Stata is a registered trademark of StataCorp LP , College Station, TX, USA, and the Stata logo is used with permission of StataCorp.
StataCorp社 国内正規販売代理店 インフォーマティック（株） [Back] [Home] [Bottom] お問い合わせ・注文
The big feature of Stata 10 that will be of interest to everyone is
o Stata's new WYSIWYG Graph Editor, which makes preparing Stata
graphs
for inclusion in documents a snap.
That feature, however, should not eclipse other important new
features.
Two more that will also be of interest to nearly all users are
o Date/time variables. Stata already had date variables; now
it
has time and time-and-date variables, too. Time is recorded with
up to millisecond resolution, which will be important to some
users.
In addition, Stata's time and time-and-date variables will work
with or without leap-second adjustment. You may never have heard
about leap seconds, but there are clocks that are adjusted for
them, and clocks that are not, and in computer-generated datasets,
time stamps from some system are adjusted and others are not.
The important thing is that Stata can work with the data, either
way.
o Estimation results may be saved on disk. People who analyze
data produce estimation results. Previously, those results had
to be stored on paper, in logs, or in notes. In Stata 10,
they can be stored on disk and reused anytime.
After that, Stata 10 has new statistical features, some of
which will interest
some, others of which will interest others. We have made some
major additions
to Stata:
o Exact logistic and Poisson regression. This will be of major
importance to biostatisticians and those in related fields.
o Nested, hierarchical, and mixed logistic and Poisson regression.
This is basically the equivalent of Stata 9's -xtmixed-, but
for binary and count responses. Researchers in many (most)
fields will be interested in this.
o More estimators for dynamic panel-data models, including
the Arellano-Bover/Blundell-Bond system estimator. Economists
will take note.
o LIML and GMM regression in addition to 2SLS. Economists again.
o Nonlinear, seemingly unrelated regression. Economists.
o Even more survey estimators, most importantly including
survey Cox proportional hazards regression. As for the
rest, Stata 10 includes 27 more survey estimators, making
it the broadest package available for analyzing survey data.
(Stata 9 had 21 estimators. We have more than doubled what
is available.)
o Discriminant analysis, including linear, quadratic, and
kth-nearest-neighbor. This is for researchers using
multivariate methods, such as sociologists and psychologists.
o Multiple Correspondence Analysis (MCA) and Joint Correspondence
Analysis (JCA). More for researchers using multivariate methods.
o Sample-size and power calculations for survival studies.
This is of importance to those designing experiments such as
drug trials.
There's lots more --
[Top] Copyright 2004, 2005 StataCorp All Rights Reserved.
[Home] [Top] [Back] お問い合わせ・注文