
Re: Is there a way to calculate an average ranking from uneven lists?
Posted:
Oct 28, 2013 8:09 AM


On Mon, 28 Oct 2013 00:31:31 0700 (PDT), grahamcooper7@gmail.com wrote:
>On Monday, October 28, 2013 12:14:36 AM UTC7, graham...@gmail.com wrote: >> >> SITE 2 >> >> BOOK 1 100% >> >> BOOK 5 80% >> >> BOOK 3 60% >> >> BOOK 11 40% >> >> BOOK 2 20% >> >> BOOK 4 0% >> >> >> >> >> >> >> >> Then to modify each books rank use: >> >> >> >> >> >> BOOKRANK = (BOOKRANK) + %*TOP  (100%)*BOTTOM >> >> / 2 >> >> >> >> >> >> If you use annealing temperatures its like this: >> >> >> >> >> >> BOOKRANK = (BOOKRANK) + TEMP*%*TOP  TEMP*(100%)*BOTTOM >> >> / (TEMP+1) >> >> > > >Not quite right, with the bottom rank for each site being around 0.5 >and the top ranks 2.0, they are meant to be multiplied not added. > > >SITE TOP BOTTOM >1 1.0 1.2 >2 1.1 0.8 >3 0.8 0.9 > > >That might work better with my formula! > > > > BOOKRANK = BOOKRANK + TEMP*%*TOP + TEMP*(100%)*BOTTOM > / (TEMP+1) > > > > >But you'll get a good result with a simple SCALAR for each site too. > >BOOKRANK = ( BOOKRANK + TEMP*WEIGHT*% ) / (TEMP + 1) > >that's what I used on horse races! > > > >That gives each RACE a CLASS which helps pick trifectas! >With books there could be a big variation in GENERAL REVIEWS (wide variance) >and specific review sites of books all in much the same score anyway... >which is where the TOP and BOTTOM more complicate spread calcs. would >improve the result.. > > >Herc
That's a lot to digest. It'll take be some time to think about it.
Thanks for posting.
If you have time, maybe you can apply your method to the sample data I posted for Virgil:
Let's consider some actual data. Here are 3 sample lists each containing 5 books, but not the same 5 books:
Rank List 1 List 2 List 3 1 A B F 2 B A H 3 C E C 4 D G D 5 E D A
When listed by book, the data looks like this:
List 1 List 2 List 3 Books Rank Rank Rank Book A 1 2 5 Book B 2 1 Book C 3 3 Book D 4 5 4 Book E 5 3 Book F 1 Book G 4 Book H 2
How would you calculate average rankings?

