The name is absent

Stata Technical Bulletin

an1.1 STB categories and insert codes

Inserts in the STB are presently categorized as follows:

In addition, we have granted one other prefix, crc, to the manufacturers of Stata for their exclusive use.

an44.1 StataQuestdiskenclosed (really)

Patricia Branton, Stata Corporation, FAX 409-696-4601

Although an44 stated that a StataQuest disk would be included with STB-19 for those who subscribe with magnetic media,
we forgot. The disk is included with this issue.

To enter StataQuest, put the diskette into the drive, select that drive, and type go.

There have been a few enhancements to the original StataQuest software. After entering StataQuest, if you select “Read
StataQuest release 2 notes”, you will see a list of the new features.

Reference

Loll, S. 1994. an44: StataQuest: Stata for teaching. Stata Technical Bulletin 19: 3-4.

an46 Stata and Stage now available for IBM PowerPC

Tim McGuire, Stata Corporation, FAX 409-696-4601

Stata 3.1 and the Stata Graphics Editor (Stage) are now available for the IBM PowerPC running AIX (IBM’s version of Unix).
The PowerPC chip is the result of a joint venture of Motorola, IBM, and Apple. IBM’s version is available in both desktop and
notebook computers, and supports Unix (in the form of AIX and the X Window standard (in the form of Motif.)

Stata 3.1 on the PowerPC is like Stata 3.1 on all other platforms; thus version 3.1 data sets, graphs, and ado-files from other
computers can be used without translation. Pricing is the same as for all other Stata/Unix systems.

crc36 Clarification on analytic weights with linear regression

A popular request on the help line is to describe the effect of specifying [aweeχp∙t=exp] with regress or fit in terms
of transformation of the dependent and independent variables. The mechanical answer is that typing

. regress y x₁ X2 [aweight=n]

is equivalent to estimating the model:

Vjy∕nj = βθy∕nj + βlXljy∕nj + β2X2jy∕nj + Uj_y∕nj

This regression will reproduce the coefficients and covariance matrix produced by the aweighted regression. The mean square
errors (estimate of the variance of the residuals) will, however, be different. The transformed regression reports s%, an estimate

<<   1   2   3   4   5   >>

More intriguing information