1

A very well validated score exists. This score predicts mortality after disease A when patients present from country W . The score is a 4 point score. If a subject presents from the community with disease A and his score is 1, mortality is x1. If a subject presents from the community with disease A and his score is 2, mortality is x2 etc...

I have a population with disease A. Some present from country W and some from country M. each subject has a clear classfication= mortality ie dead or alive.

The score when applied to those from country W seems to perform as expected for each category. meaning individuals with score 1 seems to have a mortality very close to x1 and those with score 2 close to x2 etc...

However for population M, that is not the case. score 1 mortality is far from x1 and score 2 far from x2 etc....

1- is there a statistic that proves that for my sample population (from country W) the concordance between the expected mortality at each score category and mortality is very good? 2- is there a statistic that shows that for the sample from country M this is not the case ?

In other words, for a validated score, how can I show that it expectedly performs well in the target population but not so in another.

please be elaborate and simple. I am not a statistician.

Ali Mansour
  • 21
  • You cannot 'prove' that the two countries are different with respect to the score. Maybe you can say that if the two countries are the same, it would be almost impossible to get the data we have at hand. The data are what we have; we can make statements about them. – BruceET May 24 '20 at 04:30
  • that makes sense, i am more interested in showing the poor performance os the score in country M, and that it performs as expected in country W , any way to do that? – Ali Mansour May 24 '20 at 04:35
  • Analyzing the three-way table will give you an idea whether there are statistically significant differences among your counts. If so, you can do further 'post hoc' analyses to investigate differences of interest. – BruceET May 24 '20 at 05:14

1 Answers1

0

I hope this points a way to analyzing your data. If you don't think it is the right approach for your data, please explain you misgivings.

From what you say, it seems you can put counts of subjects into the 16 'cells' of the table below. Then, in the Total column at the right you will put counts of the total numbers of subjects from Countries M vs, W, and Dead vs. Alive. Notice that you will need counts not percentages or proportions. 

                   Score
             -----------------
Cntry  Mortl   1   2   3   4      Total
---------------------------------------
  M    Dead
       Alive
  W    Dead
       Alive
---------------------------------------
Total

This is a three-way contingency table. It contains counts for three categorical variables: Score (1,2,3,4), Country (M,W), and Mortality (Dead, Alive).

The link gets you started with the analysis in R statistical software for a particular dataset. That dataset has categorical variables Treated (Y,N), Sex (M, F), and Improvement (None, Some, Marked).

BruceET
  • 56,185
  • thank you for helping and trying to get me there. However, let me be more elaborate: here is what I have, please check the table in the link https://stats.stackexchange.com/questions/468263/comparing-the-performance-of-a-score-across-different-populations2.. any chance there is a statistic that can be used to prove that the observed percentages are in line with expected in country W but not in M – Ali Mansour May 24 '20 at 13:21