An iteration for particular combination

[Crubal]

Hi,

Forthe following table X, for each combination of variable 'A', 'B' and 'C', there are 'Count' from 0 to 10. 'Probability' means the probability for 'Count' equals to that value. 

Where P1 = Probability(Count = 1)  and P0 + P1 + ... + P10 = 1.

P0, P1, ..., P10 is known. 

A      B      C     Count           Probability 

...     ...     ...        0                      P0

...     ...     ...        1                      P1

.        .       .         .                        .

.        .       .         .                        .

...     ,,,     ,,,       10                     P10 

I would like to write an iteration within a combination of variables 'A', 'B' and 'C', start frpm Count = 0, keep increasing 

for count = i. If P(Count >= i) * 300 - P(Count >= i) * 600 > 0 do i = i+1; until P(Count >= i) * 300 - P(Count >= i) * 600 <= 0 or i =10. It will stop and output i for a combination of 'A', 'B' and 'C'. 

What I need is the number of i, which is regarded as a threshold number in my case (combination of A, B and C) 

How could I write this kind of code since there are many combinations of variables 'A', 'B' and 'C'.

As an example:

A      B      C     Count             Probability 

...     ...     ...        0                      0.05

...     ...     ...        1                      0.10

.        .       .         2                      0.15

.        .       .         3                      0.20

.        .       .         4                      0.20 

.        .       .         .                         .  

.        .       .         .                         .

...     ,,,     ,,,       10                       1 

Example:

When i = 0, P(Count >= 0) * 300 - P(Count < 0) * 600 = 1* 300 - 0* 600 = 300 > 0 Hence, i = 0+1 = 1

When i = 1, P(Count >= 1) * 300 - P(Count < 1) * 600 = 0.95* 300 - 0.05* 600 = 255 > 0   i = 1+1 = 2

When i = 2, P(Count >= 2) * 300 - P(Count < 2) * 600 = 0.85* 300 - 0.15* 600 = 165 > 0   i = 2+1 = 3

When i = 3, P(Count >= 3) * 300 - P(Count < 3) * 600 = 0.70* 300 - 0.30* 600 = 30 > 0     i = 3+1 = 4

When i = 4, P(Count >= 4) * 300 - P(Count < 4) * 600 = 0.50* 300 - 0.50* 600 = -150 < 0   we stop and output i =4 for this combination of 'A', 'B' and 'C'. 

Thank you! 

[ballardw]

It really helps to provide at least a small sample of starting data, say one combination of A B C and the other variables and then what the desired output for that sample data would be.

But in view of your other post about the news vendor problem I suspect that Proc IML may be more conducive and the whole question maybe belongs in either SAS/IML Softaware and Matrix Computations or  the Mathmatical Optimization, Discrete-Event Simulation, and OR part of the forum.

[Crubal]

Thank you! That's a good idea, I changed it and made a small example. I will look at PROC IML as well. Thanks!