Stata 15 is here

[Bill Gould (StataCorp)]

With this message, we announce Stata 15.

Downloads are available now.

Shipped copies begin shipping today.

And of course, you can obtain your copy at our website.

Stata 15 is remarkable for its sheer size. I'll list some highlights here and make some snappy comments, but I make about 20 pages of comments on the blog entry I am about to post, which will be a record. The most thorough coverage, of course, is at the Stata 15 features page at the stata.com website.

Here are sixteen of the highlights:

1. Extended regression. It fits continuous, binary, ordered responses with (1) endogenous covariates, (2) endogenous (Heckman-style) selection, and (3) endogenous treatment effects. This command does a lot and is easy to use.
    
2. Latent class analysis. Binary outcomes. Ordinal outcomes. Continuous outcomes (latent profile analysis). Even incorporate latent classes in path models.
    
3. Bayesian prefix command. You can now type -bayes:- in front of estimation commands to fit Bayesian regression models for over fifty likelihoods. And multilevel models are among them!
    
4. Dynamic stochastic general equilibrium (DSGE) models. Fit structural macro models based on theory with lots of equations. Graph impulse-response functions afterward.
    
5. Markdown for Stata. You can now combine Markdown text with executable Stata code to produce web containing prose, Stata output, parts of Stata output, and graphs. By parts, we mean you can write a sentence such as "The F statistic is 52.4 and ...", where the 52.4 is obtained from -e(F)-.
    
6. Nonlinear mixed-effects models. Because some problems are just not linear in the parameters.
    
7. Spatial autoregressive models (SAR). Download shapefiles from the web, merge with your geographic-based data, and fit your SAR models with cross-sectional or panel data.
    
8. Interval-censored parametric survival-time models. For when you only know a time when subjects have not yet failed and another when they have already failed.
    
9. Finite mixture models (FMMs). The new -fmm:- command is a prefix command. You mix one or more regression models using any of 17 existing estimation commands.
    
10. Mixed logit models. Discrete choice models with random coefficients, meaning you can relax the IIA assumption.
     
11. Nonparametric regression. Our implementation uses kernel methods. Bootstrap standard errors. Graph slices after fitting. Predict derivatives or levels.
     
12. Power analysis for cluster-randomized designs (CRDs) and for regression models. You can now add your own power and sample-size methods too.
     
13. Word and PDF documents. It's now just as easy to produce Word and PDF documents as it is to produce Excel worksheets.
     
14. Graph color transparency/opacity. Stata's colors used to be fully opaque, which is to say, not-at-all transparent. Now you can change them so that you can see what's underneath.
     
15. ICD-10-CM/PCS support. These are the codes from NCHS and CMS that are mandated for all medical billing in the U.S. Support means a database system that can even manage codes from different versions in one file!
     
16. Federal Reserve Economic Data (FRED) support. 470,000 U.S. and international economic and financial time series are available to registered users courtesy of the St. Louis Federal Reserve Bank. You should register. It's free and easy. If you do, Stata can browse, search, and assemble datasets for you.
     

I'll stop, but the following are most certainly highlights too:

• Bayesian multilevel models
• Threshold regression
• Panel-data tobit with random coefficients
• Multilevel regression for interval-measured outcomes
• Multilevel tobit regression for censored outcomes
• Panel data cointegration tests
• Tests for multiple breaks in time series
• Multiple-group generalized SEM
• Heteroskedastic linear regression
• Poisson models with Heckman-style sample selection
• Panel-data nonlinear models with random coefficients
• Bayesian panel-data models
• Panel-data interval regression with random coefficients
• SVG export
• Bayesian survival models
• Zero-inflated ordered probit
• Add your own power and sample-size methods
• Bayesian sample-selection models
• And even more in statistics
• Stata in Swedish
• Improvements to the Do-file Editor
• Stream random-number generator
• Improvements for Java plugins
• More parallelization in Stata/MP

By the way, Stata 15's dataset format is the same as Stata 14's. You can upgrade and still share with those who haven't.

Visit our blog and our features page to learn more.

Stata 15 is in distribution now.

[Richard Williams]

separate question: someone help me here; what is wrong with my syntax? It is not running for some reason
gsem (L1 -> CC1,) (L1 -> CC2,) (L1 -> CC4,) (L1 -> CC5,) (L1 -> CC6,) (L1 -> CC7, ) (L1 -> rCC3, family(ordinal) link(logit) ) (L2 -> rCF2, ) (L2 -> rCF3, ) (L2 -> rCF4, ) (L2 -> rCF5, ) (L2 -> CF1, ), family(ordinal) link(logit) ) covstruct(_lexogenous, diagonal) nolog (L1 L2 ) nocapslatent

Eve, I would start a new thread with a clear title. Include the error message Stata is giving you. See pt 12 of the FAQ for advice about asking questions effectively. Adding a totally unrelated question at the end of a long thread is almost always a bad idea.

[Eve Sykes]

separate question: someone help me here; what is wrong with my syntax? It is not running for some reason
gsem (L1 -> CC1,) (L1 -> CC2,) (L1 -> CC4,) (L1 -> CC5,) (L1 -> CC6,) (L1 -> CC7, ) (L1 -> rCC3, family(ordinal) link(logit) ) (L2 -> rCF2, ) (L2 -> rCF3, ) (L2 -> rCF4, ) (L2 -> rCF5, ) (L2 -> CF1, ), family(ordinal) link(logit) ) covstruct(_lexogenous, diagonal) nolog (L1 L2 ) nocapslatent

[Nick Cox]

I was going to write similarly to Clyde Schechter (#75). I'll suggest to StataCorp that the sticky status be removed for precisely that reason.

[Clyde Schechter]

I would also add that this thread is starting to get a little diffuse. Some of the more recent posts are really requests for help with specific issues arising from specific commands, rather than being commentary on Stata 15 as a whole, what is liked or disliked about it, how it compares to earlier versions or competing statistical packages etc. Posts that deal with specific problems running specific commands would be better posted as separate threads, in my opinion. If nothing else, it will make it much easier for people searching for those particular problems to find them.

[Nick Cox]

postdoc nl: Please use your full real name here as requested. https://www.statalist.org/forums/help#realnames

[Ayesha Sajjad]

Hi all,
I opened my stata 15 today and the simple mi command gives the following error:
mi impute chained (regress) var1 var2 (logit) var3 (ologit) var4 , add(10)

invalid freeparm argument;
only "on" or "off" is allowed
error occurred during imputation of var1 var2 var3 var4 on m = 1

A little help with this would be appreciated.

[Emilio Matuk]

I have tried to estimate the mean difference between wage of male and female workers. I have followed two approaches
1. Generate anew variable called wage gap (Male's wage- female's wage) and take the average
2. take the average of male and female separately and take the difference
but the result is not the same. so my concern is; which one is the right result and if not what is the possible problem that the two are not equal.

Thank you

I will not suggest to do average in any circumstance. Better to work with the full data set and try to evaluate intercept dummy and slope dummy

[Emilio Matuk]

The limit on the size of the weighting matrices in the Sp commands is the limit of matrices in Mata -- which is 2^48 - 1. Obviously, you will reach memory limits on your computer before you make a square matrix of that size. The limit of 11,000 is max_matsize, which only applies to matrices created in Stata, not those created in Mata.

So the effective limit on the size of weighting matrices is the RAM of your computer.

I'm working now in Stata 15. I was able to create a square matrix with dimension 21,689 after day and a half (see command below)

*** spmatrix create idistance W, normalize(minmax)

Later i was able to run a regression with heterocedasticity corrected (see command below)

*** spregress WAGE FR_1-FR_3 PER WAGE_M, gs2sls heteroskedastic

But when I tried dependent variable lagged option (see command below) , I crashed due to memory limitations.

*** spregress WAGE FR_1-FR_3 PER WAGE_M, gs2sls dvarlag(W) heteroskedastic

What suprises me is why I was able to run SPMATRIX but I'mm not able to run SPREGRESS with DVARLAG option.

[Joseph Coveney]

Debugger features would be good, especially if you do a lot with Mata.

But when I scan through the New in Stata 15 page, I'm glad that StataCorp invested the limited resources that it has as it did. I'll take menl over autocomplete any day of the week.

[Michael Anbar]

I'm sorry to say that on the face of it, this looks like a very disappointing release.

Disappointing indeed. The complete lack of "modern" debugging tools in Stata (I wouldn't consider breakpoints modern, since they've been around since the 1960s, but I digress) is a major drawback. -set trace on- and -pause- are inferior substitutes, to say the least. Even basic features like autocomplete in the do-file editor are still missing from Stata, years after even some of the most basic text editors, not to mention IDEs, have implemented such features.

[Nick Cox]

File/Import/...Fred works for me. As does

db import fred

[Sean Fiedler]

One question about freduse in Stata 15, I saw a new GUI interface for this command heavily advertised. However after upgrading to Stata 15 I see no interface. Typing

help freduse

doesn't describe any interface, I see nothing in the dropdown menus, and

db freduse

doesn't bring anything up. How do I access this?

Yes, there is new functionality. import fred is a entirely new implementation to access FRED and ALFRED series, and it includes a new and slick graphical interface for searching and browsing for series of interest. It has more new features too.

The old freduse let you specify the series that you wished to load but did not provide ability to search, ability to control aggregation level, a graphical user interface, support for wide versus long formats when importing, selection of date range, and so on. It also used a now-deprecated URL-only way of accessing the series. The old command continues to work for now, but FRED wants developers to use their API for accessing series.

In addition to the new import fred's interface, the new command includes lots of options to control date ranges imported, how series are aggregated, access to historical series, control over wide versus long format, and interacts with FRED via the official FRED API.

The old freduse was not official because it was not up to our standards. It was a placeholder until we could do something better.

[Marcos Almeida]

Fissha Asmare Welcome to the Statalist/Stata Forum,

It seems your query is not related to this thread.

Being this so, you may wish to start a new topic.

Please read the FAQ, particularly the topic about the best way to post a question so as to entail a helpful reply. Thanks.

[Fissha Asmare]

I have tried to estimate the mean difference between wage of male and female workers. I have followed two approaches
1. Generate anew variable called wage gap (Male's wage- female's wage) and take the average
2. take the average of male and female separately and take the difference
but the result is not the same. so my concern is; which one is the right result and if not what is the possible problem that the two are not equal.

Thank you