whatsnew6.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* 08apr2005}{...}
{cmd:help whatsnew6}
{hline}

{title:Additions made to Stata during version 6}

{pstd}
This file records the additions and fixes made to Stata during the life
of Stata version 6:

    {c TLC}{hline 67}{c TRC}
    {c |} help file       contents                   dates                  {c |}
    {c LT}{hline 67}{c RT}
    {c |} {help whatsnew}        Stata 9.0                  22apr2005 to present   {c |}
    {c |} {help whatsnew8to9}    Stata 9.0 new release      22apr2005              {c |}
    {c |} {help whatsnew8_2}     Stata 8.2                  28oct2003 to 24feb2005 {c |}
    {c |} {help whatsnew8_1}     Stata 8.1                  01jul2003 to 30sep2003 {c |}
    {c |} {help whatsnew8_0}     Stata 8.0                  14jan2003 to 25jun2003 {c |}
    {c |} {help whatsnew7to8}    Stata 8.0 new release      02jan2003              {c |}
    {c |} {help whatsnew7}       Stata 7.0                  08jan2001 to 05dec2002 {c |}
    {c |} {help whatsnew6to7}    Stata 7.0 new release      15dec2000              {c |}
    {c |} {bf:this file}       Stata 6.0                  13jan1999 to 20nov2000 {c |}
    {c BLC}{hline 67}{c BRC}

{pstd}
Most recent changes are listed first.
Note:  Starred (*) items mean the update was made to the executable.


{hline 5} {hi:more recent updates} {hline}

{pstd}
See {help whatsnew6to7}.


{hline 5} {hi:update 20nov2000} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-58


{hline 5} {hi:update 03nov2000} {hline}

{p 0 4}
{help biprobit} had difficulty parsing the second equation when it was longer
than 80 characters; in that case, if the first and second equations were
identical for the first 80 characters, {cmd:biprobit} would use the first
equation as the second equation, and so estimate a model which was not the one
requested.  This has been fixed.

{p 0 4}
{help glm} with {cmd:family(binomial)} would report an error if the dependent
variable did not vary even when the binomial denominator did.  This has been
fixed.

{p 0 4}
{help xtpcse} with the options {cmd:correlation(ar1)} or
{cmd:correlation(psar1)} was reporting an uncentered R-squared -- an R-squared
with a base of 0 rather than the mean of the dependent variable -- and
associated model sum of squares {hi:e(mss)} and model degrees of freedom
{hi:e(df_m)}.  It now computes a centered R-squared unless option
{cmd:noconstant} is specified.

{hline 5} {hi:update 25oct2000} {hline}

{p 0 4}
{help stsplit}, as updated 19sep2000, when used with datasets containing more
than 32,766 observations, would fail to split the data correctly. This has
been fixed.

{hline 5} {hi:update 12oct2000} {hline}

{p 0 4}
{help stcurv}, with multiple failure data and used after {cmd:streg,}
{cmd:dist(lognormal)}, produced a graph with a jagged line; this has been
fixed.  In addition, {cmd:stcurv} used after {cmd:streg,}
{cmd:dist(exponential)} had a spelling error on the default labeling of the
axis.

{p 0 4}
{help vif} on rare occasions would fail to compute variance inflation factors
for all the rhs variables in the model.

{hline 5} {hi:update 19sep2000} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-57

{p 0 4}
{help bstat} has a new option {cmd:title()} allowing the title on the output
to be changed.

{p 0 4}
{help stcox} did not save in {hi:e()} the names of the variables created when
the {cmd:basehazard()}, {cmd:basechazard()}, or {cmd:basesurv()} options were
specified and fully spelled out rather than entered as abbreviations, such as
{cmd:baseh()}, {cmd:basec()}, and {cmd:bases()}.  This caused no problems
whatsoever, but could cause problems if you wanted to use the saved results.

{p 0 4}
{help stcurv}'s new {cmd:outfile(}{it:filename}{cmd:)} option will save the
data generated to produce the graphed curves in a Stata .dta dataset for later
use.

{p 0 4}
{help stsplit} has been improved.  It runs faster, it has additional options,
and it has a new syntax that facilitates splitting at failure times.  See help
{help stsplit}.  In addition, the new help file stsplit2 is very much
like a FAQ in that it explains the usefulness of splitting at failure times
and the relationship between {help stcox}'s {cmd:exactp} option and
conditional logistic regression estimates produced by {help clogit}; see help
stsplit2.  There were no bugs in the previous {cmd:stsplit}.

{hline 5} {hi:update 11sep2000} {hline}

{p 0 4}
{help alpha} with option {cmd:generate()} would fail with an "invalid syntax"
error message if the option was completely spelled out; this is fixed.

{p 0 4}
{help avplot} after {help regress} with the {cmd:cluster()} option would title
the resulting plot using the non-robust standard error.

{p 0 4}
{help xtgee} on rare occasions would fail with error message r(505) "matrix
not symmetric". This has been fixed.

{hline 5} {hi:update 18aug2000} {hline}

{p 0 4}
{help tabstat} has a new {cmd:statistics(sdmean)} option to produce standard
deviation of the mean, the {cmd:statistics()} option is now case insensitive,
and the default output format has been changed if only one variable is
specified.

{hline 5} {hi:update 15aug2000} {hline}

{p 0 4}
{hi:Stata executable}(*), all platforms.

{p 0 4}
{help rotate} with the {cmd:varimax} option, used after {help factor} with two
factors retained, produced incorrect answers; results are now correct.

{hline 5} {hi:update 14aug2000} {hline}

{p 0 4}
{help dprobit} would give an error message if any of the independent variables
contained the string "_cons" in the variable name.

{p 0 4}
{help xtpcse} with the option {cmd:correlation(ar1)} or
{cmd:correlation(psar1)} now constrains estimates of panel-level
autocorrelation to be in the range [-1,1].  This bounding imposes the
theoretical limits on the correlations and allows the Prais-Winsten
computation to always be performed.  The change only affects estimation
results for unusual datasets where any estimated panel-level autocorrelation
fell outside the range [-1,1].  Even in these cases, the new results are
asymptotically equivalent to the prior results.

{hline 5} {hi:update 02aug2000} {hline}

{p 0 4}
{help avplot} after {help regress} with the {cmd:robust} option would title
the resulting plot using the non-robust standard error.

{p 0 4}
{help dfuller} reported an incorrect 1% critical value when the number of
observations was between 101 and 500 and options {cmd:trend} and
{cmd:noconstant} were not specified.

{p 0 4}
{help pperron} reported incorrect Z(t) and Z(rho) statistics.  In addition, as
with {cmd:dfuller}, {cmd:pperron} reported incorrect 1% critical values when
the number of observations was between 101 and 500 and options {cmd:trend} and
{cmd:noconstant} were not specified.

{hline 5} {hi:update 17jul2000} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-56

{hline 5} {hi:update 07jul2000} {hline}

{p 0 4}
{help xtpcse} when specified with the {cmd:pairwise} option would exit with a
"matrix not positive definite" message in the unusual case when the estimated
covariance matrix of the disturbances was not positive definite.  The error
message has been improved to state that the pairwise option may not be used.
As noted in help {help xtpcse}, this can only occur when the {cmd:pairwise}
option is specified.

{p 0 4}
{help strate} with option {cmd:smr} and option {cmd:output()} would fail with
an error message.  It now works.

{p 0 4}
{help stsum} with option {cmd:by()}, and when two variables were specified in
the {cmd:by()}, would sometimes display the stub of the table with quote
characters in odd positions.  This is fixed.

{hline 5} {hi:update 03jul2000} {hline}

{p 0 4}
{help stset}, due to a recent update, when
{cmd:exit(}{it:eventvar}{cmd:==}{it:numlist} {cmd:time} {it:varname}{cmd:)}
was specified, could ignore the events in favor of the time, treating the
option as if {cmd:exit(time} {it:varname}{cmd:)} had been specified.  The same
could happen with the {cmd:enter()} and {cmd:origin()} options.  The problem
could only occur when both an event list and a time were specified; there was
no problem with statements such as
{cmd:exit(}{it:eventvar}{cmd:==}{it:numlist}{cmd:)} or
{cmd:exit(time} {it:varname}{cmd:)}.

{hline 5} {hi:update 29jun2000} {hline}

{p 0 4}
{help ml} has improved convergence properties for pathological likelihoods
where one or more parameters are being driven to positive or negative
infinity.

{p 0 4}
{help reshape}, in a certain case, gave an unhelpful error message.  The error
message has been improved.

{p 0 4}
{help sts} {cmd:generate}, in rare circumstances, would give an error message
rather than producing the requested result.  That is fixed.

{p 0 4}
{help tabstat} is a new command to display a table of summary statistics; see
help {help tabstat}.

{p 0 4}
{help xi} would give an error message if one or more of the variables in the
model contained a constant; {cmd:xi} should have not complained and simply
allowed the model to be estimated.  This arose as a side effect of the
12jun2000 update and is now fixed.

{hline 5} {hi:update 26jun2000} {hline}

{p 0 4}
{help wntestb} had an unnecessary global macro that was never explicitly used
but could on occasion be outputted on the graph's title. This has been fixed.

{p 0 4}
{help xthaus} when used with no covariates which vary within panel would
produce a syntax error. It now gives a more informative error message.

{p 0 4}
{help xtpcse} specified with options {cmd:correlation(ar1)} and
{cmd:pairwise}, and when there were no observations on which to compute the
autocorrelation parameter, would exit with the error message "matrix has
missing values".  It now exits with the appropriate error message
"insufficient observations".

{hline 5} {hi:update 12jun2000} {hline}

{p 0 4}
{help collapse} would not allow a mix of its two syntaxes, one of which
specified the name of the new variable and the other of which did not, such as
"{cmd:collapse newvar1=oldvar1 oldvar2 newvar3=oldvar3}".
"{cmd:collapse newvar1=oldvar1 newvar3=oldvar3}" was allowed as was
"{cmd:collapse oldvar2}", but you could not mix the two together into one
statement.  Now you can.

{p 0 4}
{help xi} would give a syntax error if what followed it contained a reference
to a Stata function.  This was fixed on 31may2000, but not completely.

{hline 5} {hi:update 31may2000} {hline}

{p 0 4}
{help dstdize} now saves numbers of observations, unadjusted, and adjusted
rates for use by other programs; see help {help dstdize} for details.

{p 0 4}
{help xi} would give a syntax error if what followed it contained a reference
to a Stata function.  This has been fixed.

{hline 5} {hi:update 25may2000} {hline}

{p 0 4}
{hi:Stata executable}(*), all platforms.

{p 0 4}
{help xtclog} produced estimates of the parameters and standard errors that
were only accurate to a few digits or, in a few cases, failed to converge.
This was traced to an error in the calculation of the matrix of 2nd
derivatives and is fixed.

{hline 5} {hi:update 24may2000} {hline}

{p 0 4}
{help ci} with the options {cmd:poisson} and {cmd:by()} along with an {cmd:if}
restriction would fail to produce results when one of the by groups had no
observations meeting the if condition.

{p 0 4}
{help hausman} output makes it clearer that the more efficient model in the
test must be fully efficient.

{hline 5} {hi:update 08may2000} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-55

{hline 5} {hi:update 19apr2000} {hline}

{p 0 4}
{help codebook} would produce an error when sent certain variable names such
as {hi:_d}.  This has been fixed.

{p 0 4}
{help fracpred} with the {cmd:dresid} option and {help fracplot} gave
uninformative error messages after "{cmd:fracpoly clogit} ..." or
"{cmd:fracpoly probit} ..."  They now produce more informative errors.  (The
manual does not list {cmd:fracpoly} as working with {help clogit} and
{help probit}, but it does.  Neither {cmd:clogit} nor {cmd:probit}, however,
can produce deviance residuals and so {cmd:fracplot} and
{cmd:fracpred, dresid} are not allowed after {cmd:fracpoly} with either of
these commands.)

{p 0 4}
{help gladder} now works with variables with nonpositive values.

{p 0 4}
{help nl} now includes an {cmd:if} exp on an "{cmd:nl ?}" call.  See "Advanced programming of
    nlfcns" in help {help nl}.  On a query call, the syntax is now

{p 8 16}{cmd:nlfcn} {cmd:?} [{it:varlist}] {cmd:if} {it:exp} [{cmd:,} {it:options}]

{p 4 4}This allows the nlfcn to perform initialization computations restricted
to the relevant subsample within the portion of the code that sets the initial
parameters into global macros.  In addition, {cmd:nl} will no longer remove
existing variables with the same name (or similar name based on abbreviation
rules) as the parameter names.  The {cmd:leave} option is still supported, but
a check is first made that no existing variables by those names exist before
creating the variables.

{p 0 4}
{help predict} after {help stcox} and {cmd:cox} reported hazard ratios of 1
rather than exp(x*b) whenever x*b>18.  This has been fixed.