What is the current state of the R-art for ordered probit models, and more esoterically is there any available R strategy for ordered cauchit models, i.e. ordered multinomial alternatives with a cauchy link function. MCMC is an option, obviously, but for a univariate latent variable model this seems to be overkill... standard mle methods should be preferable. (??) Googling reveals that spss provides such functions... just to wave a red flag.> url: www.econ.uiuc.edu/~roger Roger Koenker > email rkoenker at uiuc.edu Department of Economics > vox: 217-333-4558 University of Illinois > fax: 217-244-6678 Champaign, IL 61820
On Wednesday, Sep 22, 2004, at 03:42 Europe/London, roger koenker wrote:> What is the current state of the R-art for ordered probit models, and > more > esoterically is there any available R strategy for ordered cauchit > models, > i.e. ordered multinomial alternatives with a cauchy link function. > MCMC > is an option, obviously, but for a univariate latent variable model > this seems > to be overkill... standard mle methods should be preferable. (??) >A quick look at polr (in the MASS package) suggests to me that it wouldn't be all that hard to extend it to link functions other than logistic. Is MLE known to be well behaved in these models if the latent variable is Cauchy? David> Googling reveals that spss provides such functions... just to wave a > red > flag. > >> url: www.econ.uiuc.edu/~roger Roger Koenker >> email rkoenker at uiuc.edu Department of >> Economics >> vox: 217-333-4558 University of Illinois >> fax: 217-244-6678 Champaign, IL 61820 > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide! > http://www.R-project.org/posting-guide.html
roger koenker wrote:> What is the current state of the R-art for ordered probit models, and > more > esoterically is there any available R strategy for ordered cauchit > models, > i.e. ordered multinomial alternatives with a cauchy link function. MCMC > is an option, obviously, but for a univariate latent variable model > this seems > to be overkill... standard mle methods should be preferable. (??) > > Googling reveals that spss provides such functions... just to wave a red > flag. >I find polr(MASS) Ordered Logistic or Probit Regression MCMCoprobit(MCMCpack) Markov chain Monte Carlo for Ordered Probit Regression and in Jim Lindsey's gnlm there is nordr Nonlinear Ordinal Regression ordglm Generalized Linear Ordinal Regression Kjetil -- Kjetil Halvorsen. Peace is the most effective weapon of mass construction. -- Mahdi Elmandjra