clean up a bit, including historical remarks

git-svn-id: https://svn.r-project.org/R/trunk@87470 00db46b3-68df-0310-9c12-caf00c1e9a41

Author: ripley

src/library/stats/man/fisher.test.Rd

@@ -1,6 +1,6 @@
 % File src/library/stats/man/fisher.test.Rd
 % Part of the R package, https://www.R-project.org
-% Copyright 1995-2022 R Core Team
+% Copyright 1995-2024 R Core Team
 % Distributed under GPL 2 or later
 
 \name{fisher.test}
@@ -24,17 +24,17 @@ fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
   \item{workspace}{an integer specifying the size of the workspace
     used in the network algorithm.  In units of 4 bytes.  Only used for
     non-simulated p-values larger than \eqn{2 \times 2}{2 by 2} tables.
-    Since \R version 3.5.0, this also increases the internal stack size
-    which allows larger problems to be solved, however sometimes needing
-    hours.  In such cases, \code{simulate.p.values=TRUE} may be more
+    This also increases the internal stack size
+    which allows larger problems to be solved, sometimes needing
+    hours.  In such cases, \code{simulate.p.values = TRUE} may be more
     reasonable.}
     \item{hybrid}{a logical. Only used for larger than \eqn{2 \times 2}{2 by 2}
     tables, in which cases it indicates whether the exact probabilities
     (default) or a hybrid approximation thereof should be computed.}
   \item{hybridPars}{a numeric vector of length 3, by default describing
     \dQuote{Cochran's conditions} for the validity of the chi-squared
     approximation, see \sQuote{Details}.}
-  \item{control}{a list with named components for low level algorithm
+  \item{control}{a list with named components for low-level algorithm
     control.  At present the only one used is \code{"mult"}, a positive
     integer \eqn{\ge 2} with default 30 used only for larger than
     \eqn{2 \times 2}{2 by 2} tables.  This says how many times as much
@@ -56,7 +56,7 @@ fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
     p-values by Monte Carlo simulation, in larger than \eqn{2 \times
       2}{2 by 2} tables.}
   \item{B}{an integer specifying the number of replicates used in the
-    Monte Carlo test.}
+    Monte Carlo test when \code{simulate.p.value} is true.}
 }
 \value{
   A list with class \code{"htest"} containing the following components:
@@ -83,7 +83,7 @@ fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
   length.  Incomplete cases are removed, vectors are coerced into
   factor objects, and the contingency table is computed from these.
 
-  For \eqn{2 \times 2}{2 by 2} cases, p-values are obtained directly
+  For \eqn{2 \times 2}{2 by 2} tables, p-values are obtained directly
   using the (central or non-central) hypergeometric
   distribution. Otherwise, computations are based on a C version of the
   FORTRAN subroutine \code{FEXACT} which implements the network developed by
@@ -105,7 +105,7 @@ fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
   alternative for a one-sided test is based on the odds ratio, so
   \code{alternative = "greater"} is a test of the odds ratio being bigger
   than \code{or}.
-
+%
   Two-sided tests are based on the probabilities of the tables, and take
   as \sQuote{more extreme} all tables with probabilities less than or
   equal to that of the observed table, the p-value being the sum of such
@@ -120,16 +120,9 @@ fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
   cells have expected counts at least 5 (\code{= expect}), otherwise
   the exact calculation is used.  A corresponding \code{if()} decision
   is made for all sub-tables considered.
-  %
-  Accidentally, \R has used \code{180} instead of \code{80} as
-  \code{percent}, i.e., \code{hybridPars[2]} in \R versions between
-  3.0.0 and 3.4.1 (inclusive), i.e., the 2nd of the \code{hybridPars}
-  (all of which used to be hard-coded previous to \R 3.5.0).
-  Consequently, in these versions of \R, \code{hybrid=TRUE} never made a
-  difference.
 
   In the \eqn{r \times c}{r x c} case with \eqn{r > 2} or \eqn{c > 2},
-  internal tables can get too large for the exact test in which case an
+  internal tables can be too large for the exact test in which case an
   error is signalled.  Apart from increasing \code{workspace}
   sufficiently, which then may lead to very long running times, using
   \code{simulate.p.value = TRUE} may then often be sufficient and hence
@@ -243,7 +236,7 @@ MP6 <- rbind(
         c(1,1,2,0,0,0,1),
         c(0,1,1,1,1,0,0))
 fisher.test(MP6)
-# Exactly the same p-value, as Cochran's conditions are never met:
-fisher.test(MP6, hybrid=TRUE)
+# Exactly the same p-value, as Cochran's conditions are not met:
+fisher.test(MP6, hybrid = TRUE)
 }
 \keyword{htest}

tests/Examples/stats-Ex.Rout.save

@@ -1,7 +1,7 @@
 
-R Under development (unstable) (2024-11-12 r87322) -- "Unsuffered Consequences"
+R Under development (unstable) (2024-12-25 r87467) -- "Unsuffered Consequences"
 Copyright (C) 2024 The R Foundation for Statistical Computing
-Platform: aarch64-apple-darwin24.1.0
+Platform: aarch64-apple-darwin24.2.0
 
 R is free software and comes with ABSOLUTELY NO WARRANTY.
 You are welcome to redistribute it under certain conditions.
@@ -5124,7 +5124,7 @@ function (V)
         r[seq.int(from = 1L, by = p + 1L, length.out = p)] <- 1
     r
 }
-<bytecode: 0x10b83cec8>
+<bytecode: 0x12090f330>
 <environment: namespace:stats>
 > stopifnot(all.equal(Cl, cov2cor(cov(longley))),
 +           all.equal(cor(longley, method = "kendall"),
@@ -7662,8 +7662,8 @@ data:  MP6
 p-value = 0.03929
 alternative hypothesis: two.sided
 
-> # Exactly the same p-value, as Cochran's conditions are never met:
-> fisher.test(MP6, hybrid=TRUE)
+> # Exactly the same p-value, as Cochran's conditions are not met:
+> fisher.test(MP6, hybrid = TRUE)
 
 	Fisher's Exact Test for Count Data hybrid using asym.chisq. iff (exp=5,
 	perc=80, Emin=1)
@@ -7772,7 +7772,7 @@ attr(,".Environment")
 > environment(as.formula("y ~ x"))
 <environment: R_GlobalEnv>
 > environment(as.formula("y ~ x", env = new.env()))
-<environment: 0x10d923d98>
+<environment: 0x10699fb68>
 > 
 > 
 > ## Create a formula for a model with a large number of variables:
@@ -12714,14 +12714,14 @@ attr(,"class")
 $linkfun
 function (mu) 
 mu^lambda
-<bytecode: 0x10dce8030>
-<environment: 0x10dcf1fd8>
+<bytecode: 0x12056a680>
+<environment: 0x120575bb0>
 
 $linkinv
 function (eta) 
 pmax(eta^(1/lambda), .Machine$double.eps)
-<bytecode: 0x10dce7ee0>
-<environment: 0x10dcf1fd8>
+<bytecode: 0x12056a530>
+<environment: 0x120575bb0>
 
 > 
 > 
@@ -17080,8 +17080,8 @@ Step function with continuity 'f'= 0.2 ,  3 knots at
 > unclass(sfun0)
 function (v) 
 .approxfun(x, y, v, method, yleft, yright, f, na.rm)
-<bytecode: 0x12c5bc600>
-<environment: 0x10d8ab2d8>
+<bytecode: 0x115d97208>
+<environment: 0x106858c98>
 attr(,"call")
 stepfun(1:3, y0, f = 0)
 > ls(envir = environment(sfun0))
@@ -19647,7 +19647,7 @@ Number of Fisher Scoring iterations: 6
 > cleanEx()
 > options(digits = 7L)
 > base::cat("Time elapsed: ", proc.time() - base::get("ptime", pos = 'CheckExEnv'),"\n")
-Time elapsed:  2.868 0.238 3.12 0 0 
+Time elapsed:  2.846 0.215 3.067 0 0 
 > grDevices::dev.off()
 null device 
           1