| ![](/includes/contimages/spacer.gif) |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: power calculation and sample size
Thanks Svend,
The value of 1.6% means in my case 0.016, therefore the sample will be much
larger.
I have an other problem with three groups (I assume they have equal sizes),
I am interested only in two, is the Bonferroni correction important in this
case when using the sampsi?
It will be useful to know how to include information about censoring in the
sampsi.
BW,
Sami
Sami wrote:
I would be highly thankful to you if you let me know
the way in which sample size can be calculated for
the following problem
I am studying the occurrence of a disease between two
groups. I have an annual average event rate of 1.6 %
and a follow up period of 5 years, I want to have a
power of 80% with alpha 5% I am looking to detect a
relative risk of 3.0 associated with group1 versus
group 2 .
--------------------------------------------------------
Do you assume that there will be no censorings? If there
may be, you must make an assumption about the rate of
censorings. In the following I assume no censorings.
Next: Is the assumed incidence rate of 1.6% per year:
- for the non-exposed?
- for the exposed?
- a population average?
If the latter is the case, you also need an assumption
about the proportion exposed.
Assuming that the annual incidence rate of 1.6% is among the
unexposed, the five year incidence proportion is approximately
5*1.6% = 0.08 (actually it is 1-exp(-0.08) = 0.077, but that
is hardly important).
. sampsi .24 .08 , power(.80)
Estimated sample size for two-sample comparison of proportions
Test Ho: p1 = p2, where p1 is the proportion in population 1
and p2 is the proportion in population 2
Assumptions:
alpha = 0.0500 (two-sided)
power = 0.8000
p1 = 0.2400
p2 = 0.0800
n2/n1 = 1.00
Estimated required sample sizes:
n1 = 94
n2 = 94
But are these assumptions right? There are more sophisticated
tools for sample size estimation. That is fine, but the most
important is to use realistic assumptions.
Hope this helps
Svend
________________________________________________________
Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(Institute of Public Health, Department of Epidemiology)
Vennelyst Boulevard 6
DK-8000 Aarhus C, Denmark
Phone, work: +45 8942 6090
Phone, home: +45 8693 7796
Fax: +45 8613 1580
E-mail: [email protected]
_________________________________________________________
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
_________________________________________________________________
Txt a lot? Get Messenger FREE on your mobile.
https://livemessenger.mobile.uk.msn.com/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/