Tim Bates

why was this closed? the agreement was that no change was needed for an orthogonal issue about (looks up...) the term status in the output of an identification checker. but...

cool: just wanting to register the decision - no catch in model building, no report in failed model.

Agree with @jpritikin about not giving people warnings: they just frighten users. In this case we should simply add a conditional string appended to the existing Code 5 ```R if(latentX...

Great progress! Comparing two single group models, the `SBchisq` column is printed, but is NaN, as is the p column. regular `chisq` is also printed (is that by design and...

No p-value or fit for the above example (as of OpenMx version: 2.18.1.233 [GIT v2.18.1-233-ga849f4e3]) ```R mxCompare(w1, w2) base comparison ep chisq df AIC SBchisq diffdf p 1 DWLS 6...

Yeah, but I think the purpose of adding `SBChisq` was to enable comparison of nested models and p-values? Satorra, A. & Bentler, P.M. (2010). Ensuring positiveness of the scaled difference...

For `summary`, keeping semantic labels on paths is valuable for the user: They don't have to mentally strip off the brackets or look up what the index pointed too, and...

Discussion today 1. Do labels on an algebra create any side effects? 2. Need to fix the path label

Righty, so setting `X$label` to a bracket label requires that `X$free == FALSE` (Same I think for `X$label= “data.z” - X$free must == fixed`, and `X$value` is ignored) So if...

#78 is relevant for this issue to (in terms of the confidence limit = NaN and user work required with summary(), 'CI details' table, possible subtraction of fit at the...