
Message/Author 

RJM posted on Thursday, September 15, 2005  8:14 am



I would like to specify a model having an induced latent variable, that is, an endogenous latent variable having no indicators and being wholly defined by its predictors. I imagine the code something like as follows, but this is obviously incorrect: eta1 on x1@1 eta1 on x2; eta1@0; y1 on eta1 x3 x4; Is it possible to specify an induced variable using Mplus? 


I think you are asking about formative indicators. Following is a description from an earlier post by Bengt: "In some applications it may be more natural to let a factor be defined as being influenced by indicators, rather than influencing the indicators. An example is SES. Mplus handles this modeling by the following model statements. f by y*; f@0; f on x1@1 x2 x3; Note that f by y* (that is, freeing the factor loading for the single indicator y) is the same as y on f. f has to be defined by some y  if instead you use the dummy definition f by y@0; y on f; the estimate shows up in f by y." 

RJM posted on Thursday, September 15, 2005  8:43 am



Yes, this is just right. Thank you. 

Back to top 

