[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

R: st: clinical trials

From   "Carlo Lazzaro" <[email protected]>
To   <[email protected]>
Subject   R: st: clinical trials
Date   Thu, 3 Jan 2008 19:43:40 +0100

Dear Statalisters,

just to add some lines to the ongoing debate about clinical trials:

the most part of the most recent literature on the economic evaluation of
clinical trials (the side of the matter I am interested in) reports examples
and exercises performed with Stata. This holds particularly true for
non-parametric bootstrap resampling and Monte Carlo simulations and, more in
general, for probabilistic sensitivity analysis of the base case findings. 

However in Italy too SAS is the most frequently used statistical package for
analysing the results of the clinical trials.

Kind Regards,

-----Messaggio originale-----
Da: [email protected]
[mailto:[email protected]] Per conto di E. Paul Wileyto
Inviato: gioved´┐Ż 3 gennaio 2008 19.11
A: [email protected]
Oggetto: Re: st: clinical trials

We're all preaching to the choir here.  Most of us on this list-serve 
like Stata better than SAS.  Do we need to recount the reasons?

1) Better teaching tool than SAS.  (and it's making inroads to clinical 
trials because the epi people like it)
2) Smaller than SAS
3) You can actually reach their Tech Support people.
4) Not predatory in their business practices
5) Interactive in use (No typing a command longer than your dissertation)
6) Really good set of general tools for repeated measures (that can be 
applied to most procedures)

And so on...


Phil Schumm wrote:
> On Jan 3, 2008, at 8:32 AM, David Airey wrote:
>> Does anyone on the list use Stata for clinical trials analysis? I get 
>> the impression companies that specialize in this field use SAS almost 
>> exclusively. From what I know of Stata's feature set, I don't think 
>> this is because Stata cannot be use to perform analysis of clinical 
>> trials data. SAS certainly pushes this area of use with SAS, and they 
>> have several SAS published how-to texts.
> On Jan 3, 2008, at 9:50 AM, Gabi Huiber wrote:
>> Stata's best chance at getting into clinical trials is to win over 
>> one-drug startups and small contractors, I think. But for that Stata 
>> people must be visible at such industry venues as the ISPOR 
>> ( meetings.
> Another area where there can be movement is in the collaborations 
> between industry (drug companies and CROs) and academia, which are, I 
> believe, becoming more common as both try to make maximum use of their 
> resources.  For example, at U of C, our medical center has been 
> converted largely to Stata, thanks to the help of our faculty teaching 
> courses with it and our biostatistics laboratory using it and/or 
> recommending it for a good share of its collaborative work.  As a 
> result, when someone here collaborates with a company, we address this 
> in the workflow we agree upon, and both sides learn from each other.
> <rant>IMHO, vendor lock-in reduces uncertainty for the pointy heads, 
> but is bad regardless of which vendor you're talking about.  Stata has 
> made inroads not because of aggressive marketing or vendor lock-in, 
> but because once someone really learns what can be done with it (and 
> how dependable and insanely well-supported it is), the choice usually 
> becomes a no-brainer.  And, don't forget, those who are in the best 
> position to appreciate it are the ones who are most familiar with the 
> limitations of other packages.</rant>
> -- Phil
> *
> *   For searches and help try:
> *
> *
> *

E. Paul Wileyto, Ph.D.
Assistant Professor of Biostatistics
Tobacco Use Research Center
School of Medicine, U. of Pennsylvania
3535 Market Street, Suite 4100
Philadelphia, PA  19104-3309

Fax: 215-746-7140
[email protected] 

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index