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

{help svytab} with the {cmd:subpop()} and {cmd:obs} options now displays
subpopulation counts in each cell rather than the full population counts
previously displayed.

{hline 5} {hi:update 12oct1999} {hline}

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

{p 0 4}
Stata has had a long history (since Stata 1.0) of confusing expressions such
as e+3 with numbers such as 1e+3, leading to syntax errors and users avoiding
the name e for variables or scalars.  That has been fixed.

{p 0 4}
{help anova} with {help aweight}s now works.  The precision improvements made
to {cmd:anova} on 2aug1999 resulted in aweighted models being reported with
all zero coefficients and missing test statistics.  That has been fixed.

{p 0 4}
{help arima}, or rather, "{cmd:predict, dynamic()}" used after
"{cmd:arima, ar(1)}" now produces dynamic predictions.  Previously
"{cmd:predict, dynamic()}" after "{cmd:arima, ar(1)}" produced structural
predictions.  The problem existed only with pure AR(1) models --
"{cmd:predict, dynamic()}" used after "{cmd:arima, ar(1) ma(1)}", for
instance, always produced dynamic predictions.  Now all produce dynamic
predictions.

{p 0 4}
{help cnreg} now saves {hi:e(censored)} containing the censoring variable name
along with the other saved results.

{p 0 4}
{help estimates} {cmd:matrix} and {help return} {cmd:matrix} will no longer
create multiple matrices with the same name.  Instead, the previous matrix is
erased and the new matrix replaces it.  This problem only caused a waste of
memory.

{p 0 4}
{help infile} and {help infix} no longer issue an error message when the
{cmd:using()} option is specified and the (irrelevant) data file mentioned in
the dictionary (if any) does not exist.

{p 0 4}
{help insheet} will no longer allow creation of str81 variables.

{p 0 4}
{help ivreg} now produces more digits of precision when used with
ill-conditioned data.

{p 0 4}
{help macro} {cmd:drop} now allows multiple wildcard references such as
"{cmd:macro drop A* B*}".

{p 0 4}
{help table} now honors specified formats wider than 9 characters.

{p 0 4}
{help tobit} now saves {cmd:e(llopt)} and {cmd:e(ulopt)} -- the lower and
upper bounds -- along with the other saved results.


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

{p 0 4}
Stata for Unix is now 8-bit cleaner.  Stata now defaults to specifying -e
("stata -e") when loading the pipeline driver ({help pd}) automatically.  This
allows 8-bit streams to be sent to the terminal.

{hline 5} {hi:update 28sep1999} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-51.

{p 0 4}
{help joinby} has been made faster and some new options were added.  There
were no problems with the previous {cmd:joinby}.

{p 0 4}
{help qreg}, {help iqreg}, {help sqreg}, and {help bsqreg} sometimes reported
that a collinear variable was being dropped whereas in actuality another of
the collinear variables was dropped.  The reported variable dropped now always
agrees with the actual variable dropped.  In rare instances, this could lead
to a "conformability error" when using {cmd:bsqreg}; this no longer occurs.

{p 0 4}
{help pwcorr} stopped with an error message if a pair of variables had no
observations in common; now {cmd:pwcorr} reports missing value for the
correlation.

{p 0 4}
{help _rmcoll} is now documented on-line.  This is an advanced programming
command for use in writing estimation commands that are to run efficiently.

{p 0 4}
{help xttab} produced an inappropriate error message when run on zero
observations.

{hline 5} {hi:update 10sep1999} {hline}

{p 0 4}
{help cloglog} with {cmd:fweight}s reported incorrect number of zeros and
ones. The estimation results were correct. This has been fixed.

{p 0 4}
{help dotplot} now accepts a string variable in the {cmd:by()} option.

{p 0 4}
{help quadchk} now works correctly after {help xttobit}.  {cmd:xttobit} now
saves returned results {hi:e(ulopt)} and {hi:e(llopt)} for use by
{cmd:quadchk} but which other programs may now use.  {hi:e(ulopt)} and
{hi:e(llopt)} are the {cmd:ul()} and {cmd:ll()} options specified by the user.

{p 0 4}
{help recast} has a new {cmd:force} option that forces the change to be made
even if that change would cause a loss of precision, introduction of missing
values, etc.

{p 0 4}
{help reshape} now allows variable-name abbreviation for varlist and {cmd:j()}
option when changing data from long to wide form.

{p 0 4}
{help reg3} and {help sureg} with weights specified now save the weighting
expression in {cmd:e(wexp)} and the weight type in {cmd:e(wtype)}.

{p 0 4}
{help zinb} option {cmd:nbreg} has been replaced by option {cmd:vuong}.
{cmd:vuong} requests that a Vuong test of ZINB vs. negative binomial be done.

{p 0 4}
{help zip} option {cmd:poisson} has been replaced by option {cmd:vuong}.
{cmd:vuong} requests that a Vuong test of ZIP vs. Poisson be done.

{hline 5} {hi:update 30aug1999} {hline}

{p 0 4}
{help xi}, when producing interactions of variables taking on hundreds of
different values, could fail with the error message "syserr: length |5| not
right"; r(198).  This has been fixed.

{hline 5} {hi:update 27aug1999} {hline}

{p 0 4}
{help cchart} and {help pchart} now correctly plot and report the number of
units out of control if the lower control limit is zero or lower.

{p 0 4}
{help predict} after {help streg}, {cmd:dist(exponential)} and {cmd:streg},
{cmd:dist(weibull)} now calculates predicted time without including Euler's
constant.

{p 0 4}
{help predict} after {help streg}, {cmd:dist(gamma)} now produces correct
predicted time values when kappa is negative.  Also the way it calculates
hazard values has been made more numerically stable.

{p 0 4}
{help recode}, when used on a variable of storage type {help long} or
{help double}, and the variable contained lots of significant digits, could
incorrectly include in recode ranges values that should have been excluded.
This has been fixed.

{p 0 4}
{help sts} {cmd:generate} {it:newvar} {cmd:= s} now produces survival
probabilities equal to 1 rather than missing when there are no failures in the
data.

{p 0 4}
{help tsset} now returns values for the time unit (i.e., periodicity) and the
time-series format.  {hi:r(unit)} contains {hi:daily}, {hi:weekly},
{hi:quarterly}, etc.  {hi:r(unit1)} contains {hi:d}, {hi:w}, {hi:q}, etc.
{hi:r(tsfmt)} contains the time-series format.

{hline 5} {hi:update 17aug1999} {hline}

{p 0 4}
{help codebook} now handles date variables more elegantly.  In addition, the
new option {cmd:notes} displays {help notes} associated with variables and the
new option {cmd:header} reports the dataset's name, etc., above the report on
the individual variables.  New option {cmd:all} is equivalent to specifying
both {cmd:header} and {cmd:notes}.

{p 0 4}
{help xi} now works properly with commands that use bound (parenthesized)
equation or variable lists (such as {help ivreg}) and with commands that take
equations or variable lists in options (such as {help heckman}).

{hline 5} {hi:update 16aug1999} {hline}

{p 0 4}
{help arima} with the {cmd:arima()} option specified as
{cmd:arima(}{it:k}{cmd:,0,0)} now estimates ARIMA
models with {it:k} AR terms and no MA terms; previously
{cmd:arima(}{it:k}{cmd:,0,0)} was incorrectly taken to mean {it:k} AR and
{it:k} MA terms.

{p 0 4}
{help egen}'s {cmd:robs()} function has a new {cmd:strok} option.  {cmd:strok}
allows string variables to be specified and they are counted as containing
missing when the string variables contain "".

{p 0 4}
{help streg}{cmd:, dist(exponential)} and {help ereg}, when the {cmd:robust}
option is specified, now label the chi-squared model test "Wald chi2".  They
previously incorrectly labeled the test "LR chi2".

{p 0 4}
{help svytab} can now tabulate variables whose variable labels contain quotes.

{hline 5} {hi:update 05aug1999} {hline}

{p 0 4}
{help lrecomp} is a new command for making tables of number of correctly
estimated digits (LREs) when comparing calculated results to
known-to-be-correct results.

{hline 5} {hi:update 02aug1999} {hline}

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

{p 4 4}
{help anova} now provides more digits of precision when used with
ill-conditioned data.

{p 4 4}
{help mlogit}, {help ologit}, and {help oprobit} now produce correct standard
errors when {cmd:pweight}s are specified with option {cmd:cluster()}.
Previously, absurdly large standard errors were reported.

{p 4 4}
{help net} now works with paths including "{cmd:..}" for all HTTP servers,
including Macintosh servers.  Previously, {cmd:net} relied on the server to
handle relative paths.

{p 4 4}
{help regress} now provides more digits of precision in R-squared near 1
regressions.

{p 4 4}
Typing "{cmd:save, replace}" now works when the remembered filename exceeds 64
characters.

{p 4 4}
The {cmd:subinstr} extended macro function with the option {cmd:word} now
correctly handles words at the beginning of a string when the first character
is doubled.

{p 4 4}
{help table} now handles spaces at the beginning and end of string variables
more elegantly.

{p 4 4}
{help tab2} now allows option {cmd:exact} to be abbreviated {cmd:e} as per the
documentation.


{p 0 4}
{hi:Stata for Windows executable}(*).

{p 4 4}
The do-file editor now includes {hi:.dct} files in the list of editable files.

{p 4 4}
The log window now remembers the printer font as well as the screen font
between sessions.

{p 4 4}
Copying and pasting into the data editor no longer creates a row of missing
values below the pasted data.

{p 4 4}
Stata now reports attempts to open log files in read-only directories.


{p 0 4}
{hi:Stata for Macintosh executable}(*).

{p 4 4}
Copying and pasting into the data editor no longer creates a row of missing
values below the pasted data.

{hline 5} {hi:update 29jul1999} {hline}

{p 0 4}
On-line help and search index brought up to date for STB-50.

{p 0 4}
{help sts} {cmd:graph} now includes option {cmd:censored()} which allows
placing tick marks on the graph to indicate censorings.

{hline 5} {hi:update 23jul1999} {hline}

{p 0 4}
{help dprobit} added two matrices to saved results -- {hi:e(dfdx)} records the
vector marginal effects and {hi:e(se_dfdx)} records their standard errors.

{p 0 4}
{help cc} now suppresses the test for homogeneity when any of the estimated
odds ratios are zero or missing.

{p 0 4}
{help reshape}.  A message {cmd:reshape} sometimes displays has been reworded
to correct a typographical error.

{hline 5} {hi:update 13jul1999} {hline}

{p 0 4}
{help aorder} now handles multiple number fields within variable names.

{p 0 4}
{help centile} now correctly handles the case of no observations (it
previously went into an endless loop) and it correctly handles {cmd:if}
{it:exp} and {cmd:in} {it:range} when there are multiple variables.

{p 0 4}
{help cf} could become confused when different variables appeared in both
datasets and the name of one of the variables could be interpreted as an
abbreviation of the other.

{p 0 4}
{help dotplot} now recognizes labels for the y variable.

{p 0 4}
{help egen}'s {cmd:rmean()} and {cmd:rsum()} functions now allow one or more
variables rather than requiring at least two.

{p 0 4}
{help nl} has a new {cmd:delta(}{it:#}{cmd:)} option and a default value for
same that should improve the accuracy of coefficients and standard-error
estimates.

{p 0 4}
{help predict} after {help streg}{cmd:, dist(gamma)} produced incorrect hazard
values.  This also caused {help stcurv} to make incorrect plots.

{p 0 4}
{help heckman} with the {cmd:twostep} option sometimes reported the message
"matrix not symmetric".

{p 0 4}
{help ksmirnov}, after reporting an uncorrected P-value of zero, reported the
corrected P-value as zero rather than missing.