The R Project SVN R

Rev

Rev 87478 | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 87478 Rev 88563
Line 1... Line 1...
1 
% File src/library/stats/man/loglin.Rd
 1 
% File src/library/stats/man/loglin.Rd
2 
% Part of the R package, https://www.R-project.org
 2 
% Part of the R package, https://www.R-project.org
3 
% Copyright 1995-2024 R Core Team
 3 
% Copyright 1995-2025 R Core Team
4 
% Distributed under GPL 2 or later
 4 
% Distributed under GPL 2 or later
5 
 
 5 
 
6 
\name{loglin}
 6 
\name{loglin}
7 
\alias{loglin}
 7 
\alias{loglin}
8 
\title{Fitting Log-Linear Models}
 8 
\title{Fitting Log-Linear Models}
Line 63... Line 63...
63 
    (e.g., zero row and column sums for a two factor parameter) are
 63 
    (e.g., zero row and column sums for a two factor parameter) are
64 
    employed.  Only returned if \code{param} is \code{TRUE}.}
 64 
    employed.  Only returned if \code{param} is \code{TRUE}.}
65 
}
 65 
}
66 
\details{
 66 
\details{
67 
  The Iterative Proportional Fitting algorithm as presented in
 67 
  The Iterative Proportional Fitting algorithm as presented in
68 
  \bibcite{Haberman (1972)} is used for fitting the model.  At most \code{iter}
 68 
  \bibcitet{R:Haberman:1972} is used for fitting the model.  At most \code{iter}
69 
  iterations are performed, convergence is taken to occur when the
 69 
  iterations are performed, convergence is taken to occur when the
70 
  maximum deviation between observed and fitted margins is less than
 70 
  maximum deviation between observed and fitted margins is less than
71 
  \code{eps}.  All internal computations are done in double precision;
 71 
  \code{eps}.  All internal computations are done in double precision;
72 
  there is no limit on the number of factors (the dimension of the
 72 
  there is no limit on the number of factors (the dimension of the
73 
  table) in the model.
 73 
  table) in the model.
Line 86... Line 86...
86 
  fitted in a formula-based manner similar to that of other fitting
 86 
  fitted in a formula-based manner similar to that of other fitting
87 
  functions such as \code{lm} or \code{glm}.
 87 
  functions such as \code{lm} or \code{glm}.
88 
}
 88 
}
89 
 
 89 
 
90 
\references{
 90 
\references{
91 
  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988).
 - 
 
92 
  \emph{The New S Language}.
 - 
 
93 
  Wadsworth & Brooks/Cole.
 - 
 
94 
 
 - 
 
95 
  Haberman, S. J. (1972).
 - 
 
96 
  Algorithm AS 51: Log-linear fit for contingency tables.
 - 
 
97 
  \emph{Applied Statistics}, \bold{21}, 218--225.
 - 
 
98 
  \doi{10.2307/2346506}.
 91 
  \bibshow{*,
99 
 
 - 
 
100 
  Agresti, A. (1990).
 92 
    R:Agresti:1990,
101 
  \emph{Categorical data analysis}.
 93 
    R:Becker+Chambers+Wilks:1988}
102 
  New York: Wiley.
 - 
 
103 
}
 94 
}
104 
\author{Kurt Hornik}
 95 
\author{Kurt Hornik}
105 
\seealso{
 96 
\seealso{
106 
  \code{\link{table}}.
 97 
  \code{\link{table}}.
107 
 
 98