Date:         Mon, 14 Jul 2008 11:11:26 -0500
Reply-To:     "Swank, Paul R" <Paul.R.Swank@UTH.TMC.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Swank, Paul R" <Paul.R.Swank@UTH.TMC.EDU>
Subject:      Re: PROC MEANS
Comments: To: Nanita <susana.urbano@GMAIL.COM>
In-Reply-To:  <dff14331-e512-4fb7-8f91-f9976caf0769@2g2000hsn.googlegroups.com>
Content-Type: text/plain; charset="us-ascii"

With an N of 19, a t distribution is more appropriate than Z unless you
have the population standard deviation.

Paul R. Swank, Ph.D.
Professor and Director of Research
Children's Learning Institute
University of Texas Health Science Center - Houston


-----Original Message-----
From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
Nanita
Sent: Monday, July 14, 2008 7:56 AM
To: SAS-L@LISTSERV.UGA.EDU
Subject: Re: PROC MEANS

I have just one more question.

LCLM= mean - 1.96*std_dev/(N)^0.5?
UCLM =mean - 1.96*std_dev/(N)^0.5?

If so, why do I have an output like this?

N=19
Mean= 2.57046
StdDev= 0.11615
LCLM= 2.51447
UCLM = 2.62644 ?

It shouldn't be:
LCLM= 2.57046-(1.96*0.11615)/(19^0.5) = 2.518233
UCLM = 2.57046+(1.96*0.11615)/(19^0.5) = 2.622687 ????


On 14 Jul, 10:55, Nanita <susana.urb...@gmail.com> wrote:
> Hi all,
>
> I have this code to calculate the confidence bands of set of data.
>
> proc means data =sort_ic
> fw=12
> printalltypes
> printidvars
> alpha=0.05
> vardef=NF
> chartype
> mean
> std
> clm;
>
> var V_ASK V_BID V_MID;
>
> by codigo_param prazo;
> id codigo_param prazo;
>
> output out=sort_ic_source
> mean()=
> std()=
> lclm()=
> uclm()=
> / autoname autolabel inherit
> ;
> run;
>
> My question is... what is the destribuition used? Normal(0,1)??
>
> Thanks in advance