Stata 10 printed manual errata

Errata are available for the following manuals:

Base Reference Manual, Volume 1
Base Reference Manual, Volume 2
Base Reference Manual, Volume 3
Data Management Reference Manual
Longitudinal/Panel Data Reference Manual
Mata Reference Manual
Multivariate Statistics Reference Manual
Programming Reference Manual
Survival Analysis and Epidemoiological Tables Reference Manual
User's Guide

Base Reference Manual, Volume 1

(1) [R] doedit, p. 352, third paragraph under Remarks
On Windows and Macintosh, you may have more than one Do-file Editor open at once. Each time you submit the doedit command, a new window will be opened. The Unix(GUI) is limited to one open Do-file Editor. You may have more than one Do-file Editor open at once. Each time you submit the doedit command, a new window will be opened.
(1) [R] estat, p. 387, first syntax
estat ic, n(#) estat ic  [ , n(#) ]
(1) [R] estimates, p. 396, second item under Remarks
2. You can store up to 20 estimation results in memory so that they are at your fingertips. 2. You can store up to 300 estimation results in memory so that they are at your fingertips.
(1) [R] heckman, p. 554, vce(vcetype) description
vce(conventional), the default, uses the conventionally derived variance estimator for generalized least-squares regression. vce(conventional), the default, uses the two-step variance estimator derived by Heckman.

Base Reference Manual, Volume 2

(1) [R] ivprobit, p. 16, tse_options table

vce(vcetype)      vcetype may be standard, bootstrap, jackknife
vce(vcetype)      vcetype may be twostep, bootstrap, jackknife
(1,2,3) [R] ivregress, p. 43, table at top of page
(1) [R] ivtobit, p. 58, tse_options table

vce(vcetype)      vcetype may be standard, bootstrap, jackknife
vce(vcetype)      vcetype may be twostep, bootstrap, jackknife
(1,2,3) [R] mfx, p. 270, commands in at() description
. probit foreign mpg weight price . sureg (price disp weight) (mpg disp weight foreign)
(1,2,3) [R] mkspline, p. 289, second equation under Restricted cubic splines
(1,2) [R] more, p. 335, Syntax

set pagesize set pagesize

Base Reference Manual, Volume 3

(1) [R] roc, p. 173, middle of page
The msymbol(O S) option should be removed from the second command line; it is not a valid option with roccomp.
(1) [R] set, p. 266
set reventries is not limited to Windows; it is available for all operating systems.
(1,2,3) [R] tabulate twoway, p. 426, lrchi2 description
lrchi2 displays the likelihood-ratio chi-squared statistic. The request is ignored if any cell of the table contains no observations. lrchi2 may not be specified if aweights or iweights are specified. lrchi2 displays the likelihood-ratio chi-squared statistic. lrchi2 may not be specified if aweights or iweights are specified.
(1) [R] treatreg, p. 511, vce(vcetype) description
vce(conventional), the default, uses the conventionally derived variance estimator for generalized least-squares regression. vce(conventional), the default, uses the conventionally derived variance estimator for the two-step estimator of the treatment-effects model.

Data Management Reference Manual

(1) [D] dates and times, all occurrences of baseyear should be changed to topyear.
(1) [D] dates and times, p. 92–93, last two paragraphs in Working with two-digit years
When you specify baseyear, you are stating that when years in string are two digits, the full year is to be obtained by finding the year closest to baseyear. Thus you could code,

. generate double timestamp =
  clock(timestr, "DMYhm", 2000)

Two-digit year 06 would be interpreted as 2006 because 2006 is closer to 2000 than 1906, or 2106, or 1806, etc. Two-digit 98 would be interpreted as 1998 because 1998 is closer to 2000 than 2098, 1898, etc.

When you specify topyear, you are stating that when years in string are two digits, the full year is to be obtained by finding the largest year not exceeding topyear. Thus you could code,

. generate double timestamp =
  clock(timestr, "DMYhm", 2020)

Two-digit year 06 would be interpreted as 2006 because 2006 does not exceed 2020. Two-digit 98 would be interpreted as 1998 because 2098 does exceed 2020; 1998 does not.

(1,2) [D] functions, p. 212, invnormal(uniform())
Range: 0 to 1 Range: −39 to 6.2302601

Longitudinal/Panel Data Management Reference Manual

(1,2) [XT] xtgee, p. 130, insertion of new sentence before the last line on the page
In what follows, we let ni = n without loss of generality.
(1) [XT] xtmelogit postestimation, p. 249 and 250, description of mu option
The phrase “i.e., the predicted success probability” should be deleted from the description.
(1) [XT] xtmepoisson, p. 264, first sentence on page
... you can obtain equivalent results by using xtmepoisson with options re and normal. ... you can obtain equivalent results by using xtpoisson with options re and normal.
(1,2) [XT] xtmixed, p. 303, parenthetical notation, first line, third paragraph

Mata Reference Manual

(1) [M-2] exp, p. 93, Operators table
The negation operator should be listed above the e.w. power operator in the table to indicate that the negation operator has a lower precedence than that of the e.w. power and power operators.
(1) [M-5] invsym(), p. 218, first sentence in Description
invsym(A) returns a generalized inverse of real, symmetric matrix A. invsym(A) returns a generalized inverse of real, symmetric, positive-definite matrix A.
(1) [M-5] invsym(), p. 218, first sentence in Definition of generalized inverse
When the matrix is of full rank, the generalized inverse equals the inverse, i.e., assuming A is n x n, ... When the matrix is of full rank and positive definite, the generalized inverse equals the inverse, i.e., assuming A is n x n, ...
(1) [M-5] invsym(), p. 220, addition to Diagnostics
invsym() and _invsym() return a matrix of zeros if A is not positive definite.
(1) [M-5] optimize(), p. 293, third sentence in optimize_init_nmsimplexdeltas()
The values in delta must be at least 10 times larger than ptol, which is set by optimize_init_ptol(). The values in delta must be at least 10 times larger than ptol, which is set by optimize_init_conv_ptol().

Multivariate Statistics Reference Manual

(1,2) [MV] mdsmat, p. 487
(3) sammon specifies the Sammon mapping criterion (Sammon 1969; Niemann and Weiss 1979): the sum of the scaled, squared differences between the disparities and the dissimilarities, normalized by the sum of the disparities. (3) sammon specifies the Sammon mapping criterion (Sammon 1969; Niemann and Weiss 1979): the sum of the scaled, squared differences between the distances and the disparities, normalized by the sum of the disparities.
(1) [MV] pca postestimation, p. 531–534, rotate and estat rotatecompare output
The order of the column labels over the components should be Comp1, Comp2, Comp3, and Comp4.
(1,2) [MV] rotatemat, p. 583, second line, first paragraph in Description
so that the result maximizes some criterion function c() over all matrices T in a so that the result minimizes some criterion function c() over all matrices T in a

Programming Reference Manual

(1) [P] creturn, p. 60
c(reventries) is not limited to Windows and Mac; it is available for all operating systems.
(1) [P] matrix dissimilarity, p. 266, last sentence on page
Let's find the Canberra distance between the measurements found among the first 25 observations of the labtech dataset. Let's find the Canberra distance between the measurements performed by lab technician Bill found among the first 25 observations of the labtech dataset.
(1) [P] matrix dissimilarity, p. 267, bottom of page
. clustermat averagelinkage Avars, clear
obs was 0, now 60
cluster name: _cl_1

. cluster generate g5 = groups(5)
. clustermat averagelinkage Avars, clear
obs was 0, now 60
cluster name: _clus_1

. cluster generate g5 = groups(5)

Survival Analysis and Epidemiological Tables Reference Manual

(1) [ST] stci, p. 121, second paragraph
The expression “is less than or equal to p” should be “is less than or equal to 1-p/100”. This expression appears twice in this paragraph.
(1) [ST] stfill, p. 196, syntax diagram
stfill varlist [if] [in] , {baseline | forward} [ , options ] stfill varlist [if] [in] , {baseline | forward} [ options ]
(1) [ST] stpower logrank, p. 283, first equation

User's Guide

(1,2,3) [U] 18.3.6 Extended macro functions, p. 195, second command in first set of examples in section
local filenames : "." files "*.dta" local filenames : dir "." files "*.dta"