Greetings All.
I draw your attention to a posting on AllStat yesterday:
Subject:
Professor Donald Rubin - lecture on methodological issues- London
From: Hilary Browne
Date: Fri, 13 Aug 2010 11:51:59 +0100
AllStat archive reference:
https://www.jiscmail.ac.uk/cgi-bin/
webadmin?A2=ind1008&L=ALLSTAT&F=&S=&P=53823
[equivalently: http://tinyurl.com/36uk5yp ]
Excerpt:
Professor Donald Rubin will be giving a special lecture on
methodological issues in the evaluation of a job-training
programme [...]
Abstract: In recent years, job-training programmes have
become increasingly important in many developed countries
with rising unemployment. It is widely accepted that the
best way to evaluate such programmes is to conduct randomized
experiments. With these, among a group of people who indicate
that they want job-training, some are randomly assigned to be
offered the training and the others are denied it, at least
initially. According to a well-defined protocol, outcomes
such as employment statuses or wages for those who are employed
are then measured for those who were offered the training and
compared to the same outcomes for those who were not.
I seriously question the ethics of such an approach! Firstly,
for the sake of the validity of the method, surely those who
are "participating" in the experiment cannot be told that they
are taking part -- otherwise, when they find themselves denied
training, they would suspect (at least) the reason for the denial
and this might influence their future behaviour and bias the
results, relative to applicants who would (non-experimentally)
be passed over in favour of applicants evaluated as more likely
to benefit from the limited available training (which therefore
has to be rationed).
Possibly similar for those who are randomly offered it.
So presumably people in need of job-training are being experimented
on without their consent. Or do the facts of what happens contradict
my surmise -- in which case what allowance is made for such biases?
Secondly: When young people are facing obstacles in a declining
job-market, and therefore experiencing hardship and possible
long-term detriment through -- basically -- no fault of their own,
can it be ethical to abandon them at random to moulder in their
detriment?
What next? Say we have young men already injured at work (e.g. back
strain) who, for that reason, can no longer get work on construction
sites because of their physical weakness. They might benefit (in terms
of finding work) from orthopaedic hospital treatment and physiotherapy.
Or they might not. So let's experiment. So deny them treatment for
their medical conditions at random -- and maybe not tell them why.
I'm all in favour of doing one's best towards valid inference, but ...
Methodological issues indeed!
Comments?
Ted.
--------------------------------------------------------------------
E-Mail: (Ted Harding) <[log in to unmask]>
Fax-to-email: +44 (0)870 094 0861
Date: 14-Aug-10 Time: 13:03:16
------------------------------ XFMail ------------------------------
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|