Date:         Mon, 31 Dec 2007 09:25:24 -0600
Reply-To:     "data _null_," <datanull@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "data _null_," <datanull@GMAIL.COM>
Subject:      Re: Which statistics should have STD decimal places?
Comments: To: RolandRB <rolandberry@hotmail.com>
In-Reply-To:  <c7f9fd35-e56d-4910-b2c8-12f98b0a1bac@l6g2000prm.googlegroups.com>
Content-Type: text/plain; charset=ISO-8859-1

I should think that the user would be able to supply all that
information via parameters.  For example STD: might be specified as

STD: +2   to specify two additional decimal places.

Then the formats associates with the analysis variable provides the
desired "precision".

FORMAT weight 5.1 height 3.;

p-values of course are completely different as are their associated
statistics.  Their display format should be control directly throught
the FORMAT statement.
On Dec 31, 2007 3:56 AM, RolandRB <rolandberry@hotmail.com> wrote:
> Out of the list of these statistics that come out of proc univariate,
> which should typically have the extra decimal place that STD and
> STDMEAN have? Is it only those variables starting with STD? Stated
> another way, if I were to group variables into the MEAN camp and the
> STD camp so that one set used the same format applied to MEAN and one
> set used the format applied to STD then what variables should fall
> into the STD camp apart from those which start with STD?
>
> CSS CV KURTOSIS MAX MEAN MIN MODE N NMISS NOBS RANGE SKEWNESS STD
> STDMEAN SUM SUMWGT USS VAR P1 P5 P10 Q1 MEDIAN Q3 P90 P95 P99 QRANGE
> GINI MAD QN SN STD_GINI STD_MAD STD_QN STD_QRANGE STD_SN MSIGN
> NORMALTEST SIGNRANK PROBM PROBN PROBS PROBT T
>