interpretation of transition probability graph

[Rose Matthews]

Hi I produce the following transition probability graph using the following code

Question:
With reference to the graph produced below and the data in the dataset

Am I correct to say at
time 5.26 years these are the following transition probabilities for the state:
Transition 1: Alive to Relapse = 0.28
Transiiton 2: Alive to Dead = 0.11
Transition 3: Relapse to died = 0.60

The reason I ask is because when I draw an imaginary line at 5.26 years for the blue shaded area (it comes up to 0.4 region) on the graph

use http://fmwww.bc.edu/repec/bocode/m/multistate_example,clear


///rfi = relapse indication
//osi overall survvior alive or fead, times rf - relapse free, os - overall srufvial 
msset, id(pid) states(rfi osi) times(rf os) covariates(age)

//Stores matrix callted tmat name, stores the values from transmatrix 
mat tmat = r(transmatrix)

//Displays tmat ie the values of transmatrix 
mat list tmat

//Declare survival data
stset _stop, enter(_start) failure(_status=1) scale(12)

//Only focus on those who had hormonal treatment
drop if hormon ==0  


stmerlin age if _trans1==1, distribution(weibull)
estimate store m1


stmerlin age if _trans2==1, distribution(weibull)
estimate store m2

stmerlin age if _trans3==1, distribution(weibull)
estimate store m3

///transition probabilities for a patient with age 50  

predictms, transmatrix(tmat) models(m1 m2 m3) probability at1(age 50)
graphms

[Carlo Lazzaro]

Rose:
for each time period, transition probabilities should sum up to 1.
Therefore, your statement sounds correct.
What strikes me, though, is the fact that no patients seems to fall/remain in the health state: Alive No Relapse.

[Rose Matthews]

Good point, I didn't think of that,
However, I suppose if patient stayed alive - then they wouldn't have a transition probability



As M Crowther shows his Markov model in slide 7

https://web-archive.lshtm.ac.uk/csm....31-03-2017.pdf