Hello all,
I have a data table in Excel with 20+ headers. It deals with insurance, and the only two columns that I want to use are "Claim Number" and "Indemnity $" Using only these two columns, I want to organize the Claim Numbers by the $$ range they fall within (we call them Buckets, and there are 6 of them: NA, $0-500,501-2500,2501-10000,10001-50000,50001-250000). In excel, this is done using a Vlookup.
I also have a list of "Already Reviewed" claims in Excel that I want to use to eliminate claims from the "master" Claim Numbers list because you don't want to review a claim twice. Again, this would be a Vlookup in Excel.
Once I have this list of Claim Numbers alongside the Bucket they fall under (with the already reviewed claims eliminated), I need to separate each bucket so I can randomize the order within the bucket.
Last, once I have each Bucket separated and randomized, I need to run the equivalent of the Excel Solver-Analysis tool. That is, say I am told, "We need you to pick out 25 Claims from this list of 5,000 claims but in way thats proportionate to each bucket." This means for the 25 claim sample, I will choose more from a bucket with 4,000 claims in it than a bucket with 200 claims.
I just realized this is a lot, and I am not sure that the last two steps couldn't be reversed so that I can pick out my claim sample before I randomize. Regardless, any amount of help or feedback would be appreciated!
-Olathe.