Date:         Wed, 27 Aug 2003 11:42:19 +0100
Reply-To:     John Whittington <John.W@MEDISCIENCE.CO.UK>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         John Whittington <John.W@MEDISCIENCE.CO.UK>
Subject:      Re: partial dates?
Comments: To: Ian Whitlock <WHITLOI1@WESTAT.COM>
In-Reply-To:  <E19qGbb-00041F-00@coumxnn01.netbenefit.co.uk>
Content-Type: text/plain; charset="us-ascii"; format=flowed

At 14:25 22/08/03 -0400, Ian Whitlock wrote:

>Roland,  Sounds like a missing macro in you library.
>     %macro impdate
>[snip]
>          /* 0 - exact date
>             1 - day imputed
>             2 - month imputed
>             3 - day and month imputed
>             4 - year imputed
>             5 - year and day imputed
>             6 - year and month imputed ....

Ian, I think Roland has probably been very wise in keeping any such macro
out of his library.  Assuming we are talking about serious pharmaceutical
work, the FDA and other regulatory authorities would have a fit if people
started imputing dates!

If important dates are missing (partially or completely), attempts should
obviously be made to discover what they should be - and, at the very least,
'intelligent' human attempts made to estimate what they should/could have
been.  In general, any sort of algorithmic imputation is really 'not on'
for clinical trials work.

Kind Regards,


John

----------------------------------------------------------------
Dr John Whittington,       Voice:    +44 (0) 1296 730225
Mediscience Services       Fax:      +44 (0) 1296 738893
Twyford Manor, Twyford,    E-mail:   John.W@mediscience.co.uk
Buckingham  MK18 4EL, UK             mediscience@compuserve.com
----------------------------------------------------------------