Re: poly: Does home ownership cause unemployment?

At 04:00 AM 12/10/97 -0500, you wrote:
> So this is the issue of distribution of promiscuity - in some
distributions, other
>things being equal, it may make sense to increase the promiscuity of the most
>cautious people; in all distributions it probably still makes sense to
proportionally
>decrease everyone's promiscuity.

If your only concern is preventing sexually-transmitted disease, yes.

>I am usually quite suspicious of statistical analysis, because some of the
>important variables, ... may be not taken into account at all. ...
>I do not know about this particular research, but a large number of
observations
>I read get caught in statistics and often draw very funny conclusions,
often preselected
>to support some particular policy;

This is a reason to be suspicious regarding ALL forms of analysis. Every
informal
inference you make consciously or unconsciously, every informal argument
you hear, and every
formal statistical or theoretical analsysis can be misleading because
important variables
are not taken into account. This is not a reason to swear off all
inference and analysis.
It IS a reason to try to be as careful and critical as you can be before
allowing yourself
to be persuaded by any analysis. Statistics is no different on this point.

Robin Hanson
hanson@econ.berkeley.edu http://hanson.berkeley.edu/
RWJF Health Policy Scholar, Sch. of Public Health 510-643-1884
140 Warren Hall, UC Berkeley, CA 94720-7360 FAX: 510-643-8614
Received on Wed Dec 10 17:49:54 1997