[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Hazard ratios to rates.

From   Enzo Coviello <>
Subject   Re: st: Hazard ratios to rates.
Date   Wed, 17 Dec 2008 08:21:43 +0100

Steven Samuels ha scritto:
Hazard ratios compare two distributions, but you want to know something about one of the distributions. It is the same as if you had asked: "I know the ratio of two numbers is 2:1. What is one of them?"

So,unless you have more information, the answer to your question is "No".

I would add that a Cox model makes available an estimate of the cumulative hazard and after we can use -stcurve- to obtain an estimate of the hazard at some specified value. See -stcurve-.



On Dec 16, 2008, at 5:03 PM, Ricardo Ovaldia wrote:

Is there a way to convert hazard ratios from survival to rates such as number of deaths per 10,000?

For example if for treatment A compare to a pacebo the HR=1.3, I know that there is 30% increase risk of failure under treatment A. However, can I say what the rate per 1000 patients would be? For example: X patient per 1000 will die on treatment A

*   For searches and help try:

Enzo Coviello
Unità di Epidemiologia e Statistica ASL Bari
Piazza V. Emanuele, 14 - 70054 GIOVINAZZO (BA)
tel +39 080 3357883 - fax +39 080 3357867
mobile 347 5016016 ^^^^
via Imbriani, 186 - 70055 MINERVINO MURGE (BA)
tel +39 0883 695055

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index