Search found 432 matches

by GeorgeLeckie
Thu Mar 11, 2021 8:20 pm
Forum: runmlwin user forum
Topic: Coefficient legends after runmlwin
Replies: 2
Views: 1178

Re: Coefficient legends after runmlwin

Hi Manuel,

If you type

. matrix list e(b)

You will see the vector of parameter estimates and you can then refer to them by their column names. For example...

display _b[FP1:cons]

Best wishes

George
by GeorgeLeckie
Tue Feb 02, 2021 1:27 pm
Forum: runmlwin user forum
Topic: Is it possible to constrain the residual variance in MLwiN?
Replies: 5
Views: 1756

Re: Is it possible to constrain the residual variance in MLwiN?

Hi Erik, This would be my guess at what you want to do... Think you want to specify a three-level model. So shift the usual two-level growth-curve model up to level-2 and level-3 Observations (level-1) within observations (level-2) within persons (level-3) Then at the new level-1 you enter the const...
by GeorgeLeckie
Thu Jan 09, 2020 7:36 pm
Forum: runmlwin user forum
Topic: The difference of the results of "mixed" and "runmlwin"
Replies: 1
Views: 1679

Re: The difference of the results of "mixed" and "runmlwin"

Dear Umitotakao, Thank you for your query. I'm afraid I don't have a good answer for you. However, at least in the example below, mixed and runmlwin provide very similar model-based standard errors to one another and equally they provide very similar cluster-robust standard errors to one another. So...
by GeorgeLeckie
Wed Jan 08, 2020 4:00 pm
Forum: runmlwin user forum
Topic: How can I plot a caterpillar plot using odd ratios
Replies: 3
Views: 2339

Re: How can I plot a caterpillar plot using odd ratios

Dear nabilshaaban, You need to first create a dataset with the predicted odds ratio of each hospital and the the associated limits of the 95% CI. Once you have done that you need to plot the results. You can do this with the twoway command and the scatter option for the point estiamates and the rcap...
by GeorgeLeckie
Fri Dec 06, 2019 3:59 pm
Forum: runmlwin user forum
Topic: Four-level CCM, variance components
Replies: 3
Views: 2309

Re: Four-level CCM, variance components

Dear dand1994, "I have used: runmlwin s_roa cons, level6(home : cons) level5(firm: cons) level4(industry: cons) level3(host: cons) level2(unit: cons) level1(year: cons) mcmc(cc) initsprevious nopause, although I do not believe it to be forrect" What you have written is correct for a cross-...
by GeorgeLeckie
Fri Aug 23, 2019 4:02 pm
Forum: runmlwin user forum
Topic: Inconsistent results from runmlwin and svy:mean
Replies: 2
Views: 2547

Re: Inconsistent results from runmlwin and sys:mean

Dear Sun, Not sure, but am not that experienced in Stata's svyset commands runmlwin should give the same results as Stata's mixed command. So suggest you first compare your svyset method to mixed (where you use the mixed weights options). Assuming mixed and runmlwin give same results, Suggest then t...
by GeorgeLeckie
Thu Aug 01, 2019 3:18 pm
Forum: MLwiN user forum
Topic: Mediation
Replies: 1
Views: 2278

Re: Mediation

Dear Vicky, There is no automation of multilevel mediation analysis in MLwiN. You would need to implement the models and carry out any post-estimation tests by hand. There are no training materials on multilevel mediation analysis in MLwiN that I am aware of though you should be able to replicate th...
by GeorgeLeckie
Tue Jul 23, 2019 9:33 am
Forum: runmlwin user forum
Topic: jackknife replicate weight in runmlwin
Replies: 3
Views: 3144

Re: jackknife replicate weight in runmlwin

Hi Sun Lee, Yes you can specify weights in runmlwin. You need to specify weights at each level in the model. See the help file and search for "weight" to find the weights options. Unfortunately we do not have an example to show you. There is an example in the Stata ME manual for their -mix...
by GeorgeLeckie
Mon Jul 08, 2019 12:04 pm
Forum: runmlwin user forum
Topic: Mixed-effects, mixed distribution model
Replies: 1
Views: 3850

Re: Mixed-effects, mixed distribution model

Dear Gujarish, No you cannot fit this specific model in MLwiN. For these data, what you could do in MLwiN is fit the analyses in two parts. First, fit a multilevel model for whether peopled walked at all (0 steps vs 1+ steps) Then for the subset who had 1+ steps you could fit a multilevel model for ...
by GeorgeLeckie
Mon Jun 10, 2019 9:09 am
Forum: runmlwin user forum
Topic: autocorrelation problem in within-between random effect model
Replies: 10
Views: 7867

Re: autocorrelation problem in within-between random effect model

Dear umitotakao,

You can specify cluster robust standard errors in runmlwin

See the fpsandwich option

Note. If you wish to exclude the random effect from the model then you will need to constrain this parameter to zero, otherwise MLwiN won't know what the clusters are.

Best wishes

George