Skip to content

Commit

Permalink
version 2011.02-1
Browse files Browse the repository at this point in the history
  • Loading branch information
@gaborcsardi
Marek Gagolewski authored and gaborcsardi committed Feb 28, 2011
0 parents commit 2eebedf
Show file tree
Hide file tree
Showing 51 changed files with 3,239 additions and 0 deletions.
20 changes: 20 additions & 0 deletions DESCRIPTION
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
Package: CITAN
Type: Package
Version: 2011.02-1
Date: 2011-02-28
License: LGPL (>= 3)
Depends: R (>= 2.8.0), ADGofTest
Title: CITation ANalysis toolpack
Author: Marek Gagolewski <gagolews@ibspan.waw.pl>
Description: CITAN is a library of functions useful in - but not
limited to - quantitative research in the field of
scientometrics.
Maintainer: Marek Gagolewski <gagolews@ibspan.waw.pl>
Collate: 'CITAN-package.R' 'distrib_hirsch.R' 'distrib_p2.R'
'distrib_sstat.R' 'impact_functions.R' 'impact_visualization.R'
'p2.confint.h.R' 'p2.confint.rho.approx.R' 'p2.confint.rho.R'
'p2.ftest.R' 'p2.goftest.R' 'p2.htest.R' 'p2.zsestimate.R'
'rho.R'
Packaged: 2011-02-27 23:02:29 UTC; gagolews
Repository: CRAN
Date/Publication: 2011-02-28 09:27:32
165 changes: 165 additions & 0 deletions LICENSE.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,165 @@
GNU LESSER GENERAL PUBLIC LICENSE
Version 3, 29 June 2007

Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.


This version of the GNU Lesser General Public License incorporates
the terms and conditions of version 3 of the GNU General Public
License, supplemented by the additional permissions listed below.

0. Additional Definitions.

As used herein, "this License" refers to version 3 of the GNU Lesser
General Public License, and the "GNU GPL" refers to version 3 of the GNU
General Public License.

"The Library" refers to a covered work governed by this License,
other than an Application or a Combined Work as defined below.

An "Application" is any work that makes use of an interface provided
by the Library, but which is not otherwise based on the Library.
Defining a subclass of a class defined by the Library is deemed a mode
of using an interface provided by the Library.

A "Combined Work" is a work produced by combining or linking an
Application with the Library. The particular version of the Library
with which the Combined Work was made is also called the "Linked
Version".

The "Minimal Corresponding Source" for a Combined Work means the
Corresponding Source for the Combined Work, excluding any source code
for portions of the Combined Work that, considered in isolation, are
based on the Application, and not on the Linked Version.

The "Corresponding Application Code" for a Combined Work means the
object code and/or source code for the Application, including any data
and utility programs needed for reproducing the Combined Work from the
Application, but excluding the System Libraries of the Combined Work.

1. Exception to Section 3 of the GNU GPL.

You may convey a covered work under sections 3 and 4 of this License
without being bound by section 3 of the GNU GPL.

2. Conveying Modified Versions.

If you modify a copy of the Library, and, in your modifications, a
facility refers to a function or data to be supplied by an Application
that uses the facility (other than as an argument passed when the
facility is invoked), then you may convey a copy of the modified
version:

a) under this License, provided that you make a good faith effort to
ensure that, in the event an Application does not supply the
function or data, the facility still operates, and performs
whatever part of its purpose remains meaningful, or

b) under the GNU GPL, with none of the additional permissions of
this License applicable to that copy.

3. Object Code Incorporating Material from Library Header Files.

The object code form of an Application may incorporate material from
a header file that is part of the Library. You may convey such object
code under terms of your choice, provided that, if the incorporated
material is not limited to numerical parameters, data structure
layouts and accessors, or small macros, inline functions and templates
(ten or fewer lines in length), you do both of the following:

a) Give prominent notice with each copy of the object code that the
Library is used in it and that the Library and its use are
covered by this License.

b) Accompany the object code with a copy of the GNU GPL and this license
document.

4. Combined Works.

You may convey a Combined Work under terms of your choice that,
taken together, effectively do not restrict modification of the
portions of the Library contained in the Combined Work and reverse
engineering for debugging such modifications, if you also do each of
the following:

a) Give prominent notice with each copy of the Combined Work that
the Library is used in it and that the Library and its use are
covered by this License.

b) Accompany the Combined Work with a copy of the GNU GPL and this license
document.

c) For a Combined Work that displays copyright notices during
execution, include the copyright notice for the Library among
these notices, as well as a reference directing the user to the
copies of the GNU GPL and this license document.

d) Do one of the following:

0) Convey the Minimal Corresponding Source under the terms of this
License, and the Corresponding Application Code in a form
suitable for, and under terms that permit, the user to
recombine or relink the Application with a modified version of
the Linked Version to produce a modified Combined Work, in the
manner specified by section 6 of the GNU GPL for conveying
Corresponding Source.

1) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (a) uses at run time
a copy of the Library already present on the user's computer
system, and (b) will operate properly with a modified version
of the Library that is interface-compatible with the Linked
Version.

e) Provide Installation Information, but only if you would otherwise
be required to provide such information under section 6 of the
GNU GPL, and only to the extent that such information is
necessary to install and execute a modified version of the
Combined Work produced by recombining or relinking the
Application with a modified version of the Linked Version. (If
you use option 4d0, the Installation Information must accompany
the Minimal Corresponding Source and Corresponding Application
Code. If you use option 4d1, you must provide the Installation
Information in the manner specified by section 6 of the GNU GPL
for conveying Corresponding Source.)

5. Combined Libraries.

You may place library facilities that are a work based on the
Library side by side in a single library together with other library
facilities that are not Applications and are not covered by this
License, and convey such a combined library under terms of your
choice, if you do both of the following:

a) Accompany the combined library with a copy of the same work based
on the Library, uncombined with any other library facilities,
conveyed under the terms of this License.

b) Give prominent notice with the combined library that part of it
is a work based on the Library, and explaining where to find the
accompanying uncombined form of the same work.

6. Revised Versions of the GNU Lesser General Public License.

The Free Software Foundation may publish revised and/or new versions
of the GNU Lesser General Public License from time to time. Such new
versions will be similar in spirit to the present version, but may
differ in detail to address new problems or concerns.

Each version is given a distinguishing version number. If the
Library as you received it specifies that a certain numbered version
of the GNU Lesser General Public License "or any later version"
applies to it, you have the option of following the terms and
conditions either of that published version or of any later version
published by the Free Software Foundation. If the Library as you
received it does not specify a version number of the GNU Lesser
General Public License, you may choose any version of the GNU Lesser
General Public License ever published by the Free Software Foundation.

If the Library as you received it specifies that a proxy can decide
whether future versions of the GNU Lesser General Public License shall
apply, that proxy's public statement of acceptance of any version is
permanent authorization for you to choose that version for the
Library.
29 changes: 29 additions & 0 deletions NAMESPACE
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
export(dhirsch)
export(phirsch)
export(rpareto2)
export(ppareto2)
export(qpareto2)
export(dpareto2)
export(dsstat)
export(psstat)
export(index.h)
export(index.g)
export(index.rp)
export(index.lp)
export(Sstat2)
export(Sstat)
export(plot.citfun)
export(curve.add.rp)
export(curve.add.lp)
export(pareto2.confint.h)
export(pareto2.confint.rho.approx.lower)
export(pareto2.confint.rho.approx.upper)
export(pareto2.confint.rho.approx)
export(pareto2.confint.rho.upper)
export(pareto2.confint.rho.lower)
export(pareto2.confint.rho)
export(pareto2.ftest)
export(pareto2.goftest)
export(pareto2.htest)
export(pareto2.zsestimate)
export(rho.get)
115 changes: 115 additions & 0 deletions R/CITAN-package.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,115 @@
#' CITation ANalysis toolpack.
#'
#' CITAN is a library of functions useful in --- but not limited to ---
#' quantitative research in the field of scientometrics.
#'
#' Fair and objective assessment methods of individual scientists
#' had become the focus of scientometricians' attention since the
#' very beginning of their discipline. A quantitative expression
#' of some publication-citation process
#' characteristics is assumed to be a predictor of broadly conceived
#' scientific competence.
#'
#' Among the most popular scientific impact indicators is the
#' \eqn{h}-index, proposed by J. Hirsch (2005).
#' It has been defined as follows. An author who had published \eqn{n}
#' papers has the Hirsch index equal to \eqn{H}, if each of his \eqn{H}
#' publications were cited at least \eqn{H} times, and each of the
#' other \eqn{n-H} items were cited no more than \eqn{H} times. This simple
#' bibliometric indicator
#' quickly received much attention in the academic community
#' and started to be a subject of intensive
#' research. It was noted that contrary to earlier approaches,
#' i.e. publication count, citation count etc.,
#' this measure both concerns productivity and impact of an
#' individual.
#'
#' In a broader perspective, this issue is a special case
#' of the so-called Producer Assessment Problem (Gagolewski, Grzegorzewski, 2010b).
#' Its main aim is to analyze (both theoretically and empirically)
#' a special class of aggregation
#' operators (see Grabisch et al, 2009) called impact functions.
#'
#' The CITAN package consists of three types of tools.
#' Given a numeric vector, the first class of functions computes the values
#' of certain impact functions.
#' Among them are:
#' \enumerate{
#' \item Hirsch's \eqn{h}-index (Hirsch, 2005; see \code{\link{index.h}}),
#' \item Egghe's \eqn{g}-index (Egghe, 2006; see \code{\link{index.g}}),
#' \item the \eqn{r_p} and \eqn{l_p} indices (Gagolewski, Grzegorzewski, 2009a, 2009b;
#' see \code{\link{index.rp}} and \code{\link{index.lp}}), which
#' generalize the \eqn{h}-index and the \eqn{w}-index (Woeginger, 2008), and
#' \item S-statistics (Gagolewski, Grzegorzewski, 2010a, 2011;
#' see \code{\link{Sstat}} and \code{\link{Sstat2}}),
#' which generalize the OWMax operators (Dubois et al, 1988)
#' and the \eqn{h}- and \eqn{r_\infty}-indices.
#' }
#'
#' Additionally, a set of functions dealing with stochastic aspects
#' of the class of S-statistics and the Pareto type-II family of distributions
#' is included (Gagolewski, Grzegorzewski, 2010a). We have the following.
#' The functions that work for any continuous distribution (see Gagolewski, Grzegorzewski, 2010a):
#' \enumerate{
#' \item \code{\link{psstat}}, \code{\link{dsstat}} for computing the distribution of S-statistics
#' generated by a control function,
#' \item \code{\link{phirsch}}, \code{\link{dhirsch}} for computing the distribution of the Hirsch index,
#' \item \code{\link{rho.get}} for computing the so-called \eqn{\kappa}-index (\eqn{\rho_\kappa}),
#' which is a particular location characteristic of a given probability distribution
#' depending on a control function \eqn{\kappa}.
#' }
#' Tools for the Pareto-type II family:
#' \enumerate{
#' \item \code{\link{ppareto2}}, \code{\link{dpareto2}}, \code{\link{qpareto2}}, \code{\link{rpareto2}}
#' for general functions dealing with the Pareto distribution of the second kind,
#' including the c.d.f., p.d.f, quantiles and random deviates,
#' \item \code{\link{pareto2.htest}} --- two-sample \eqn{h}-test for equality of shape parameters based on the difference of \eqn{h}-indices,
#' \item \code{\link{pareto2.ftest}} --- two-sample exact F-test for equality of shape parameters,
#' \item \code{\link{pareto2.zsestimate}} --- estimation of parameters using the Bayesian method (MMSE) developed by Zhang and Stevens (2009),
#' \item \code{\link{pareto2.goftest}} --- goodness-of-fit tests,
#' \item \code{\link{pareto2.confint.rho}} and \code{\link{pareto2.confint.rho.approx}} --- exact and approximate (asymptotic)
#' confidence intervals for the \eqn{\kappa}-index basing on S-statistics,
#' \item \code{\link{pareto2.confint.h}} --- exact confidence intervals for the theoretical \eqn{h}-index.
#' }
#'
#' Moreover, we have implemented some simple graphical methods than may be used
#' to illustrate various aspects of data being analyzed,
#' see \code{\link{plot.citfun}}, \code{\link{curve.add.rp}}, and \code{\link{curve.add.lp}}.
#'
#'
#'
#'
#' Please feel free to send any comments and suggestions (e.g.
#' to include some new bibliometric impact indices) to the author.
#'
#' For a complete list of functions, use \code{library(help="CITAN")}.
#'
#' @name CITAN-package
#' @aliases CITAN
#' @docType package
#' @title CITation ANalysis toolpack
#' @author Marek Gagolewski \email{gagolews@@ibspan.waw.pl}
#' @keywords Hirsch h-index, Egghe g-index, L-statistics, S-statistics, bibliometrics, scientometrics, informetrics,
#' webometrics, aggregation operators, impact functions, impact assessment
#' @references
#' Dubois D., Prade H., Testemale C., Weighted fuzzy pattern matching, Fuzzy Sets and Systems 28, s. 313-331, 1988.\cr
#' Egghe L., Theory and practise of the g-index, Scientometrics 69(1), 131-152, 2006.\cr
#' Gagolewski M., Grzegorzewski P., Possibilistic analysis of arity-monotonic aggregation operators and its relation to bibliometric impact assessment of individuals, International Journal of Approximate Reasoning, doi:10.1016/j.ijar.2011.01.010.\cr
#' Gagolewski M., Grzegorzewski P., A geometric approach to the construction of scientific impact indices, Scientometrics 81(3), 2009a, 617-634.\cr
#' Gagolewski M., Debski M., Nowakiewicz M., Efficient algorithms for computing ''geometric'' scientific impact indices, Research Report of Systems Research Institute, Polish Academy of Sciences RB/1/2009, 2009b.\cr
#' Gagolewski M., Grzegorzewski P., S-statistics and their basic properties, In: Borgelt C. et al (Eds.), Combining Soft Computing and Statistical Methods in Data Analysis, Springer-Verlag, 2010a, 281-288.\cr
#' Gagolewski M., Grzegorzewski P., Arity-monotonic extended aggregation operators, In: Hüllermeier E., Kruse R., Hoffmann F. (Eds.), Information Processing and Management of Uncertainty in Knowledge-Based Systems, CCIS 80, Springer-Verlag, 2010b, 693-702.\cr
#' Grabisch M., Pap E., Marichal J.-L., Mesiar R.. Aggregation functions, Cambridge, 2009.\cr
#' Hirsch J.E., An index to quantify individual's scientific research output, Proceedings of the National Academy of Sciences 102(46), 16569-16572, 2005.\cr
#' Kosmulski M., MAXPROD - A new index for assessment of the scientific output of an individual, and a comparison with the h-index, Cybermetrics 11(1), 2007.\cr
#' Woeginger G.J., An axiomatic characterization of the Hirsch-index, Mathematical Social Sciences 56(2), 224-232, 2008.\cr
#' Zhang J., Stevens M.A., A New and Efficient Estimation Method for the Generalized Pareto Distribution, Technometrics 51(3), 2009, 316-325.\cr
NA



.onLoad <- function(lib, pkg)
{
library.dynam("CITAN", pkg, lib)
# cat("CITAN loaded. Send any comments to <gagolews@ibspan.waw.pl>.\n")
}
46 changes: 46 additions & 0 deletions R/distrib_hirsch.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
#' The probability mass function of Hirsch's \eqn{h}-index
#' for sample of size \code{n} in an i.i.d. model with common increasing and continuous c.d.f. \eqn{F} defined on \eqn{[0,\infty)}.
#'
#' @references
#' Gagolewski M., Grzegorzewski P., S-Statistics and Their Basic Properties, In: Borgelt C. et al (Eds.), Combining Soft Computing and Statistical Methods in Data Analysis, Springer-Verlag, 2010, 281-288.\cr
#'
#' @title Distribution of the \eqn{h}-index - p.m.f.
#' @param x numeric vector.
#' @param n sample size.
#' @param cdf a continuous cumulative distribution function \eqn{F}, e.g. \code{\link{ppareto2}}.
#' @param ... optional arguments to \code{cdf}.
#' @return The value of the p.m.f. at \code{x}.
#' @export
#' @seealso \code{\link{index.h}}, \code{\link{rho.get}}, \code{\link{phirsch}}
dhirsch <- function(x, n, cdf, ...)
{
phirsch(x+1e-9, n, cdf, ...)-phirsch(x-1e-9, n, cdf, ...)
}


#' The cumulative distribution function of Hirsch's \eqn{h}-index
#' for sample of size \code{n} in an i.i.d. model with common increasing and continuous c.d.f. \eqn{F} defined on \eqn{[0,\infty)}.
#'
#' @references
#' Gagolewski M., Grzegorzewski P., S-Statistics and Their Basic Properties, In: Borgelt C. et al (Eds.), Combining Soft Computing and Statistical Methods in Data Analysis, Springer-Verlag, 2010, 281-288.\cr
#'
#' @title Distribution of the \eqn{h}-index - c.d.f.
#' @param x numeric vector.
#' @param n sample size.
#' @param cdf a continuous cumulative distribution function \eqn{F}, e.g. \code{\link{ppareto2}}.
#' @param ... optional arguments to \code{cdf}.
#' @return The value of the c.d.f. at \code{x}.
#' @export
#' @seealso \code{\link{index.h}}, \code{\link{rho.get}}, \code{\link{dhirsch}}
phirsch <- function(x, n, cdf, ...)
{
warn <- getOption("warn");
options("warn"=-1);
y <- ifelse(x>n-1e-16, 1.0,
ifelse(x<0, 0.0,
pbeta(cdf(floor(x+1), ...), n-floor(x),floor(x)+1)));
options("warn"=warn);
return(y);
}


0 comments on commit 2eebedf

Please sign in to comment.