Dear R Users: The functions of our "micEcon" package [1,2] can be subdivided into three categories: - microeconomic demand and firm models - sample selection models (mainly selection()) - routines for (likelihood) maximisation (e.g. maxLik(), maxNR(), maxBHHH()) (mainly used for ML estimation of sample selection models) Although sample selection models are often used in microeconomic analyses, they are also used in several other disciplines. Therefore, we are unsure whether it is better to keep these different functionalities in the micEcon package or to move the sample selection models and the routines for (likelihood) maximisation into one or two new package(s) (increasing the long list of R packages even further). What is the recommendation of the R community? Thank you, Ott & Arne Note: We have asked this question already on R-devel five days ago [3], but we did not receive an answer yet. References: [1] http://cran.r-project.org/src/contrib/Descriptions/micEcon.html [2] http://www.micecon.org/ [3] http://tolstoy.newcastle.edu.au/R/e3/devel/07/10/0222.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 ahenningsen at agric-econ.uni-kiel.de http://www.uni-kiel.de/agrarpol/ahenningsen/ -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: not available Url : https://stat.ethz.ch/pipermail/r-help/attachments/20071030/7c542818/attachment.bin
Dear Arne and Ott-Simm It always seemed weird to me mixing demand and firm models with SSel. models on a single package. Separating them would seem the logical thing to do. On the other hand, one more R package :/ , I?m not too big of a fan of increasing this list ad infinitum. My take on this is that it would be worth it to split it if you think you?ll keep expanding the SSel. models under the new package. Otherwise keep it the way it is. I still dream of contributing a package that offers a group of SSel. models under a wide variety of settings, but still haven?t found the time to do so, nor it seems i?ll have it in the near future. On the other hand, judging by the low number of replies it seems to me that the audiece for SSel. in R is still quite limited. My two cents, greetings robert On 10/30/07, Arne Henningsen <ahenningsen at email.uni-kiel.de> wrote:> Dear R Users: > > The functions of our "micEcon" package [1,2] can be subdivided into three > categories: > - microeconomic demand and firm models > - sample selection models (mainly selection()) > - routines for (likelihood) maximisation (e.g. maxLik(), maxNR(), maxBHHH()) > (mainly used for ML estimation of sample selection models) > > Although sample selection models are often used in microeconomic analyses, > they are also used in several other disciplines. Therefore, we are unsure > whether it is better to keep these different functionalities in the micEcon > package or to move the sample selection models and the routines for > (likelihood) maximisation into one or two new package(s) (increasing the long > list of R packages even further). > What is the recommendation of the R community? > > Thank you, > Ott & Arne > > Note: We have asked this question already on R-devel five days ago [3], > but we did not receive an answer yet. > > References: > [1] http://cran.r-project.org/src/contrib/Descriptions/micEcon.html > [2] http://www.micecon.org/ > [3] http://tolstoy.newcastle.edu.au/R/e3/devel/07/10/0222.html > > -- > Arne Henningsen > Department of Agricultural Economics > University of Kiel > Olshausenstr. 40 > D-24098 Kiel (Germany) > Tel: +49-431-880 4445 > Fax: +49-431-880 1397 > ahenningsen at agric-econ.uni-kiel.de > http://www.uni-kiel.de/agrarpol/ahenningsen/ > > ______________________________________________ > R-help at r-project.org mailing list > 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. > > >
Dear Arne and Ott-Siim,
my personal opinion is that one single package is easiest both for the
useR who wants to keep track of the add-ins he might need and for the
maintainer(s) of the relevant Task Views. I'd prefer to have one single
micEcon as long as I know that I've to look there both for micro demand
models and for sample selection. Moreover, I feel they fit together
nicely from a broad econometric viewpoint (if this means anything).
Of course, if splitting the package up means easing the maintenance
burden in any way, we'll just keep track of one more package... :^)
Best regards and many thanks for your effort
Giovanni
Giovanni Millo
Research Dept.,
Assicurazioni Generali SpA
Via Machiavelli 4,
34131 Trieste (Italy)
tel. +39 040 671184
fax +39 040 671160
#################
Original message:
Message: 34
Date: Tue, 30 Oct 2007 18:44:12 +0200
From: Arne Henningsen <ahenningsen at email.uni-kiel.de>
Subject: [R] Splitting up the micEcon package?
To: r-help at r-project.org
Cc: Ott-Siim Toomet <ott.toomet at ut.ee>
Message-ID: <200710301744.47349.r-devel-bounces at r-project.org>
Content-Type: text/plain; charset="us-ascii"
Dear R Users:
The functions of our "micEcon" package [1,2] can be subdivided into
three
categories:
- microeconomic demand and firm models
- sample selection models (mainly selection())
- routines for (likelihood) maximisation (e.g. maxLik(), maxNR(),
maxBHHH())
(mainly used for ML estimation of sample selection models)
Although sample selection models are often used in microeconomic
analyses,
they are also used in several other disciplines. Therefore, we are
unsure
whether it is better to keep these different functionalities in the
micEcon
package or to move the sample selection models and the routines for
(likelihood) maximisation into one or two new package(s) (increasing the
long
list of R packages even further).
What is the recommendation of the R community?
Thank you,
Ott & Arne
Note: We have asked this question already on R-devel five days ago [3],
but we did not receive an answer yet.
References:
[1] http://cran.r-project.org/src/contrib/Descriptions/micEcon.html
[2] http://www.micecon.org/
[3] http://tolstoy.newcastle.edu.au/R/e3/devel/07/10/0222.html
--
Arne Henningsen
Department of Agricultural Economics
University of Kiel
Olshausenstr. 40
D-24098 Kiel (Germany)
Tel: +49-431-880 4445
Fax: +49-431-880 1397
ahenningsen at agric-econ.uni-kiel.de
http://www.uni-kiel.de/agrarpol/ahenningsen/
####################
Ai sensi del D.Lgs. 196/2003 si precisa che le informazi...{{dropped:13}}