Help: SAS - 未名空间MITBBS历史存档

国际科技财经博客移民网络热点娱乐民生时事公众号

Redian新闻

>未名空间

>Database - 数据库

Help: SAS

Help: SAS# Database - 数据库

g*e2002-07-06 07:07

1 楼

Somebody ask me something about SAS which I know nothing about. Anybody can
help me? Here is the quote of his question:
when I am doing my data analysis, I use SAS. I'm simply running General
Linear
Models and Logistic regressions. A procedural-based package such as SAS is
quite up to the task. But the problem is that I've been running up against
some limitations of SAS (e.g., the ability to write estimated parameters to
a separate database). I'm wondering if I should move to a more general

f*y2002-07-06 07:07

2 楼

SAS definetely can write the results of GLM to a separate database.
Check help for LIBNAME.

【在 g*****e 的大作中提到】

: Somebody ask me something about SAS which I know nothing about. Anybody can
: help me? Here is the quote of his question:
: when I am doing my data analysis, I use SAS. I'm simply running General
: Linear
: Models and Logistic regressions. A procedural-based package such as SAS is
: quite up to the task. But the problem is that I've been running up against
: some limitations of SAS (e.g., the ability to write estimated parameters to
: a separate database). I'm wondering if I should move to a more general

b*b2002-07-06 07:07

3 楼

Sorry that I didn't see this question earlier. It's very straight forward in
SAS V8. Use "ods ouput" plus a table name. I am pretty sure there is
out=dataset option that you can also use to output parameters which is
available in SAS V6.

can
is
against
to
(and

【在 f**y 的大作中提到】

: SAS definetely can write the results of GLM to a separate database.
: Check help for LIBNAME.

n*n2002-07-06 07:07

4 楼

Bibbub had that good suggestion already. BTW, you can use S-plus, which can
save your model and apply the model to the new data. SAS is a industrial
product, while S-plus is statistican-oriented. A lot of new and advanced
statistical methods, like AVAS,ACE, PPR, are also available in S-plus (Higher
version of SAS, like SAS 9 also added some indirect functions to implement
them). But S-pLus is not good at memory-consuming and large-volumn dataset.

in
the

【在 b****b 的大作中提到】

: Sorry that I didn't see this question earlier. It's very straight forward in
: SAS V8. Use "ods ouput" plus a table name. I am pretty sure there is
: out=dataset option that you can also use to output parameters which is
: available in SAS V6.
:
: can
: is
: against
: to
: (and