Statalist


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

Re: sts test: displaying log-rank test of equality within a Kaplan Meier graph


From   Michael McCulloch <[email protected]>
To   [email protected]
Subject   Re: sts test: displaying log-rank test of equality within a Kaplan Meier graph
Date   Thu, 11 Feb 2010 21:17:34 -0800

Thanks! The humorous re-sizing really makes the point.
I very much appreciate your help Philip.
Michael

On Feb 11, 2010, at 8:46 PM, Philip Ryan wrote:

Michael

The placement() suboption's arguments (ne, se etc) are relative to the
_point_ you nominate as the #y #x arguments of the main text() option. In this case we had text(.05 5...) and the placement was ne , so the box was sited to the northeast (above and to the right) of of the point defined
by y=0.05 and x=5.

If you want the text box elsewhere, you will need to change the #y and #x
specs.

As far as box size is concerned:

sysuse cancer.dta, clear
stset studytime
drop if drug==3
sts test drug
local chi_P  logrank P = `=round(chi2tail(r(df),r(chi2)), .01)'
sts graph, by(drug) risktable text(.05 5 "`chi_P'", place(ne) box
size(small) col(red) width(80) height(40))


... though admittedly more care with the height() and width() option might
be warranted.

Phil

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Michael McCulloch
Sent: Friday, 12 February 2010 2:59 PM
To: [email protected]
Subject: Re: sts test: displaying log-rank test of equality within a Kaplan
Meier graph

Thanks Phillip! This gives me the idea. May I ask:
	* regardless of what place option I use: ne, se, nw, sw, etc., they

all put the text box in the lower left corner. I've read -help
compassdirstyle- and
	* bexpand also doesn't expand the size of the box.
Michael


On Feb 11, 2010, at 8:05 PM, Philip Ryan wrote:

Michael

I note you wanted a "window".  Here is a box instead. I also correct
my
misuse of the return scalars :-(


sysuse cancer.dta, clear
stset studytime
drop if drug==3
sts test drug
local chi_P  logrank P = `=round(chi2tail(r(df),r(chi2)), .01)'
sts graph, by(drug) risktable text(.05 5 "`chi_P'", place(ne) box
size(small) col(red))



Philip Ryan
University of Adelaide


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Michael
McCulloch
Sent: Friday, 12 February 2010 1:23 PM
To: Statalist Statalist
Subject: sts test: displaying log-rank test of equality within a
Kaplan
Meier graph

Dear Statalist members,
I'm creating a Kaplan-Meier graph, and also performing the log-rank
test of equality, for example:

sysuse cancer.dta, clear
stset studytime
drop if drug==3
sts graph, by(drug) risktable
sts test drug

My question: is it possible to display the results of the log-rank
test in a small window within the area of the Kaplan-Meier survival
curve?


Best wishes,

Michael McCulloch
Pine Street Foundation
124 Pine Street
San Anselmo, CA 94960-2674
tel:	415-407-1357
fax: 	206-338-2391

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


Best wishes,

Michael McCulloch
Pine Street Foundation
124 Pine Street
San Anselmo, CA 94960-2674
tel:	415-407-1357
fax: 	206-338-2391

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


Best wishes,

Michael McCulloch
Pine Street Foundation
124 Pine Street
San Anselmo, CA 94960-2674
tel:	415-407-1357
fax: 	206-338-2391

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



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