Use of R in clinical trials

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
46 messages Options
123
Reply | Threaded
Open this post in threaded view
|

Use of R in clinical trials

Cody Hamilton-2
Dear all,

There have been a variety of discussions on the R list regarding the use of R in clinical trials. The following post from the STATA list provides an interesting opinion regarding why SAS remains so popular in this arena: http://www.stata.com/statalist/archive/2008-01/msg00098.html

Regards,

-Cody Hamilton

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Frank Harrell
Cody,

How amazing that SAS is still used to produce reports that reviewers
hate and that requires tedious low-level programming.  R + LaTeX has it
all over that approach IMHO.  We have used that combination very
successfully for several data and safety monitoring reporting tasks for
clinical trials for the pharmaceutical industry.

Frank


Cody Hamilton wrote:
> Dear all,
>
> There have been a variety of discussions on the R list regarding the use of R in clinical trials. The following post from the STATA list provides an interesting opinion regarding why SAS remains so popular in this arena: http://www.stata.com/statalist/archive/2008-01/msg00098.html
>
> Regards,
>
> -Cody Hamilton

--
Frank E Harrell Jr   Professor and Chairman        School of Medicine
                      Department of Biostatistics   Vanderbilt University

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Frank Harrell
Department of Biostatistics, Vanderbilt University
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Ista Zahn
Agreed. The tables in the pdf the poster at
http://www.stata.com/statalist/archive/2008-01/msg00098.html links to
look terrible compared to the standard I am used to from
Hmisc::latex(). Just saying.

-Ista

On Wed, Feb 17, 2010 at 9:33 PM, Frank E Harrell Jr
<[hidden email]> wrote:

> Cody,
>
> How amazing that SAS is still used to produce reports that reviewers hate
> and that requires tedious low-level programming.  R + LaTeX has it all over
> that approach IMHO.  We have used that combination very successfully for
> several data and safety monitoring reporting tasks for clinical trials for
> the pharmaceutical industry.
>
> Frank
>
>
> Cody Hamilton wrote:
>>
>> Dear all,
>>
>> There have been a variety of discussions on the R list regarding the use
>> of R in clinical trials. The following post from the STATA list provides an
>> interesting opinion regarding why SAS remains so popular in this arena:
>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>
>> Regards,
>>
>> -Cody Hamilton
>
> --
> Frank E Harrell Jr   Professor and Chairman        School of Medicine
>                     Department of Biostatistics   Vanderbilt University
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>



--
Ista Zahn
Graduate student
University of Rochester
Department of Clinical and Social Psychology
http://yourpsyche.org

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Erik Iverson-3
In reply to this post by Frank Harrell
Frank E Harrell Jr wrote:
> Cody,
>
> How amazing that SAS is still used to produce reports that reviewers
> hate and that requires tedious low-level programming.  R + LaTeX has
> it all over that approach IMHO.  We have used that combination very
> successfully for several data and safety monitoring reporting tasks
> for clinical trials for the pharmaceutical industry.
>
> Frank

I used to work for a research group that also used R + LaTeX to produce
DSMB reports for clinical trials.  If the DSMB members had only been
exposed to SAS reports before, you could not get them to stop praising
the quality of the R + LaTeX reports, even years into a trial.

Erik

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Frank Harrell
Erik Iverson wrote:

> Frank E Harrell Jr wrote:
>> Cody,
>>
>> How amazing that SAS is still used to produce reports that reviewers
>> hate and that requires tedious low-level programming.  R + LaTeX has
>> it all over that approach IMHO.  We have used that combination very
>> successfully for several data and safety monitoring reporting tasks
>> for clinical trials for the pharmaceutical industry.
>>
>> Frank
>
> I used to work for a research group that also used R + LaTeX to produce
> DSMB reports for clinical trials.  If the DSMB members had only been
> exposed to SAS reports before, you could not get them to stop praising
> the quality of the R + LaTeX reports, even years into a trial.
>
> Erik

Thanks for your note Erik.  That's been my experience too.

For those that haven't seen it already, you may be interested in
http://biostat.mc.vanderbilt.edu/Rreport and its "Statistical Tables and
Plots" link.

Frank

--
Frank E Harrell Jr   Professor and Chairman        School of Medicine
                      Department of Biostatistics   Vanderbilt University

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Frank Harrell
Department of Biostatistics, Vanderbilt University
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Peter Dalgaard
In reply to this post by Frank Harrell
Frank E Harrell Jr wrote:
> Cody,
>
> How amazing that SAS is still used to produce reports that reviewers
> hate and that requires tedious low-level programming.  R + LaTeX has it
> all over that approach IMHO.  We have used that combination very
> successfully for several data and safety monitoring reporting tasks for
> clinical trials for the pharmaceutical industry.
>
> Frank

There is a point to it, though. One of my friends and colleagues in the
business put it in one word: Mediocrity.

SAS does a mediocre job at analysing and reporting and data handling
using a mediocre control language. But: It can be handled by mediocre
programmers writing and modifying mediocre programs, and those people
are more available and replaceable, maybe even cheaper. R/LaTeX may run
circles around SAS in terms of capapilities, flexibility, and elegance,
but it can also send a programmer who doesn't have the required skill
set running around in circles.

-pd

>
> Cody Hamilton wrote:
>> Dear all,
>>
>> There have been a variety of discussions on the R list regarding the
>> use of R in clinical trials. The following post from the STATA list
>> provides an interesting opinion regarding why SAS remains so popular
>> in this arena:
>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>
>> Regards,
>>
>> -Cody Hamilton
>


--
    O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
   c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
  (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45) 35327918
~~~~~~~~~~ - ([hidden email])              FAX: (+45) 35327907

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Bill.Venables
I can't believe I'm saying this, but I think Peter is being a bit harsh on SAS.  

I prefer Greg Snow's analogy (in the fortune collection): If SPSS (or SAS) and R were vehicles, SPSS would be the bus, going on fixed routes and efficiently carrying lots of people to standard places, whereas R is the off-road 4WD SUV, complete with all sorts of kit including walking boots, kayak on the top, &c.  R will take you anywhere you want to go, but it might take you longer to master it than the simple recipes for data analysis typical of the 'bus' programs.


Bill Venables
CSIRO/CMIS Cleveland Laboratories


-----Original Message-----
From: [hidden email] [mailto:[hidden email]] On Behalf Of Peter Dalgaard
Sent: Thursday, 18 February 2010 5:55 PM
To: Frank E Harrell Jr
Cc: [hidden email]; Cody Hamilton
Subject: Re: [R] Use of R in clinical trials

Frank E Harrell Jr wrote:
> Cody,
>
> How amazing that SAS is still used to produce reports that reviewers
> hate and that requires tedious low-level programming.  R + LaTeX has it
> all over that approach IMHO.  We have used that combination very
> successfully for several data and safety monitoring reporting tasks for
> clinical trials for the pharmaceutical industry.
>
> Frank

There is a point to it, though. One of my friends and colleagues in the
business put it in one word: Mediocrity.

SAS does a mediocre job at analysing and reporting and data handling
using a mediocre control language. But: It can be handled by mediocre
programmers writing and modifying mediocre programs, and those people
are more available and replaceable, maybe even cheaper. R/LaTeX may run
circles around SAS in terms of capapilities, flexibility, and elegance,
but it can also send a programmer who doesn't have the required skill
set running around in circles.

-pd

>
> Cody Hamilton wrote:
>> Dear all,
>>
>> There have been a variety of discussions on the R list regarding the
>> use of R in clinical trials. The following post from the STATA list
>> provides an interesting opinion regarding why SAS remains so popular
>> in this arena:
>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>
>> Regards,
>>
>> -Cody Hamilton
>


--
    O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
   c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
  (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45) 35327918
~~~~~~~~~~ - ([hidden email])              FAX: (+45) 35327907

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Liviu Andronic
In reply to this post by Frank Harrell
On 2/18/10, Frank E Harrell Jr <[hidden email]> wrote:
>  How amazing that SAS is still used to produce reports that reviewers hate
> and that requires tedious low-level programming.  R + LaTeX has it all over
>
To simplify things, R + LyX could also be a solution.
Liviu

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

John Sorkin
In reply to this post by Cody Hamilton-2
It is easy to devolve into visceral response mode, lose objectivity and slip into intolerance. R, S, S-Plus, SAS, PASW (nee SPSS), STATA, are all tools. Each has strengths and weaknesses. No one is inherently better, or worse than the other. The quality of the results produced by anyone of them is a function of the abilities of the person who manipulates them. Don't expect quality work from any program unless the person running the program knows what he, or she is doing!  
John
John Sorkin
[hidden email]
-----Original Message-----
From: Liviu Andronic <[hidden email]>
Cc:  <[hidden email]>
To: Frank E Harrell Jr <[hidden email]>
Cc: Cody Hamilton <[hidden email]>

Sent: 2/18/2010 4:29:27 AM
Subject: Re: [R] Use of R in clinical trials

On 2/18/10, Frank E Harrell Jr <[hidden email]> wrote:
>  How amazing that SAS is still used to produce reports that reviewers hate
> and that requires tedious low-level programming.  R + LaTeX has it all over
>
To simplify things, R + LyX could also be a solution.
Liviu

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Confidentiality Statement:
This email message, including any attachments, is for th...{{dropped:6}}

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Barry Rowlingson
On Thu, Feb 18, 2010 at 12:12 PM, John Sorkin
<[hidden email]> wrote:
> It is easy to devolve into visceral response mode, lose objectivity and slip into intolerance. R, S, S-Plus, SAS, PASW (nee SPSS), STATA, are all tools. Each has strengths and weaknesses. No one is inherently better, or worse than the other.

Sometimes it seems the name of the tool is more important. SPSS became
PASW for a brief inkling of time until someone at IBM perhaps
recognised the enormous value of just the name and then decided they
better stick with it, but decided to prefix everything with 'IBM'.
Corporate ego trip anyone?

http://spss.com/software/statistics/

Barry

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Frank Harrell
In reply to this post by Bill.Venables
I really like both of your responses.  To add to Peter's thoughts, I've
found that more than half of SAS programmers can learn modern
programming languages given a push.  And if pharmaceutical companies
ever knew the true cost of SAS in terms of their having to hire more
programmers to deal with an archaic language they would be astonished.
Rumor had it that Pfizer's yearly SAS licensing costs were $14M/year
several years ago.  Programmer costs were probably in the same range.

Frank


[hidden email] wrote:

> I can't believe I'm saying this, but I think Peter is being a bit harsh on SAS.  
>
> I prefer Greg Snow's analogy (in the fortune collection): If SPSS (or SAS) and R were vehicles, SPSS would be the bus, going on fixed routes and efficiently carrying lots of people to standard places, whereas R is the off-road 4WD SUV, complete with all sorts of kit including walking boots, kayak on the top, &c.  R will take you anywhere you want to go, but it might take you longer to master it than the simple recipes for data analysis typical of the 'bus' programs.
>
>
> Bill Venables
> CSIRO/CMIS Cleveland Laboratories
>
>
> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On Behalf Of Peter Dalgaard
> Sent: Thursday, 18 February 2010 5:55 PM
> To: Frank E Harrell Jr
> Cc: [hidden email]; Cody Hamilton
> Subject: Re: [R] Use of R in clinical trials
>
> Frank E Harrell Jr wrote:
>> Cody,
>>
>> How amazing that SAS is still used to produce reports that reviewers
>> hate and that requires tedious low-level programming.  R + LaTeX has it
>> all over that approach IMHO.  We have used that combination very
>> successfully for several data and safety monitoring reporting tasks for
>> clinical trials for the pharmaceutical industry.
>>
>> Frank
>
> There is a point to it, though. One of my friends and colleagues in the
> business put it in one word: Mediocrity.
>
> SAS does a mediocre job at analysing and reporting and data handling
> using a mediocre control language. But: It can be handled by mediocre
> programmers writing and modifying mediocre programs, and those people
> are more available and replaceable, maybe even cheaper. R/LaTeX may run
> circles around SAS in terms of capapilities, flexibility, and elegance,
> but it can also send a programmer who doesn't have the required skill
> set running around in circles.
>
> -pd
>
>> Cody Hamilton wrote:
>>> Dear all,
>>>
>>> There have been a variety of discussions on the R list regarding the
>>> use of R in clinical trials. The following post from the STATA list
>>> provides an interesting opinion regarding why SAS remains so popular
>>> in this arena:
>>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>>
>>> Regards,
>>>
>>> -Cody Hamilton
>
>


--
Frank E Harrell Jr   Professor and Chairman        School of Medicine
                      Department of Biostatistics   Vanderbilt University

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Frank Harrell
Department of Biostatistics, Vanderbilt University
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Peter Dalgaard
In reply to this post by Bill.Venables
[hidden email] wrote:
> I can't believe I'm saying this, but I think Peter is being a bit harsh on SAS.  
>
> I prefer Greg Snow's analogy (in the fortune collection): If SPSS (or
>
SAS) and R were vehicles, SPSS would be the bus, going on fixed routes
and efficiently carrying lots of people to standard places, whereas R is
the off-road 4WD SUV, complete with all sorts of kit including walking
boots, kayak on the top, &c. R will take you anywhere you want to go,
but it might take you longer to master it than the simple recipes for
data analysis typical of the 'bus' programs.


I wasn't really trying to be harsh. I think my friend actually said
something like "endearing mediocrity", and particularly the recruiting
aspect is not something to take lightly if you have a business to run.

Incidentally SAS is not quite as bus-like as SPSS - it does actually
allow you to take the driver's seat as long as you keep to the road. It
would be more like the pickup truck or delivery van: moves best in a
straight line, but will take you between most places you need to go.

I have

Stata as the mini SUV city car (like SAS but quicker round the corners)

Genstat as the Land Rover (a bit like R designed in the 60's, but still
running)

The F1 car would probably be Ox or Gauss or similar programs designed to
do one kind of thing very efficiently.

-pd


>
> Bill Venables
> CSIRO/CMIS Cleveland Laboratories
>
>
> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On Behalf Of Peter Dalgaard
> Sent: Thursday, 18 February 2010 5:55 PM
> To: Frank E Harrell Jr
> Cc: [hidden email]; Cody Hamilton
> Subject: Re: [R] Use of R in clinical trials
>
> Frank E Harrell Jr wrote:
>> Cody,
>>
>> How amazing that SAS is still used to produce reports that reviewers
>> hate and that requires tedious low-level programming.  R + LaTeX has it
>> all over that approach IMHO.  We have used that combination very
>> successfully for several data and safety monitoring reporting tasks for
>> clinical trials for the pharmaceutical industry.
>>
>> Frank
>
> There is a point to it, though. One of my friends and colleagues in the
> business put it in one word: Mediocrity.
>
> SAS does a mediocre job at analysing and reporting and data handling
> using a mediocre control language. But: It can be handled by mediocre
> programmers writing and modifying mediocre programs, and those people
> are more available and replaceable, maybe even cheaper. R/LaTeX may run
> circles around SAS in terms of capapilities, flexibility, and elegance,
> but it can also send a programmer who doesn't have the required skill
> set running around in circles.
>
> -pd
>
>> Cody Hamilton wrote:
>>> Dear all,
>>>
>>> There have been a variety of discussions on the R list regarding the
>>> use of R in clinical trials. The following post from the STATA list
>>> provides an interesting opinion regarding why SAS remains so popular
>>> in this arena:
>>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>>
>>> Regards,
>>>
>>> -Cody Hamilton
>
>


--
   O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45) 35327918
~~~~~~~~~~ - ([hidden email])              FAX: (+45) 35327907

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Bert Gunter
In reply to this post by Frank Harrell
DISCLAIMER: This represents my personal view and in no way reflects that of
my company.

Warning: This is a long harangue that contains no useful information on R.
May be wise to delete without reading.
----------

Sorry folks, I still don't understand your comments. As Cody's original post
pointed out, there are a host of factors other than ease of programmability
or even quality of results that weigh against any change. To reiterate, all
companies have a huge infrastructure of **validated SAS code** that would
have to be replaced. This, in itself, would take years and cost tens of
millions of dollars at least. Also to reiterate, it's not only
statistical/reporting functionality but even more the integration into the
existing clinical database systems that would have to be rewritten **and
validated**. All this would have to be done while continuing full steam on
existing submissions. It is therefore not surprising to me that no pharma
company in its right mind even contemplates undertaking such an effort.

To put these things into perspective. Let's say Pfizer has 200 SAS
programmers (it's probably more, as they are a large Pharma, but I dunno).
If each programmer costs, conservatively, $200K U.S. per year fully loaded,
that's $40 million U.S. for SAS Programmers. And this is probably a severe
underestimate. So the $14M quoted below is chicken feed -- it doesn't even
make the radar.

To add further perspective, a single (large) pivotal clinical trial can
easily cost $250M . A delay in approval due to fooling around trying to
shift to a whole new software system could easily cause hundreds of million
to billions if it means a competitor gets to the marketplace first. So, to
repeat, SAS costs are chicken feed.

Yes, I suppose that the present system institutionalizes mediocrity. How
could it be otherwise in any such large scale enterprise? Continuity,
reliability, and robustness are all orders of magnitude more important for
both the FDA and Pharma to get safe and efficacious drugs to the public.
Constantly hopping onto the latest and greatest "craze" (yes, I exaggerate
here!) would be dangerous, unacceptable, and would probably delay drug
approvals. I consider this another example of the Kuhnsian paradigm (Thomas
Kuhn: "The Structure of Scientific Revolutions")in action.

This is **not** to say that there is not a useful role for R (or STATA or
...) to play in clinical trial submissions or, more generally, in drug
research and development. There certainly is. For the record, I use R
exclusively in my (nonclinical statistics) work. Nor is to say that all
change must be avoided. That would be downright dangerous. But let's please
keep these issues in perspective. One's enthusiasm for R's manifold virtues
should not replace common sense and logic. That, too, would be unfortunate.

Since I've freely blustered, I am now a fair target. So I welcome forceful
rebuttals and criticisms and, as I've said what I wanted to, I will not
respond. You have the last word.

Bert Gunter
Genentech Nonclinical Biostatistics
 


 -----Original Message-----
From: [hidden email] [mailto:[hidden email]] On
Behalf Of Frank E Harrell Jr
Sent: Thursday, February 18, 2010 6:01 AM
To: [hidden email]
Cc: [hidden email]; [hidden email]
Subject: Re: [R] Use of R in clinical trials

I really like both of your responses.  To add to Peter's thoughts, I've
found that more than half of SAS programmers can learn modern
programming languages given a push.  And if pharmaceutical companies
ever knew the true cost of SAS in terms of their having to hire more
programmers to deal with an archaic language they would be astonished.
Rumor had it that Pfizer's yearly SAS licensing costs were $14M/year
several years ago.  Programmer costs were probably in the same range.

Frank


[hidden email] wrote:
> I can't believe I'm saying this, but I think Peter is being a bit harsh on
SAS.  
>
> I prefer Greg Snow's analogy (in the fortune collection): If SPSS (or SAS)
and R were vehicles, SPSS would be the bus, going on fixed routes and
efficiently carrying lots of people to standard places, whereas R is the
off-road 4WD SUV, complete with all sorts of kit including walking boots,
kayak on the top, &c.  R will take you anywhere you want to go, but it might
take you longer to master it than the simple recipes for data analysis
typical of the 'bus' programs.
>
>
> Bill Venables
> CSIRO/CMIS Cleveland Laboratories
>
>
> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]]
On Behalf Of Peter Dalgaard

> Sent: Thursday, 18 February 2010 5:55 PM
> To: Frank E Harrell Jr
> Cc: [hidden email]; Cody Hamilton
> Subject: Re: [R] Use of R in clinical trials
>
> Frank E Harrell Jr wrote:
>> Cody,
>>
>> How amazing that SAS is still used to produce reports that reviewers
>> hate and that requires tedious low-level programming.  R + LaTeX has it
>> all over that approach IMHO.  We have used that combination very
>> successfully for several data and safety monitoring reporting tasks for
>> clinical trials for the pharmaceutical industry.
>>
>> Frank
>
> There is a point to it, though. One of my friends and colleagues in the
> business put it in one word: Mediocrity.
>
> SAS does a mediocre job at analysing and reporting and data handling
> using a mediocre control language. But: It can be handled by mediocre
> programmers writing and modifying mediocre programs, and those people
> are more available and replaceable, maybe even cheaper. R/LaTeX may run
> circles around SAS in terms of capapilities, flexibility, and elegance,
> but it can also send a programmer who doesn't have the required skill
> set running around in circles.
>
> -pd
>
>> Cody Hamilton wrote:
>>> Dear all,
>>>
>>> There have been a variety of discussions on the R list regarding the
>>> use of R in clinical trials. The following post from the STATA list
>>> provides an interesting opinion regarding why SAS remains so popular
>>> in this arena:
>>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>>
>>> Regards,
>>>
>>> -Cody Hamilton
>
>


--
Frank E Harrell Jr   Professor and Chairman        School of Medicine
                      Department of Biostatistics   Vanderbilt University

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Frank Harrell
Bert,

I have to disagree with just part of what you said.  The ultimate
savings by using R is astronomical.  Up front it would definitely cost
more, as you so eloquently stated.  So it boils down to short-term vs.
long-term thinking.

More importantly, the statistical/graphical reports created using R are
more informative and lead to better reviews and more clear assessment of
pharmaceutical safety problems by not relying on reams of tables that
put reviewers to sleep.

Frank


Bert Gunter wrote:

> DISCLAIMER: This represents my personal view and in no way reflects that of
> my company.
>
> Warning: This is a long harangue that contains no useful information on R.
> May be wise to delete without reading.
> ----------
>
> Sorry folks, I still don't understand your comments. As Cody's original post
> pointed out, there are a host of factors other than ease of programmability
> or even quality of results that weigh against any change. To reiterate, all
> companies have a huge infrastructure of **validated SAS code** that would
> have to be replaced. This, in itself, would take years and cost tens of
> millions of dollars at least. Also to reiterate, it's not only
> statistical/reporting functionality but even more the integration into the
> existing clinical database systems that would have to be rewritten **and
> validated**. All this would have to be done while continuing full steam on
> existing submissions. It is therefore not surprising to me that no pharma
> company in its right mind even contemplates undertaking such an effort.
>
> To put these things into perspective. Let's say Pfizer has 200 SAS
> programmers (it's probably more, as they are a large Pharma, but I dunno).
> If each programmer costs, conservatively, $200K U.S. per year fully loaded,
> that's $40 million U.S. for SAS Programmers. And this is probably a severe
> underestimate. So the $14M quoted below is chicken feed -- it doesn't even
> make the radar.
>
> To add further perspective, a single (large) pivotal clinical trial can
> easily cost $250M . A delay in approval due to fooling around trying to
> shift to a whole new software system could easily cause hundreds of million
> to billions if it means a competitor gets to the marketplace first. So, to
> repeat, SAS costs are chicken feed.
>
> Yes, I suppose that the present system institutionalizes mediocrity. How
> could it be otherwise in any such large scale enterprise? Continuity,
> reliability, and robustness are all orders of magnitude more important for
> both the FDA and Pharma to get safe and efficacious drugs to the public.
> Constantly hopping onto the latest and greatest "craze" (yes, I exaggerate
> here!) would be dangerous, unacceptable, and would probably delay drug
> approvals. I consider this another example of the Kuhnsian paradigm (Thomas
> Kuhn: "The Structure of Scientific Revolutions")in action.
>
> This is **not** to say that there is not a useful role for R (or STATA or
> ...) to play in clinical trial submissions or, more generally, in drug
> research and development. There certainly is. For the record, I use R
> exclusively in my (nonclinical statistics) work. Nor is to say that all
> change must be avoided. That would be downright dangerous. But let's please
> keep these issues in perspective. One's enthusiasm for R's manifold virtues
> should not replace common sense and logic. That, too, would be unfortunate.
>
> Since I've freely blustered, I am now a fair target. So I welcome forceful
> rebuttals and criticisms and, as I've said what I wanted to, I will not
> respond. You have the last word.
>
> Bert Gunter
> Genentech Nonclinical Biostatistics
>  
>
>
>  -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On
> Behalf Of Frank E Harrell Jr
> Sent: Thursday, February 18, 2010 6:01 AM
> To: [hidden email]
> Cc: [hidden email]; [hidden email]
> Subject: Re: [R] Use of R in clinical trials
>
> I really like both of your responses.  To add to Peter's thoughts, I've
> found that more than half of SAS programmers can learn modern
> programming languages given a push.  And if pharmaceutical companies
> ever knew the true cost of SAS in terms of their having to hire more
> programmers to deal with an archaic language they would be astonished.
> Rumor had it that Pfizer's yearly SAS licensing costs were $14M/year
> several years ago.  Programmer costs were probably in the same range.
>
> Frank
>
>
> [hidden email] wrote:
>> I can't believe I'm saying this, but I think Peter is being a bit harsh on
> SAS.  
>> I prefer Greg Snow's analogy (in the fortune collection): If SPSS (or SAS)
> and R were vehicles, SPSS would be the bus, going on fixed routes and
> efficiently carrying lots of people to standard places, whereas R is the
> off-road 4WD SUV, complete with all sorts of kit including walking boots,
> kayak on the top, &c.  R will take you anywhere you want to go, but it might
> take you longer to master it than the simple recipes for data analysis
> typical of the 'bus' programs.
>>
>> Bill Venables
>> CSIRO/CMIS Cleveland Laboratories
>>
>>
>> -----Original Message-----
>> From: [hidden email] [mailto:[hidden email]]
> On Behalf Of Peter Dalgaard
>> Sent: Thursday, 18 February 2010 5:55 PM
>> To: Frank E Harrell Jr
>> Cc: [hidden email]; Cody Hamilton
>> Subject: Re: [R] Use of R in clinical trials
>>
>> Frank E Harrell Jr wrote:
>>> Cody,
>>>
>>> How amazing that SAS is still used to produce reports that reviewers
>>> hate and that requires tedious low-level programming.  R + LaTeX has it
>>> all over that approach IMHO.  We have used that combination very
>>> successfully for several data and safety monitoring reporting tasks for
>>> clinical trials for the pharmaceutical industry.
>>>
>>> Frank
>> There is a point to it, though. One of my friends and colleagues in the
>> business put it in one word: Mediocrity.
>>
>> SAS does a mediocre job at analysing and reporting and data handling
>> using a mediocre control language. But: It can be handled by mediocre
>> programmers writing and modifying mediocre programs, and those people
>> are more available and replaceable, maybe even cheaper. R/LaTeX may run
>> circles around SAS in terms of capapilities, flexibility, and elegance,
>> but it can also send a programmer who doesn't have the required skill
>> set running around in circles.
>>
>> -pd
>>
>>> Cody Hamilton wrote:
>>>> Dear all,
>>>>
>>>> There have been a variety of discussions on the R list regarding the
>>>> use of R in clinical trials. The following post from the STATA list
>>>> provides an interesting opinion regarding why SAS remains so popular
>>>> in this arena:
>>>> http://www.stata.com/statalist/archive/2008-01/msg00098.html
>>>>
>>>> Regards,
>>>>
>>>> -Cody Hamilton
>>
>
>


--
Frank E Harrell Jr   Professor and Chairman        School of Medicine
                      Department of Biostatistics   Vanderbilt University

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Frank Harrell
Department of Biostatistics, Vanderbilt University
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Christopher W. Ryan
In reply to this post by Bert Gunter
Pure Food and Drug Act: 1906
FDA: 1930s
founding of SAS: early 1970s

(from the history websites of SAS and FDA)

What did pharmaceutical companies use for data analysis before there was
SAS? And was there much angst over the change to SAS from whatever was
in use before?

Or was there not such emphasis on and need for thorough data analysis
back then?

--Chris
Christopher W. Ryan, MD
SUNY Upstate Medical University Clinical Campus at Binghamton
425 Robinson Street, Binghamton, NY  13904
cryanatbinghamtondotedu

"If you want to build a ship, don't drum up the men to gather wood,
divide the work and give orders. Instead, teach them to yearn for the
vast and endless sea."  [Antoine de St. Exupery]

Bert Gunter wrote:

> DISCLAIMER: This represents my personal view and in no way reflects that of
> my company.
>
> Warning: This is a long harangue that contains no useful information on R.
> May be wise to delete without reading.
> ----------
>
> Sorry folks, I still don't understand your comments. As Cody's original post
> pointed out, there are a host of factors other than ease of programmability
> or even quality of results that weigh against any change. To reiterate, all
> companies have a huge infrastructure of **validated SAS code** that would
> have to be replaced. This, in itself, would take years and cost tens of
> millions of dollars at least. Also to reiterate, it's not only
> statistical/reporting functionality but even more the integration into the
> existing clinical database systems that would have to be rewritten **and
> validated**. All this would have to be done while continuing full steam on
> existing submissions. It is therefore not surprising to me that no pharma
> company in its right mind even contemplates undertaking such an effort.
>
> To put these things into perspective. Let's say Pfizer has 200 SAS
> programmers (it's probably more, as they are a large Pharma, but I dunno).
> If each programmer costs, conservatively, $200K U.S. per year fully loaded,
> that's $40 million U.S. for SAS Programmers. And this is probably a severe
> underestimate. So the $14M quoted below is chicken feed -- it doesn't even
> make the radar.
>
> To add further perspective, a single (large) pivotal clinical trial can
> easily cost $250M . A delay in approval due to fooling around trying to
> shift to a whole new software system could easily cause hundreds of million
> to billions if it means a competitor gets to the marketplace first. So, to
> repeat, SAS costs are chicken feed.
>
> Yes, I suppose that the present system institutionalizes mediocrity. How
> could it be otherwise in any such large scale enterprise? Continuity,
> reliability, and robustness are all orders of magnitude more important for
> both the FDA and Pharma to get safe and efficacious drugs to the public.
> Constantly hopping onto the latest and greatest "craze" (yes, I exaggerate
> here!) would be dangerous, unacceptable, and would probably delay drug
> approvals. I consider this another example of the Kuhnsian paradigm (Thomas
> Kuhn: "The Structure of Scientific Revolutions")in action.
>
> This is **not** to say that there is not a useful role for R (or STATA or
> ...) to play in clinical trial submissions or, more generally, in drug
> research and development. There certainly is. For the record, I use R
> exclusively in my (nonclinical statistics) work. Nor is to say that all
> change must be avoided. That would be downright dangerous. But let's please
> keep these issues in perspective. One's enthusiasm for R's manifold virtues
> should not replace common sense and logic. That, too, would be unfortunate.
>
> Since I've freely blustered, I am now a fair target. So I welcome forceful
> rebuttals and criticisms and, as I've said what I wanted to, I will not
> respond. You have the last word.
>
> Bert Gunter
> Genentech Nonclinical Biostatistics

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Bert Gunter
The key dates are 1938 and 1962. The FDC act of 1938 essentially mandated
(demonstration of) safety. The tox testing infrastructure grew from that.At
that time, there were no computers, little data, little statistics
methodology. Statistics played little role -- as is still mainly the case
today for safety. Any safety findings whatever in safety testing raise a
flag; statistical significance in the multiple testing framework is
irrelevant.

1962 saw the Kefauver-Harris Amendments that mandated demonstration of
efficacy. That was the key. The whole clinical trial framework and the
relevant statistical design and analysis infrastructure flowed from that
regulatory requirement. SAS's development soon after was therefore the first
direct response to the statistical software needs that resulted. Note also,
that statistical software was in its infancy at this time: before SAS there
was Fortran and COBOL; there was no statistical software.

So, as you can see, there essentially was **no** "before SAS".

(Corrections/additional information welcome!)

Bert Gunter
Genentech Nonclinical Biostatistics
 
 

-----Original Message-----
From: [hidden email] [mailto:[hidden email]] On
Behalf Of Christopher W. Ryan
Sent: Thursday, February 18, 2010 10:09 AM
To: [hidden email]
Cc: [hidden email]
Subject: Re: [R] Use of R in clinical trials

Pure Food and Drug Act: 1906
FDA: 1930s
founding of SAS: early 1970s

(from the history websites of SAS and FDA)

What did pharmaceutical companies use for data analysis before there was
SAS? And was there much angst over the change to SAS from whatever was
in use before?

Or was there not such emphasis on and need for thorough data analysis
back then?

--Chris
Christopher W. Ryan, MD
SUNY Upstate Medical University Clinical Campus at Binghamton
425 Robinson Street, Binghamton, NY  13904
cryanatbinghamtondotedu

"If you want to build a ship, don't drum up the men to gather wood,
divide the work and give orders. Instead, teach them to yearn for the
vast and endless sea."  [Antoine de St. Exupery]

Bert Gunter wrote:
> DISCLAIMER: This represents my personal view and in no way reflects that
of
> my company.
>
> Warning: This is a long harangue that contains no useful information on R.
> May be wise to delete without reading.
> ----------
>
> Sorry folks, I still don't understand your comments. As Cody's original
post
> pointed out, there are a host of factors other than ease of
programmability
> or even quality of results that weigh against any change. To reiterate,
all

> companies have a huge infrastructure of **validated SAS code** that would
> have to be replaced. This, in itself, would take years and cost tens of
> millions of dollars at least. Also to reiterate, it's not only
> statistical/reporting functionality but even more the integration into the
> existing clinical database systems that would have to be rewritten **and
> validated**. All this would have to be done while continuing full steam on
> existing submissions. It is therefore not surprising to me that no pharma
> company in its right mind even contemplates undertaking such an effort.
>
> To put these things into perspective. Let's say Pfizer has 200 SAS
> programmers (it's probably more, as they are a large Pharma, but I dunno).
> If each programmer costs, conservatively, $200K U.S. per year fully
loaded,
> that's $40 million U.S. for SAS Programmers. And this is probably a severe
> underestimate. So the $14M quoted below is chicken feed -- it doesn't even
> make the radar.
>
> To add further perspective, a single (large) pivotal clinical trial can
> easily cost $250M . A delay in approval due to fooling around trying to
> shift to a whole new software system could easily cause hundreds of
million

> to billions if it means a competitor gets to the marketplace first. So, to
> repeat, SAS costs are chicken feed.
>
> Yes, I suppose that the present system institutionalizes mediocrity. How
> could it be otherwise in any such large scale enterprise? Continuity,
> reliability, and robustness are all orders of magnitude more important for
> both the FDA and Pharma to get safe and efficacious drugs to the public.
> Constantly hopping onto the latest and greatest "craze" (yes, I exaggerate
> here!) would be dangerous, unacceptable, and would probably delay drug
> approvals. I consider this another example of the Kuhnsian paradigm
(Thomas
> Kuhn: "The Structure of Scientific Revolutions")in action.
>
> This is **not** to say that there is not a useful role for R (or STATA or
> ...) to play in clinical trial submissions or, more generally, in drug
> research and development. There certainly is. For the record, I use R
> exclusively in my (nonclinical statistics) work. Nor is to say that all
> change must be avoided. That would be downright dangerous. But let's
please
> keep these issues in perspective. One's enthusiasm for R's manifold
virtues
> should not replace common sense and logic. That, too, would be
unfortunate.
>
> Since I've freely blustered, I am now a fair target. So I welcome forceful
> rebuttals and criticisms and, as I've said what I wanted to, I will not
> respond. You have the last word.
>
> Bert Gunter
> Genentech Nonclinical Biostatistics

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Rolf Turner
In reply to this post by John Sorkin

On 19/02/2010, at 1:12 AM, John Sorkin wrote:

> It is easy to devolve into visceral response mode, lose objectivity and slip into intolerance. R, S, S-Plus, SAS, PASW (nee SPSS), STATA, are all tools. Each has strengths and weaknesses. No one is inherently better, or worse than the other. The quality of the results produced by anyone of them is a function of the abilities of the person who manipulates them. Don't expect quality work from any program unless the person running the program knows what he, or she is doing!  


I think this sort of ``moral relativism'' is specious.  It is certainly true that the
programmer or analyst has to know what he or she is doing irrespective of package or
language.  And SAS at least has some relative strengths in respect of its capacity to
handle large data sets.  But overall, in terms of having an effective environment in
which to conduct statistical analyses, there can be no question that the R/S/S-Plus
group win hands down.

        cheers,

                Rolf Turner
######################################################################
Attention:
This e-mail message is privileged and confidential. If you are not the
intended recipient please delete the message and notify the sender.
Any views or opinions presented are solely those of the author.

This e-mail has been scanned and cleared by MailMarshal
www.marshalsoftware.com
######################################################################

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Douglas Bates-2
In reply to this post by Bert Gunter
On Thu, Feb 18, 2010 at 12:36 PM, Bert Gunter <[hidden email]> wrote:
> The key dates are 1938 and 1962. The FDC act of 1938 essentially mandated
> (demonstration of) safety. The tox testing infrastructure grew from that.At
> that time, there were no computers, little data, little statistics
> methodology. Statistics played little role -- as is still mainly the case
> today for safety. Any safety findings whatever in safety testing raise a
> flag; statistical significance in the multiple testing framework is
> irrelevant.

> 1962 saw the Kefauver-Harris Amendments that mandated demonstration of
> efficacy. That was the key. The whole clinical trial framework and the
> relevant statistical design and analysis infrastructure flowed from that
> regulatory requirement. SAS's development soon after was therefore the first
> direct response to the statistical software needs that resulted. Note also,
> that statistical software was in its infancy at this time: before SAS there
> was Fortran and COBOL; there was no statistical software.

> So, as you can see, there essentially was **no** "before SAS".

> (Corrections/additional information welcome!)

My recollection is that the BMD programs (which, in a later version,
became BMDP) predated SAS and were specifically for BioMeDical
analysis.  Early statistical software was oriented to applications
areas: SPSS (Statistical Package for the Social Sciences) was the
predominant system used in the social sciences, BMD(P) in biomedical
areas and SAS in agricultural/life sciences settings.  Eventually the
more coherent framework and comparative ease-of-use of SAS (yes, I am
saying that with a straight face - in the days of batch jobs submitted
on punched cards with data residing on magnetic tape, there were
different standards of ease-of-use) won over more users in medical
fields.


> Bert Gunter
> Genentech Nonclinical Biostatistics
>
>
>
> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On
> Behalf Of Christopher W. Ryan
> Sent: Thursday, February 18, 2010 10:09 AM
> To: [hidden email]
> Cc: [hidden email]
> Subject: Re: [R] Use of R in clinical trials
>
> Pure Food and Drug Act: 1906
> FDA: 1930s
> founding of SAS: early 1970s
>
> (from the history websites of SAS and FDA)
>
> What did pharmaceutical companies use for data analysis before there was
> SAS? And was there much angst over the change to SAS from whatever was
> in use before?
>
> Or was there not such emphasis on and need for thorough data analysis
> back then?
>
> --Chris
> Christopher W. Ryan, MD
> SUNY Upstate Medical University Clinical Campus at Binghamton
> 425 Robinson Street, Binghamton, NY  13904
> cryanatbinghamtondotedu
>
> "If you want to build a ship, don't drum up the men to gather wood,
> divide the work and give orders. Instead, teach them to yearn for the
> vast and endless sea."  [Antoine de St. Exupery]
>
> Bert Gunter wrote:
>> DISCLAIMER: This represents my personal view and in no way reflects that
> of
>> my company.
>>
>> Warning: This is a long harangue that contains no useful information on R.
>> May be wise to delete without reading.
>> ----------
>>
>> Sorry folks, I still don't understand your comments. As Cody's original
> post
>> pointed out, there are a host of factors other than ease of
> programmability
>> or even quality of results that weigh against any change. To reiterate,
> all
>> companies have a huge infrastructure of **validated SAS code** that would
>> have to be replaced. This, in itself, would take years and cost tens of
>> millions of dollars at least. Also to reiterate, it's not only
>> statistical/reporting functionality but even more the integration into the
>> existing clinical database systems that would have to be rewritten **and
>> validated**. All this would have to be done while continuing full steam on
>> existing submissions. It is therefore not surprising to me that no pharma
>> company in its right mind even contemplates undertaking such an effort.
>>
>> To put these things into perspective. Let's say Pfizer has 200 SAS
>> programmers (it's probably more, as they are a large Pharma, but I dunno).
>> If each programmer costs, conservatively, $200K U.S. per year fully
> loaded,
>> that's $40 million U.S. for SAS Programmers. And this is probably a severe
>> underestimate. So the $14M quoted below is chicken feed -- it doesn't even
>> make the radar.
>>
>> To add further perspective, a single (large) pivotal clinical trial can
>> easily cost $250M . A delay in approval due to fooling around trying to
>> shift to a whole new software system could easily cause hundreds of
> million
>> to billions if it means a competitor gets to the marketplace first. So, to
>> repeat, SAS costs are chicken feed.
>>
>> Yes, I suppose that the present system institutionalizes mediocrity. How
>> could it be otherwise in any such large scale enterprise? Continuity,
>> reliability, and robustness are all orders of magnitude more important for
>> both the FDA and Pharma to get safe and efficacious drugs to the public.
>> Constantly hopping onto the latest and greatest "craze" (yes, I exaggerate
>> here!) would be dangerous, unacceptable, and would probably delay drug
>> approvals. I consider this another example of the Kuhnsian paradigm
> (Thomas
>> Kuhn: "The Structure of Scientific Revolutions")in action.
>>
>> This is **not** to say that there is not a useful role for R (or STATA or
>> ...) to play in clinical trial submissions or, more generally, in drug
>> research and development. There certainly is. For the record, I use R
>> exclusively in my (nonclinical statistics) work. Nor is to say that all
>> change must be avoided. That would be downright dangerous. But let's
> please
>> keep these issues in perspective. One's enthusiasm for R's manifold
> virtues
>> should not replace common sense and logic. That, too, would be
> unfortunate.
>>
>> Since I've freely blustered, I am now a fair target. So I welcome forceful
>> rebuttals and criticisms and, as I've said what I wanted to, I will not
>> respond. You have the last word.
>>
>> Bert Gunter
>> Genentech Nonclinical Biostatistics
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Peter Dalgaard
In reply to this post by Christopher W. Ryan
Christopher W. Ryan wrote:

> Pure Food and Drug Act: 1906
> FDA: 1930s
> founding of SAS: early 1970s
>
> (from the history websites of SAS and FDA)
>
> What did pharmaceutical companies use for data analysis before there was
> SAS? And was there much angst over the change to SAS from whatever was
> in use before?
>
> Or was there not such emphasis on and need for thorough data analysis
> back then?

Well, I'm not quite old enough for this, but the story I heard is that
before SAS was the desktop calculator, essentially. Statistics had
correspondingly enormous focus on balanced designs, allowing computation
to be reduced to means and sums of squares. This would typically be left
to consulting firms employing (human) computers to literally do the
sums. Digital computers had of course been around for decades at the
time but mostly for hard core physics. (Well, actually, they were
finding their way into accounting too.) So SAS was, I expect, pretty
uniformly a relief.

At the same time, the requirements of the FDA have been tightening; I
suppose partly due to technological feasibility, partly in response to
certain practises being recognised as dubious, like selective
publication, multiple testing, etc. And more data are required since new
drugs are rarely all that much better than older ones, while the worries
about side effects have increased.


> --Chris
> Christopher W. Ryan, MD
> SUNY Upstate Medical University Clinical Campus at Binghamton
> 425 Robinson Street, Binghamton, NY  13904
> cryanatbinghamtondotedu



--
    O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
   c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
  (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45) 35327918
~~~~~~~~~~ - ([hidden email])              FAX: (+45) 35327907

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Use of R in clinical trials

Cody Hamilton-2
In reply to this post by Cody Hamilton-2
Points regarding the advantages of LaTex are very well taken. If I were fortunate enough to have complete ownership of the document (as might be the case with a DSMB report produced by the Biostat group), then LaTex would be a wonderful choice.  Though I am not a LaTex user, I can easily imagine that the productivity gains could be considerable.

Unfortunately, in most cases the Biostatistics group is responsible for providing a relatively small piece of the overall document which is owned by another group that inevitably uses MS Office.


--- On Wed, 2/17/10, Erik Iverson <[hidden email]> wrote:

> From: Erik Iverson <[hidden email]>
> Subject: Re: [R] Use of R in clinical trials
> To: "Frank E Harrell Jr" <[hidden email]>
> Cc: "Cody Hamilton" <[hidden email]>, [hidden email]
> Date: Wednesday, February 17, 2010, 9:05 PM
> Frank E Harrell Jr wrote:
> > Cody,
> >
> > How amazing that SAS is still used to produce reports
> that reviewers hate and that requires tedious low-level
> programming.  R + LaTeX has it all over that approach
> IMHO.  We have used that combination very successfully
> for several data and safety monitoring reporting tasks for
> clinical trials for the pharmaceutical industry.
> >
> > Frank
>
> I used to work for a research group that also used R +
> LaTeX to produce DSMB reports for clinical trials.  If
> the DSMB members had only been exposed to SAS reports
> before, you could not get them to stop praising the quality
> of the R + LaTeX reports, even years into a trial.
>
> Erik
>





______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
123