Dear adschai, > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] > Sent: Monday, April 09, 2007 8:30 PM > To: John Fox; [email protected] > Subject: Re: RE: [R] Dealing with large nominal predictor in > sem package > > Hi John, > > Additional two questions on this sem package: > (1) The tsls is based on maximum likelihood or OLS?
Neither; it does two-stage least-squares (2SLS). > (2) I am trying to find goodness of fit for the result of > tsls. Somehow, I don't see it in the documentation. Would you > please provide some examples? I'm not sure what you mean by goodness of fit. If you have in mind an R^2-like measure; you can always use 1 - error-variance/variance-of-endogenous-variable, but this is not guaranteed to be positive. > (3) If I would like to diagnostic of model selection, says > use AIC criteria, it is a bit unclear for me how I can apply > this on structural equation model as it is composed of > multiple equations rather than one. And is there any > functionality in sem that does this? Since there's no likelihood for 2SLS estimation, I don't see how you could get an AIC. On the other hand, sem() fits by full-information maximum-likelihood (FIML). It prints out the BIC; you could compute the AIC if you liked. John > Any help would be really appreciated. Thank you. > > - adschai > > ----- Original Message ----- > From: John Fox > Date: Monday, April 9, 2007 8:04 am > Subject: RE: [R] Dealing with large nominal predictor in sem package > To: [EMAIL PROTECTED] > Cc: [email protected] > > > Dear adschai, > > > > It's not possible to know from your description exactly what you're > > doing, but perhaps the following will help: > > > > (1) I presume that your nominal variable is exogenous, > since otherwise > > it wouldn't be sensible to use 2SLS. > > > > (2) You don't have to make your own dummy regressors for a nominal > > variable; just represent it in the model as a factor as you would, > > e.g., in lm(). > > > > (3) Do you have at least as many instrumental variables > (including the > > dummy > > regressors) as there are structural coefficients to > estimate? If not, > > the structural equation is underidentified, which will produce the > > error that you've encountered. > > > > I hope this helps, > > John > > > > -------------------------------- > > John Fox > > Department of Sociology > > McMaster University > > Hamilton, Ontario > > Canada L8S 4M4 > > 905-525-9140x23604 > > http://socserv.mcmaster.ca/jfox > > -------------------------------- > > > > > -----Original Message----- > > > From: [EMAIL PROTECTED] > > > [mailto:[EMAIL PROTECTED] On Behalf Of > > > [EMAIL PROTECTED] > > > Sent: Sunday, April 08, 2007 11:07 PM > > > To: [email protected] > > > Subject: [R] Dealing with large nominal predictor in sem package > > > > > > Hi, > > > > > > I am using tsls function from sem package to estimate a > model which > > > includes large number of data. Among its predictors, it has a > > > nominal data which has about 10 possible values. So I expand this > > > parameter into 9-binary-value predictors with the coefficient of > > > base value equals 0. I also have another continuous predictor. > > > > > > The problem is that, whenever I run the tsls, I will get > 'System is > > > computationally singular' error all the time. I'm > wondering if there > > > is anyway that I can overcome this problem? Please kindly > suggest. > > > Thank you so much in advance. > > > > > > - adschai > > > > > > [[alternative HTML version deleted]] > > > > > > ______________________________________________ > > > [email protected] 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. > > > > > > > > > > ______________________________________________ [email protected] 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.
