Quantcast
Channel: The Stata Blog - Latest Comments
Viewing all 1125 articles
Browse latest View live

Re: How to successfully ask a question on Statalist

$
0
0

Hi,
I typed bysort idc: egen y_mean_x=mean($ylist)
twoway scatter $ylist idc, msymbol(circle_hollow) || connected y_mean_x idc, msymbol(diamond)
graph save graph1, replace
Stata responded unknown egen function mean() r(133);


Re: Statalist

$
0
0

Hi ,
I typed
bysort idc: egen y_mean_x=mean($ylist)
twoway scatter $ylist idc, msymbol(circle_hollow) || connected y_mean_x idc, msymbol(diamond)
graph save graph1, replace
and Stata responded
unknown egen function mean()
r(133);

Re: Measures of effect size in Stata 13

$
0
0

I know you posted this a long time ago, but in case anyone else has this question, I believe that the actual estimate of the effect size would be the same as OLS, but that the confidence intervals would likely be different from a vanilla OLS regression compared to a hierarchical model.

Re: Importing WRDS data into Stata

$
0
0

why it keeps coming out with error, which says client_encoding: UHC

Re: Export tabulation results to Excel—Update

Re: Export tables to Excel

Re: Calculating power using Monte Carlo simulations, part 1: The basics

$
0
0

In this blog entry, you reference `power simmixed`. Unless I missed it somehow, I didn't see the program typed out. Is `power simmixed` available?

Re: Calculating power using Monte Carlo simulations, part 2: Running your simulation using power

$
0
0

Part 1 made it sound like there would be a part 3 using examples with multilevel modelling and complex models... is this coming shortly???


Re: Group comparisons in structural equation models: Testing measurement invariance

$
0
0

I was trying to find this too, couldn't find RMSEA but used estat ggof to get the chi-square values for both models

Re: Ermistatas and Stata’s new ERMs commands

Re: Calculating power using Monte Carlo simulations, part 1: The basics

$
0
0

Hi Chuck. In your -simtest- program, I expected to see -corr2data- where you used -drawnorm-. But when I use -corr2data- in place of -drawnorm- (with everything else the same), I get Power = 1, not Power = .91. Any idea why that is happening? Here is my -corr2data- command:

corr2data y, n(`n') means(`ma') sds(`sd') clear

Cheers,
Bruce

Re: Bayesian binary item response theory models using bayesmh

$
0
0

Hi, thank you. I am using the 2pl model described above. I would like to generate a variable consisting of the mean of the posterior distribution for each subject but I'm not sure how to do this with the data in long form. I see there are bayespredict commands, but when I use it, I get the following error: "model parameter subj:1bn.appt_id not found". Thank you for any guidance you can provide.

Re: Export tabulation results to Excel—Update

$
0
0

Hi, I would like to put several tables into one word document. The first one works fine but when I try to make the second one I get the following error:

(note: table t1 has been redefined)
expression must be enclosed in ()
invalid syntax

My code is:

putdocx begin
putdocx paragraph
tab2docx (htxfu_death_code_1)
putdocx paragraph
tab2docx (htx_fu_code_1_cv)
putdocx save test2, replace

Is it possible? Can anyone please help me to adjust the code.
Thanks,
Oscar

Re: Gelman–Rubin convergence diagnostic using multiple chains

$
0
0

Hi Nikolay,

thanks for the nice blog post.
I can't follow you on some parts.
In the first run (chain of length 25), you state:

Moreover, all Rc values exceed their corresponding upper confidence limits at the 95% confidence level.


From your output, I would think it is only true for sigma.
Is this a typo or do we have to interpret the results differently.

For the third run, I guess that you have a typo here:

This time, all the Rc values are well below 1.01

.

I think you wanted to say 1.1.

Best,

Anna

Re: Programming an estimation command in Stata: Using a subroutine to parse a complex option

$
0
0

Very Informative. I have only one comment. Even though the program is written to allow for factor notation, it seems that the command "matrix opaccum " does not handle factor notation. Is there anyway around it using only ado language?


Re: Programming an estimation command in Stata: Mata functions

$
0
0

I just encountered a somewhat weird problem with this example. Im following the first myadd Mata program. When trying to execute it under Stata 15.1 it gives the error "variable A undeclared". It has no problem with Stata 14.

Re: Export tabulation results to Excel—Update

$
0
0

Hi, i'm wondering whether the tab2xl command can be extended to include 'if' command.
Basically, my data only has three variables in it: userid, questionnaire, province

However, whenever i'm putting the command:

tab2xl demography if questionnaire=="m1" using m1test, col(1) row(1)

Stata returns the command:
(212 observations deleted)
m1 not found

Does it work with if statements?

Re: How to create animated graphics to illustrate spatial spillover effects

$
0
0

Creative indeed! I got stuck on lines 25 - 34. Please can anyone help?

Re: How to successfully ask a question on Statalist

$
0
0

Hi, this is Raj from India. I am trying to run frontier function for 9 variables for 12 states. While for 7 states, the result cud be obtained, for the remaining 5 states the iteration run continuously without providing co-efficients. What cud be the plausible reasons? Can any one help me to get the result for these five states

Re: Web scraping NFL data into Stata

$
0
0

Hi, I am attempting the web scraping for the nfl2stata. I am currently running STATA 16. Each attempt at using the command the error "invalid support" appears. Does nfl2stata still work on STATA 16?

Viewing all 1125 articles
Browse latest View live