Anonymous posted on Thursday, October 03, 2002 - 4:03 pm
How may one evaluate the significance level of correlations among the variables printed in the estimated sample statistics of LGM modeling with missing data? Does Mplus compute significance tests of these correlations?
bmuthen posted on Friday, October 04, 2002 - 6:57 pm
With missing data, you can obtain the estimated sample covariance matrix and the corresponding s.e.'s through type = basic missing and using the H1SE option (see user's guide). However, these s.e. pertain to covariances, not correlations.
To get the correlation s.e.'s that I think you are asking for requires a bit more work using either of two alternatives. First, if you are familiar with the "Delta Method" you can get the s.e.'s via this method via the covariance matrix among the parameter estimates by requesting H1TECH3. Second, you can get the s.e.'s through a model (so not using type = basic) that has Sigma = Lambda * Psi * Lambda', where with p variables Lambda is p x p diagonal and Psi is full p x p with unit, fixed diagonal elements. This can be done by saying that you have one factor for each variable and that you have zero residual variances. Lambda will contain your standard deviations and Psi will contain your correlations. The Psi estimates and s.e.'s are the ones you want.
to estimate correlations among several continuous and categorical variables with missing data.
Is it appropriate to use the resulting S.E. FOR CORRELATION MATRIX to calculate the significance of the correlations by calculating the ratio of the estimated correlation divided by its SE and comparing it to the critical value?
You could specify all of the WITH statements in the MODEL command and ask for STANDARDIZED in the OUTPUT command. You will obtain standard errors for the standardized coefficients which are correlations.
Tybeert posted on Wednesday, June 15, 2011 - 5:13 am
I used this method to obtain standardized coefficients and their correlations at the within level by specifying all of the WITH statements at the within level. If it is true that these are correlations, I would expect them to be exactly the same as the within correlations in the SAMPSTAT output. However, they are not. My question is why this difference exists, which of the two outputs are the ‘real’ correlations, and which of these correlations I should report. Thank you very much.
My output is not showing a column for statistical significance under Model Results (parameter estimations). I am getting Estimate, SE, and EST/SE but no significance. What should I specify in my input?
I am using type=basic to get descriptive statistics for several continuous manifest variables, while accounting for missing data. I will later include these variables in a model.
Is it possible to get the significance levels for the correlations between all of these variables? I am able to get standard errors for the means and covariances but not for the correlations to determine the significance. I apologize if my question is redundant from those above - I was not able to figure out the answer from them. Thank you for your time.
Hi Linda, I have a follow up question from a reply you had given back in 2011. (June 15, 2011 - 10:06). I tried to get the correlations (and their significance) of a three-level data set with the two methods: a) through the type THRELEVEL BASIC b) through estimating them with the "WITH" statement in which I included also the SAMPSTAT output. I noticed also that the correlation matrices in the SAMPSTAT in "a" differs from the SAMPSTAT in "b"; I also noticed that the SAMPSTAT in "a" is almost identical with the standardized solution of "b". So, my question is, on which SAMPSTAT should we rely in multilevel structures? This coming from "a" (i.e., SAMPSTAT as derived from the "THREELEVEL BASIC") or from "b" (i.e., SAMPSTAT as derived from the "WITH" estimates)? If the former, is there any way to get the significance level? I thank you for your consideration Thanasis Mouratidis