I apologise to the list for having inadvertently copied them in on my reply
to Markus Abt's question regarding SAD and MAD in drug development. I am
possibly compounding a felony by copying everybody in again (this time
deliberately), but this note is to make amends by stating what I believe
these acronyms (probably) stand for, namely exactly what Nick Cox stated,
Single Ascending Dose and Multiple Ascending Dose (not, in this context,
pace Trevor Farrant, Median of Absolute Differences). So, perhaps it would
have been better if I had described the terms not so much as non-standard
but as ambiguous.
A SAD design will typically involve increasing single doses of a drug being
delivered, either in between subject design with accompanying placebo or on
a within subject basis perhaps with randomly intervening placebo. MAD
involves multiple doses, that is to say the comparison of treatment
regimens. The analysis of such designs involves issues of bias variance
trade-offs.
Stephen Senn
At 13:47 15/07/2004 +0100, you wrote:
>Dear Markus/Stephen
>
>I use MAD (Median of Absolute Differences) as described in my book
>Practical Statistics for the Analytical Scientist - The Royal Society of
>Chemistry 1997 (unfortunately there is nothing on SAD). As it happens one
>of my colleagues was using MAD only yesterday analysing missed hair lengths
>and counts. Unfortunately I know very little on drug development hence I
>didn't answer your [Markus] earlier message. I would like to ask [Stephen]
>how you would define whether something is a standard term, e.g., MAD is
>commonly used, Markus was interested in it and yet you were able to answer
>his query.
>
>Trevor Farrant
>Senior Research Statistician
>Gillette Advanced Technology Centre
>
>
>
>
>
> Stephen Senn
> <[log in to unmask] To:
> [log in to unmask]
> LA.AC.UK> cc:
> Sent by: A Subject: Re: QUERY: SAD
> and MAD studies - Statistical Articles/Books
> UK-based
> worldwide e-mail
> broadcast system
> mailing list
> <allstat@JISCMAI
> L.AC.UK>
>
>
> 15/07/2004 13:04
> Please respond
> to Stephen Senn
>
>
>
>
>
>
>Dear Markus,
>There is a chapter on dose-finding in my book Statistical Issues in Drug
>Development, Wiley 1997. that has some discussion of issues and references
>to papers. I personally do not use SAD and MAD as terms and do not think
>they are standard. I heard them used earlier in the week at the ECPM course
>in Basle and if any of your colleagues were attending you might like to ask
>them for notes.
>Regards
>Stephen
>
>At 13:31 15/07/2004 +0200, Abt, Markus {PDMB~Basel} wrote:
> >Dear all,
> >
> > is anybody aware of statistically oriented articles about SAD and MAD
> >studies as they are done in early drug development. I would be
> >interested in (more statistically oriented) articles or books dealing
> >with any aspect or issues that arise during the planning or conduct
> >phase of such studies. An internet search just led to case studies,
> >which is not what I was looking for. My interest is in methodology, whey
> >are they done the way we do them, what alternative designs are there,
> >how many pts are really needed etc.
> > Many thanks in advance for your help.
> >
> >Kind regards
> >Markus
>
>Stephen Senn
>Professor of Statistics
>
>Department of Statistics
>15 University Gardens
><http://www.gla.ac.uk>University of Glasgow
>G12 8QQ
>
>Tel: +44 (0)141 330 5141
>Fax: +44(0)141 330 4814
>email [log in to unmask]
>
> Private webpage: http://www.senns.demon.co.uk/home.html
Stephen Senn
Professor of Statistics
Department of Statistics
15 University Gardens
<http://www.gla.ac.uk>University of Glasgow
G12 8QQ
Tel: +44 (0)141 330 5141
Fax: +44(0)141 330 4814
email [log in to unmask]
Private webpage: http://www.senns.demon.co.uk/home.html
|