Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Stopping rules for multiple looks at data

From   "Moran, John (NWAHS)" <>
To   "''" <>
Subject   st: RE: Stopping rules for multiple looks at data
Date   Wed, 11 Dec 2002 15:43:12 +1030

For offerings in Stata see all the survival goodies at 

Wim van Putten       (
Ron van der Holt     (
Wilfried Graveland   (

Dept of Statistics
Erasmus Medical center
Erasmus MC - Daniel den Hoed Cancer Center

In Stata

Net from "";
Net describe wgmiscel

 Wilfried Graveland
      Dept of Statistics, Erasmus MC
      Rotterdam, The Netherlands
      Programs on interim analysis:
      interim       simulate studies under several true state conditions and
specified timepoints of
                      interim analysis. After simulation the stopping
probabilities of several stopping
                      criteria can be calculated by using afterinterim.ado
      afterinterim  obtain stopping probabilities of several stopping
criteria for studies
                      simulated by interim.ado
      monitor       Program for monitoring a study: calculates stopping
probabilities for given sign. levels
      survdes       A sequential design graphic for a survival endpoint in
which the logrank-statistic
                      is plotted by the information. The borders are found
by a sequential nominal test.

For things not in Stata: besides East200 and the package at David deMets
home site (referred to by other posters),  there are a couple of S+
offerings (S+Sequential as an add on, very expensive) and S-Plus routines
from John Lawrence at FDA, Divison of Biometrics I, Rockville Maryland (J
Lawrence. Designing group sequential trials with survival endpoints. Drug
Inf.J. 36:9-15, 2002)

John moran

-----Original Message-----
From: Clyde Schechter [] 
Sent: Tuesday, December 10, 2002 5:44 AM
Subject: st: Stopping rules for multiple looks at data

Do any of you know of any Stata code to calculate stopping rules for
multiple, prospectively planned, sequential looks at study data, preserving
overall Type I and Type II error rates?  I tried -findit- with a number of
different keywords but didn't get anything that looked like what I need.

Thanks for any help.

Clyde Schechter
Dept. of Family Medicine & Community Health
Albert Einstein College of Medicine
Bronx, NY, USA

*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2023 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index