Rplots.ps pp1.blg
+	rm -f *.aux *.log *.dvi *.blg *.bbl pp1-*.pdf Rplots.pdf

inst/doc/pp1.tex

@@ -83,9 +83,9 @@ \section{Simulating from the Polya posterior}
 \begin{Sinput}
 > set.seed(313)
 > library(polyapost)
-> ysamp <- c(0, 1)
-> K <- 10 - 2
-> polyap(ysamp, K)
+> ysamp<-c(0,1)
+> K<-10-2
+> polyap(ysamp,K)
 \end{Sinput}
 \begin{Soutput}
  [1] 0 1 0 0 1 0 1 1 0 1
@@ -99,27 +99,25 @@ \section{Simulating from the Polya posterior}
 
 \begin{Schunk}
 \begin{Sinput}
-> y <- rgamma(500, 5)
+> y<-rgamma(500,5)
 > mean(y)
 \end{Sinput}
 \begin{Soutput}
 [1] 5.021535
 \end{Soutput}
 \begin{Sinput}
-> samp <- sample(1:500, 25)
-> ysamp <- y[samp]
+> samp<-sample(1:500,25)
+> ysamp<-y[samp]
 > mean(ysamp)
 \end{Sinput}
 \begin{Soutput}
 [1] 5.737207
 \end{Soutput}
 \begin{Sinput}
-> K <- 500 - 25
-> simmns <- rep(0, 10)
-> for (i in 1:10) {
-+     simmns[i] <- mean(polyap(ysamp, K))
-+ }
-> round(simmns, digits = 2)
+> K<-500-25
+> simmns<-rep(0,10)
+> for(i in 1:10){simmns[i]<-mean(polyap(ysamp,K))}
+> round(simmns,digits=2)
 \end{Sinput}
 \begin{Soutput}
  [1] 5.62 5.47 5.55 5.56 6.44 5.55 5.29 6.54 5.33 6.82
@@ -190,9 +188,9 @@ \subsection{The basic idea}
 
 \begin{Schunk}
 \begin{Sinput}
-> x <- sort(rgamma(500, 10))
-> y <- rnorm(500, 20 + 2 * x, 3)
-> cor(x, y)
+> x<-sort(rgamma(500,10))
+> y<-rnorm(500,20 + 2*x,3)
+> cor(x,y)
 \end{Sinput}
 \begin{Soutput}
 [1] 0.8966712
@@ -204,7 +202,7 @@ \subsection{The basic idea}
 [1] 39.87462
 \end{Soutput}
 \begin{Sinput}
-> mnx <- mean(x)
+> mnx<-mean(x)
 > mnx
 \end{Sinput}
 \begin{Soutput}
@@ -224,9 +222,9 @@ \subsection{The basic idea}
 
 \begin{Schunk}
 \begin{Sinput}
-> samp <- sort(c(sample(1:250, 8), sample(251:500, 17)))
-> ysamp <- y[samp]
-> xsamp <- x[samp]
+> samp<-sort(c(sample(1:250,8),sample(251:500,17)))
+> ysamp<-y[samp]
+> xsamp<-x[samp]
 > mean(ysamp)
 \end{Sinput}
 \begin{Soutput}
@@ -239,12 +237,12 @@ \subsection{The basic idea}
 [1] 10.87586
 \end{Soutput}
 \begin{Sinput}
-> A1 <- rbind(rep(1, 25), c(rep(1, 8), rep(0, 17)))
-> b1 <- c(1, 0.5)
-> A2 <- rbind(xsamp, -diag(25))
-> b2 <- c(10, rep(0, 25))
-> A3 <- matrix(xsamp, 1, 25)
-> b3 <- 9.7
+> A1<-rbind(rep(1,25),c(rep(1,8),rep(0,17)))
+> b1<-c(1,0.5)
+> A2<-rbind(xsamp,-diag(25))
+> b2<-c(10.0,rep(0,25))
+> A3<-matrix(xsamp,1,25)
+> b3<-9.7
 \end{Sinput}
 \end{Schunk}
 
@@ -274,9 +272,9 @@ \subsection{The basic idea}
 
 \begin{Schunk}
 \begin{Sinput}
-> eps <- 0.001
-> initsol <- feasible(A1, A2, A3, b1, b2, b3, eps)
-> initsol[c(3, 9, 25)]
+> eps<-0.001
+> initsol<-feasible(A1,A2,A3,b1,b2,b3,eps)
+> initsol[c(3,9,25)]
 \end{Sinput}
 \begin{Soutput}
 [1] 0.0010000 0.3107501 0.1742499
@@ -323,10 +321,9 @@ \subsection{The basic idea}
 
 \begin{Schunk}
 \begin{Sinput}
-> burnin <- 1
-> reps <- 200001
-> out <- constrppmn(A1, A2, A3, b1, b2, b3, initsol, reps, ysamp, 
-+     burnin)
+> burnin<-1
+> reps<-200001
+> out<-constrppmn(A1,A2,A3,b1,b2,b3,initsol,reps,ysamp,burnin)
 > mean(out[[1]])
 \end{Sinput}
 \begin{Soutput}
@@ -356,13 +353,13 @@ \subsection{The basic idea}
 
 \begin{Schunk}
 \begin{Sinput}
-> out[[2]]
+> out[[2]] 
 \end{Sinput}
 \begin{Soutput}
 [1] 39.81557
 \end{Soutput}
 \begin{Sinput}
-> out[[3]]
+> out[[3]] 
 \end{Sinput}
 \begin{Soutput}
     2.5%    97.5% 
@@ -408,21 +405,20 @@ \subsubsection{How long to run the chain}
 
 \begin{Schunk}
 \begin{Sinput}
-> A1 <- rbind(rep(1, 25))
-> A2 <- -diag(25)
-> b1 <- 1
-> b2 <- rep(0, 25)
-> initsol <- rep(0.04, 25)
-> reps <- 1000001
-> out <- constrppmn(A1, A2, NULL, b1, b2, NULL, initsol, reps, 
-+     ysamp, burnin)
+> A1<-rbind(rep(1,25))
+> A2<--diag(25)
+> b1<-1
+> b2<-rep(0,25)
+> initsol<-rep(0.04,25)
+> reps<-1000001
+> out<-constrppmn(A1,A2,NULL,b1,b2,NULL,initsol,reps,ysamp,burnin)
 > mean(out[[1]])
 \end{Sinput}
 \begin{Soutput}
 [1] 42.04514
 \end{Soutput}
 \begin{Sinput}
-> subseq <- seq(1, 1000001, by = 1000)
+> subseq<-seq(1,1000001,by=1000)
 > mean(out[[1]][subseq])
 \end{Sinput}
 \begin{Soutput}
@@ -455,10 +451,10 @@ \subsubsection{How long to run the chain}
 
 \begin{Schunk}
 \begin{Sinput}
-> K <- 500 - 25
-> simmns <- rep(0, 1000)
-> for (i in 1:1000) {
-+     simmns[i] <- mean(polyap(ysamp, K))
+> K<-500-25
+> simmns<-rep(0,1000)
+> for(i in 1:1000){
++        simmns[i]<-mean(polyap(ysamp,K))
 + }
 > mean(simmns)
 \end{Sinput}
@@ -498,15 +494,15 @@ \subsubsection{Estimating parameters other than the mean}
 
 \begin{Schunk}
 \begin{Sinput}
-> A1 <- rbind(rep(1, 6), 1:6)
-> A2 <- rbind(c(2, 5, 7, 1, 10, 8), diag(-1, 6))
-> A3 <- matrix(c(1, 1, 1, 0, 0, 0), 1, 6)
-> b1 <- c(1, 3.5)
-> b2 <- c(6, rep(0, 6))
-> b3 <- 0.45
-> initsol <- rep(1/6, 6)
-> out <- constrppprob(A1, A2, A3, b1, b2, b3, initsol, 2000, 5)
-> round(out, digits = 5)
+> A1<-rbind(rep(1,6),1:6)
+> A2<-rbind(c(2,5,7,1,10,8),diag(-1,6))
+> A3<-matrix(c(1,1,1,0,0,0),1,6)
+> b1<-c(1,3.5)
+> b2<-c(6,rep(0,6))
+> b3<-0.45
+> initsol<-rep(1/6,6)
+> out<-constrppprob(A1,A2,A3,b1,b2,b3,initsol,2000,5)
+> round(out,digits=5)
 \end{Sinput}
 \begin{Soutput}
            [,1]    [,2]    [,3]    [,4]    [,5]    [,6]
@@ -541,9 +537,9 @@ \subsubsection{The weighted Polya posterior}
 
 \begin{Schunk}
 \begin{Sinput}
-> ysamp <- c(1, 2, 3)
-> wts <- c(1, 2, 3)
-> wtpolyap(ysamp, wts, 25)
+> ysamp<-c(1,2,3)
+> wts<-c(1,2,3)
+> wtpolyap(ysamp,wts,25)
 \end{Sinput}
 \begin{Soutput}
  [1] 1 2 3 3 3 3 3 3 3 3 2 3 3 3 3 2 3 3 3 3 3 3 3 3 2 3 3 3

src/cwpolya.c

@@ -1,6 +1,4 @@
 
-#include <stdio.h>
-#include <float.h>
 #include <R.h>
 
 void cwpolya(double *x, double *w, int *nin, int *Nin)

src/means.c

@@ -1,8 +1,8 @@
 /*Computes the Markov chain of means for the constrained Polya method*/
 /*for combined equality and inequality constraints A1x=b1,A2x<=b2. It returns all values.*/
-#include <stdio.h>
-#include <float.h>
+
 #include <R.h>
+
 double sum( double x[], int vectsize )
 {
      double s;

src/probvect.c

@@ -1,7 +1,6 @@
 /*Computes the Markov chain of the points in the polytope*/
 /*for combined equality and inequality constraints A1x=b1,A2x<=b2. It returns the last value.*/
-#include <stdio.h>
-#include <float.h>
+
 #include <R.h>
 double sum1( double x[], int vectsize )
 {