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

Re: st: linear probability model (LPM)

From   "Tom Trikalinos" <[email protected]>
To   [email protected]
Subject   Re: st: linear probability model (LPM)
Date   Mon, 14 Jan 2008 09:44:47 -0500

On Jan 14, 2008 4:01 AM, Maarten buis <[email protected]> wrote:
> But you only need to understand two simple things to understand the
> odds ratio: odds (number of successes for every failure) and ratios,
> both of which have a clear substantive interpretation. When dealing
> with categorical dependent variables, taking time to understand that is
> a relatively small investment but a big payoff.

My comment was indeed trivial for everyone with minimal exposure to
research methodology or epi; and off-target in that it side-tracked
the thread. I did not advocate the use of LPM in place of e.g.
logistic (except -as Maarten said- for very selected examples).

I just meant that for many purposes (explain connotations to policy
makers, decision or cost-effectiveness analysis, even for attributable
fractions on the population level) one would transform ORs to RRs
(assuming a control/population prevalence) or just use the OR as RR
(when the usual circumstances hold) to go on with calculations.

*   For searches and help try:

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