it is related to linear splines as far as I can understand but with options for autocorrelation, although the significance of the latter is disputed... as per Kieran McCauls reply and the joinpoint technical article (stat med, 2000, Kim et al).
So in the end I ended up just doing log incidence plots and standard regression models and it looks reasonable..
Thx for the input everyone,
//M
On 3. feb. 2010, at 17.59, Lachenbruch, Peter wrote:
> How is this related to linear splines? From the graph, it looks like a spline model. In Stata, the command mkspline will create the needed variables and then you can do the regression
>
> Tony
>
> Peter A. Lachenbruch
> Department of Public Health
> Oregon State University
> Corvallis, OR 97330
> Phone: 541-737-3832
> FAX: 541-737-4001
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Isabelle Deltour
> Sent: Wednesday, February 03, 2010 12:54 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: RE: RE: time trends in incidence rates and joinpoint analysis in stata
>
> I am not aware of Stata programs doing Joinpoint regressions. But there
> is a program available at http://srab.cancer.gov/joinpoint/.
>
> Hope this helps
> Isabelle
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Kieran McCaul
> Sent: Wednesday, February 03, 2010 1:10 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: RE: time trends in incidence rates and joinpoint analysis
> in stata
>
> ...
>
>
> If you are only counting first cancers of a particular type, there is no
> correlation between time-intervals. The count observed within each
> time-interval will be an independent realisation of the underlying
> Poisson process.
>
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of moleps
> Sent: Wednesday, 3 February 2010 7:12 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: time trends in incidence rates and joinpoint analysis in
> stata
>
> Dear listers,
> Has anyone done joinpoint regression for time trends in incidence rates
> of cancer in stata? Any other suggestions as to how time trends of
> incidence rates in the entire population can be analyzed properly
> incorporating correlation between time-intervals?
>
> Regards,
> //M
>
>
> *
> * 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/
>
> *
> * 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/
*
* 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/
