RE: st: Implementation of Latent Variable Model with SEM Builder

[Cameron McIntosh <cnm100@hotmail.com>]

And to follow up on John`s index idea, it also seems to me that the indicators of health are causal rather than reflective (i.e., health is not a latent variable that mutually influences blood pressure, chronic disease, and physical limitations, rather, these variables cause/form health status... and are also clinimetric rather than psychometric). Please see:

Fayers P.M., & Hand, D.J. (2002). Causal variables, indicator variables, and measurement scales: an example from quality of life. Journal of the Royal Statistical Society, Series A, 165(2), 233-261.

Fayers P.M., & Hand, D.J. (1997). Factor analysis, causal indicators, and quality of life. Quality of Life Research, 6, 139-150.

Boehmer, S., & Luszczynska, A. (2006). Two Kinds of Items in Quality of Life Instruments: ‘Indicator and Causal Variables’ in the EORTC QLQ-C30. Quality of Life Research, 15(1), 131-141.

Fayers P.M. (2004). Quality-of-life measurement in clinical trials--the impact of causal variables. Journal of Biopharmaceutical Statistics, 14(1), 155-176.ftp://124.42.15.59/ck/2011-04/165/027/480/531/Quality-of-Life%20Measurement%20in%20Clinical%20Trials%A1%AAThe%20Impact%20of%20Causal%20Variables..pdf

Buis, M.L. (yyyy). Combining information from multiple variables using models for causal indicators. The Stata Journal, vv(ii), 1–14.http://www.maartenbuis.nl/wp/prop.pdf

Bollen, K.A., & Bauldry, S. (2011). Three Cs in measurement models: Causal indicators, composite indicators, and covariates. Psychological Methods, 16(3), 265-284. 

Bollen, K.A. (2011). Evaluating Effect, Composite, and Causal Indicators in Structural Equation Models. MIS Quarterly, 35(2), 359-372.

Cam

> Date: Sat, 14 Apr 2012 10:15:08 +0200
> From: John.Antonakis@unil.ch
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Implementation of Latent Variable Model with SEM Builder
> 
> Hi:
> 
> You need to do (latent variables are in CAPS in Stata and I am assuming 
> education is categorical):
> 
> xi: sem (OBJ_HEALTH->blood chronic limit) (sah<-age i.education OBJ_HEALTH)
> 
> If sah is not truly continuous but ordered, then I am afraid you cannot 
> use Stata here (MPlus could do this for you--hope that Stata Corp adds 
> the option to use categorical and ordered dependent variables in sem in 
> the future).  Other thing to do would be to create an index of objective 
> health and then to simply estimated it with
> 
> oprob sah age i.education index_obj_health
> 
> HTH,
> J.
> 
> __________________________________________
> 
> Prof. John Antonakis
> Faculty of Business and Economics
> Department of Organizational Behavior
> University of Lausanne
> Internef #618
> CH-1015 Lausanne-Dorigny
> Switzerland
> Tel ++41 (0)21 692-3438
> Fax ++41 (0)21 692-3305
> http://www.hec.unil.ch/people/jantonakis
> 
> Associate Editor
> The Leadership Quarterly
> __________________________________________
> 
> 
> On 14.04.2012 07:55, Samantha Molbach wrote:
> > Dear Statalisters,
> >
> > I need some help in implementing a Structural Equation Model in Stata
> > 12. I want to create a health index according to Bound (1999): "The
> > dynamic effects of health on the labor force transitions of older
> > workers".
> >
> > I have the following variables available: Self-assessed health on a
> > five-point scale (SAH), Age, Education, different objective measures
> > of health such as blood pressure (Blood), chronic diseases (chronic)
> > and physical limitations (limit).
> >
> > The theoretical model is the following:
> > H = X*ß1 + Z*ß2 + u
> > with  H=true health; X= socioeconomic variables; Z=objective health
> > measures; u=error term
> >
> > I do not observe the true health, but only the self-assessed health
> > which includes a reporting error e, thus:
> > SAH = H + e
> > SAH = X*ß1 + Z*ß2 + v (with v=u+e)
> >
> > I estimate the last equation via SEM the following way:
> > sem (age ->  sah) (education ->  sah) (blood ->  sah) (chronic ->  sah)
> > (limit ->  sah)
> >
> > Then, I'm stuck - how do I get back to the first equation and model
> > the health indicator H? Also, can I estimate an ordered Probit model
> > in SEM?
> > I tried to use "SEM-Predictions", but I have the feeling that I need
> > to define a latent variable first in the SEM model. I'm totally new
> > with latent variable models - could it be that both the health index
> > and SAH are latent variables with the latter one being endogenous?
> >
> > I hope that my problem is understandable. Any help will be very
> > appreciated, also some literature advice - thank you very much in
> > advance!
> >
> > Samantha
> >
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/help.cgi?search
> > *   http://www.stata.com/support/statalist/faq
> > *   http://www.ats.ucla.edu/stat/stata/
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/