Message/Author 


Hello, can I use replicate weights such as wt1  wt42 rather than one probability weight with the complex sample routines in Mplus? Thanks Pat Berglund. 


An article by Laura Stapleton came out in the most recent issue of the SEM journal which shows how to use SAS in conjunction with Mplus and replicate weights. We will eventually be adding this to Mplus. In the meantime, you can see that article. 


Thanks, I will check this out. Pat Berglund 


Dear Dr. Asparouhov and Dr. Muthen, In your paper "Asparouhov, T., & Muthen, B. O. (2010). Resampling methods in Mplus for complex survey data. Los Angeles: Muthen & Muthen", you provide syntax for using replicate weights: DATA: FILE IS ECLS repw.dat; VARIABLE: NAMES=C1RGSCAL C1RMSCAL C1RRSCAL P1NUMPLA C1CPTW0 C1CPTSTR NEWPSU W1W90; USEVAR=C1RGSCAL C1RMSCAL C1RRSCAL P1NUMPLA; WEIGHT=C1CPTW0; REPWEIGHT=W1W90; ANALYSIS: TYPE=COMPLEX; REPSE=JACKKNIFE2; What is the variable "C1CPTW0"? final student sampling weight? Many thanks. Mark 


It's the original sampling weight variable. 


Hi Linda  I'm using the ECLSK data and am confused after reading the above paper and the others by Tihomir on analyzing multilevel complex samples in Mplus  about which weights to use for these data. The file for the longitudinal data comes with both PSU and Strata weights, and full sample weights and Jackknife2 replicate weights for the kids. Since I want to take the unequal selection probabilities of the schools into account for my longitudinal analysis, I'm thinking that I should set up a growth model multivariate style, but as a multilevel model to take PSUs and strata into account. So, do I use the Taylor linearization weights for the clusters and strata for the multilevel part, as well as the full sample and JK2 replicate weights for the kids? Thanks! Bruce 


Hi Linda  Whoops! I answered my own question by rereading the manual, of all things. Where it says clearly "The STRATIFICATION and CLUSTER options may not be used in conjunction with the REPWEIGHTS option." So, I guess the best thing would be to try the analysis both ways: with COMPLEX TWOLEVEL and with REPWEIGHTS? Thanks, Bruce 


That seems reasonable. 

Stata posted on Thursday, September 13, 2012  9:27 pm



Dr. Muthen, In the complex survey data I am working now has only one weightfinal weight. Can final weight be placed under WEIGHT command? Thank you. 


Yes. 

Dan Li posted on Wednesday, June 10, 2015  8:27 pm



Hi Dr. Muthen, I am using PISA data to do a SEM. PISA use Fay's replicate weights. I read your paper "Asparouhov, T., & Muthen, B. O. (2010). Resampling methods in Mplus for complex survey data. Los Angeles: Muthen & Muthen", you provide syntax for using replicate weights: DATA: FILE IS ECLS repw.dat; VARIABLE: NAMES=C1RGSCAL C1RMSCAL C1RRSCAL P1NUMPLA C1CPTW0 C1CPTSTR NEWPSU W1W90; USEVAR=C1RGSCAL C1RMSCAL C1RRSCAL P1NUMPLA; WEIGHT=C1CPTW0; REPWEIGHT=W1W90; ANALYSIS: TYPE=COMPLEX; REPSE=JACKKNIFE2; I put REPSE=Fay; the results only give me RMSEA and SRMR not give me CFI and TLI. I am wondering how I get CFI and TLI value 


They are not available with replicate weights because the chisquare is not available and is not theoretically developed yet. 

Dan Li posted on Thursday, June 11, 2015  10:10 pm



Thank you for your help. 


Hello, If I only have the weight (and not strata and cluster) for my data, and I want to get biascorrected bootstrapped confidence intervals for indirect effects in a mediation model, is it correct to do the following under the analysis and output commands? Is repse=bootstrap needed under analysis? Or can replicate weights not be calculated when we do not have strata and cluster? Analysis: bootstrap=1000; Output: cinterval (bcbootstrap); Thanks, Dharmi 


You need strata, cluster, or both to generate replicate weights. 


Dear Dr Muthen, I am using PISA data to do SEM with one dichotomous variable and several continuous variables. I use WLSMV method of estimation. How can I get fit indices for the model? can I also test indirect effects in mediational part of the model? Thanks, Sylwia 


If you are using replicate weights, fit statistics are not available. 


Dear Dr. Muthen, I am running a path model and I want to control for complex design of the survey. In the survey I have following weights: sampling weight = a_weight cluster = b_weight strata = c_weight In my command, I specify each weight under VARIABLE command: VARIABLE: WEIGHT = a_weight; CLUSTER = b_weight; STATIFICATION = c_weight; In ANALYSIS I use: TYPE = COMPLEX; BOOTSTRAP = 2000; REPSE = BOOTSTRAP; I have 3 questions regarding my syntax. 1. Do these codes are correctly specified? 2. Although showed in the earlier threads, if I use these codes then I can't get fit indices, such as CFI, TLI, am I correct? If so, can you suggest me any reference so that I can cite? 3. How to determine my model fit if fit indices are not provided? Thank you so much! Yuchih 


1. Probably assuming the CLUSTER = b_weight; STATIFICATION = c_weight; really specify the clusters and the strata. These are not weights. 2 and 3. You can remove BOOTSTRAP = 2000; REPSE = BOOTSTRAP; and you will get fit indices. The bootstrap method concerns standard errors. It doesn't change the point estimates. The bootstrap version of chisquare (BollenStine) is not available yet in these complex sampling settings. 


Dear Tihomir, Thank you so much for your reply! For a followup question regarding your response on my Q2 and Q3. If I am testing indirect effects in my path model, can I keep these two commands (BOOTSTRAP = 2000; REPSE = BOOTSTRAP; ) in my syntax so that I can get a bootstrap estimation for indirect effects? Thank you again for your helpful comments! YuChih 


Definitely  you should do that. 


Hi, I have only one sampling weight variable. How can I obtain replicate weight variable to analysis data with complex design. Best regards, Jintana 


See our replicate weight document at: http://www.statmodel.com/download/Resampling_Methods5.pdf 


Hi I am looking for a statistical software to conduct a multilevel analysis (threelevels, dependent variable = binary 0/1) using replicate weights (complex survey design) as well as plausible values (measurement error) and multiply imputed data  is there a possibility to run such an analysis (combining all these features) in MPlus? (to me it seems that using multilevel commands in MPlus require stratification and PSU indicators and do not allow for replicate weights in conjunction with a cluster variable for the hierarchical levels?) Thank you very much! 


Replicate weights are not available in Mplus for multilevel models. 


Hi Drs. Muthen, Since "MODEL TEST is not available with replicate weights", do you have any suggestions if I want to compare two effects? Thanks! 


Use something like that model: Y1 on X1 (effect1); Y2 on X2 (effect2); model constraint: new(diff); diff=effect1effect2; This will give you the significance of the difference of the two effects. 


Thank you Dr. Asparouhov, for your very quick response with the Mplus command! It works great! Problem Solved! Thank you! 

shonnslc posted on Monday, November 25, 2019  6:55 am



Hi, As far as I know, Mplus doesn't provide fit indices when replicate weights are used. Then, how can I evaluate my SEM model(global fit) in this case? Also, reviewers are going to ask for the information if SEM is employed. Any suggestions? Thank you so much. 


Replicate weights based test of fit is not available. Include as much of the sampling information as you have: sampling weights etc. (excluding the replicates weights) and run type=complex to get fit indices and chisquare. I suppose if you compare the replicate weights SE and the type=complex SE you can make an approximate design effect of some kind which can be used to attempt to correct the test of fit but you are on your own with that. If the SE are not very different I would read that as endorsement that the test of fit and fit indices of type=complex are good enough. 


Dear MplusTeam, I want to use Mplus to generate replicate weights, but not as in the user guide for a factor model, but for an entire data set containing about 200 mainly ordinal items. Similar to Pisa, where they provide brr for the whole data set. How could this be done in Mplus. As I understand, the generation of repweights is independet from the analysed model. Only sampling weights, strata and clustering information are needed to calculate the weights. Thus, could I use an abritrary model in conjunction with an Idvariable to merge the repweights to the whole data set? Thanks Christoph 


Correct. You don't need a model. You can specify the Usevar = option to get the replicate weights and the variables you want for further analysis in the same file. 


thanks a lot! christoph 

Back to top 