Date:         Fri, 30 Jun 2006 15:37:06 -0700
Reply-To:     John Horne <John.Horne@INSIGHTSNOW.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         John Horne <John.Horne@INSIGHTSNOW.COM>
Subject:      Re: probnorm for pdf of standard normal distribution?
Content-Type: text/plain; charset="US-ASCII"

Use the pdf function:

pdf('normal',0);
probit(0.5);

probnorm(0);
cdf('normal',0);

The last two are the same and return 0.5 in this case (i.e., the
probability that a value is greater than this score in a normal
distribution having a mean of 1 and a standard deviation of zero).

The first is the pdf of the standard normal(i.e., 0.4).  The second is
the probit or normal inverse function and returns the inverse of the
standard normal (i.e., the value of the random variable at this
probability).  In this case, it resolves to zero.  The first two are not
equivalent because one is a pdf and takes the value of the random
variable as argument while the second is an inverse function and takes
the probability associated with the random variable as argument.

I prefer the cdf & pdf functions because you can enter the mean and
standard deviation of the normal distribution if you're dealing with a
normal that is not standard normal.

Cheers!


-----Original Message-----
From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
sportsfun77@HOTMAIL.COM
Sent: Friday, June 30, 2006 2:11 PM
To: SAS-L@LISTSERV.UGA.EDU
Subject: probnorm for pdf of standard normal distribution?

I have a stupid question to ask:

I know people use probnorm to compute N( ), which is cdf of standard
normal distribution. Can we use the probnorm to compute N'( ), which is
the pdf of standard normal distribution? If not, what else should we
use?

Thanks a lot for your help!