[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Markus Hahn <mhahn@unimelb.edu.au> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: RE: Stata 11 Announcement |

Date |
Fri, 26 Jun 2009 15:10:17 +1000 |

Fantastic news! The new features seem promising. Object orientation in Mata! Looking forward to it. Cheers, Markus -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of William Gould, StataCorp LP Sent: Friday, 26 June 2009 2:54 PM To: statalist@hsphsun2.harvard.edu Subject: st: Stata 11 Announcement Following long tradition, we are informing Statalist first: Stata 11 begins shipping Monday, July 27. Orders are now being accepted at http://www.stata.com Below are some highlights from the release. ---------------- Factor variables ---------------- Probably the highlight of the release is factor variables, if only because everyone is going to be using them. Stata itself now deeply understands factor variables. -xi- is dead. You can type ---------------------------------------------------------------------- . regress y i.sex i.group i.sex#i.region age (1) . regress y i.sex##i.group age (same as 1) . regress y i.sex i.group i.region i.sex#i.group i.sex#i.region i.group#i.region (2) i.sex#i.group#i.region age . regress y i.sex##i.group##i.region age (same as 2) ---------------------------------------------------------------------- Stata itself forms the necessary indicator variables. NO NEW VARIABLES ARE CREATED IN YOUR DATA. In the above, # means interaction, and ## means factorial interaction, so A##B is equivalent to A B A#B. Asterisks would have looked better, but * is Stata's varlist wildcard indicator, and factor variables are now just part of varlists, so * and # had to coexist. Anyway, interactions are much more like Kronecker products than like multiplication. By the way, I typed -i.- everywhere above, but you can type, for example, -sex#group- and Stata will know that you mean -i.sex#i.group-. You can form interactions of factor variables with continuous variables, and continuous variables with continuous variables, by using the -c.- prefix: ---------------------------------------------------------------------- . regress y i.sex##i.group##i.region age c.age#c.age (3) . regress y i.sex##i.group##i.region age i.sex##i.group##i.region#c.age (4) c.age#c.age i.sex##i.group##i.region#c.age#c.age . regress y i.sex##i.group##i.region##c.age (same as 4) i.sex##i.group##i.region##c.age#c.age . regress y i.sex##i.group##i.region##(c.age c.age#c.age) (same as 4) ---------------------------------------------------------------------- In the last example, note the clever use of # and ## together, with ## being used to produce factorial-style interactions and # being used to square age. This new factor-variable notation is understood by all but a handful of estimation commands. I demonstrated with -regress-, but I could have used nearly any other estimation command. ---------------------------------------------------------------------- . logistic outcome i.treatment##i.sex age bp c.age#c.bp ---------------------------------------------------------------------- Factor variables work with -summarize- and -list-, too: ---------------------------------------------------------------------- . list outcome i.treatment##i.sex ---------------------------------------------------------------------- That is useful for understanding exactly what the notation produces. -------- Graphics -------- You can now put bold and italic text, Greek letters, symbols, superscripts, and subscripts on graphs. What more is there to say? ---------- Statistics ---------- There are many new statistics in Stata 11, including o multiple imputation o competing-risks survival-time regression o GMM estimation with user-specified moment functions o new -margins- command, which replaces -mfx- and -adjust-, and does so much more o state-space modeling o multivariate GARCH o dynamic-factor models o unit-root tests for panel data o error structures for linear mixed models o standard errors for BLUPs in linear mixed models There is so much to say about multiple imputation that Stata's new -mi- command gets its own manual. See http://www.stata.com/stata11 for details. ------------------------------ Graphical user interface (GUI) ------------------------------ New GUI features include o Variables Manager Edit names, labels, display formats, storage types, notes, and value labels. Those with many variables can use a filter to see a selected subset of variables. o Data Editor Live view onto your data, filters, data snapshots, and more. o Do-file Editor for Stata for Windows Syntax highlighting, code folding, and no limit to file size. I admit that I do not use GUI features often, but the new Variables Manager does indeed make things easy. Others here tell me that the new Data Editor will be the most popular interface feature because you can now leave it open while you perform your analysis, and changes are reflected instantly in it. You can even perform all your data management from within the Data Editor, and do so in a reproducible manner because it issues Stata commands for all changes. ----------- Programming ----------- Mata now includes full object-oriented programming facilities: classes, inheritance, constructors and destructors, public/private/protected declarations, virtual functions, and more. Just as in Java, code is fully compiled, so there is no speed penalty for using it. ----------- PDF manuals ----------- Stata's manuals now ship in PDF format with every copy of Stata. All the manuals. That's 8,500 pages. The manuals are [GS], [U], [R], [D], [G], [P], [M], [I], [MI], [MV], [ST], [SVY], [TS], and [XT]. Even better, the manuals are fully integrated with the help system, so you can click from a help file and jump to the right manual, the right page! I admit that it's convenient having the manuals on my laptop. Of course, the manuals are available in printed form, too. ----------------- One more thing... ----------------- By the way, if you have a multicore computer, now might be a good time to upgrade to Stata/MP. It's faster, and it's even faster in Stata 11. There is much more, so visit http://www.stata.com/stata11 -- Bill wgould@stata.com ------------------------------------------------------------------ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: Stata 11 Announcement***From:*wgould@stata.com (William Gould, StataCorp LP)

- Prev by Date:
**st: Stata 11 Announcement** - Next by Date:
**Re: st: Stata 11 Announcement** - Previous by thread:
**st: Stata 11 Announcement** - Next by thread:
**Re: st: Stata 11 Announcement** - Index(es):

© Copyright 1996–2017 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |