Search found 33 matches

Bay of Angels seems like a good fit as long as gambling addiction counts.

I created a new profile to see what the site looked like with percentiles, as I didn't want to change my profile and not be able to change back. It's a little jarring not being able to see the actual scores users have assigned to films, and instead JUST seeing the percentile. Will definitely be sti...

The movies I gave a score of 100 to should be in the 100th percentile (≈99.67%), but it says 99th instead. 99th is the highest possible percentile because the site is calling the lowest percentile the '0th percentile'. to have percentile called 100th we'd need to get rid of the 0th (just like we ha...

mpowell wrote:We've added Percentiles to the film information pages. Hope you like the change!

Looks great!

On the Your Best TCIs page, the list of top users is incorrect, showing people who have TCIs from the previous system, which are lower and therefore falsely rise to the top of the list. No doubt having two simultaneous systems makes things tricky! Ah, yes, that makes sense. I was wondering why the ...

There seems to be a bug where the Best TCIs page shows a few users at the top with unusually low TCIs (around 2%)... https://i.imgur.com/tYRWbR8.png When I click over to their page, the TCIs change to around 20%. https://i.imgur.com/2Z19w7X.png Same thing happened with the other ones. Once I've clic...

https://wikimedia.org/api/rest_v1/media/math/render/svg/de47493414fb48b4939c75694077e466f3c8f935 where cℓ is the count of all scores less than the score of interest, ƒi is the frequency of the score of interest, and N is the number of examinees in the sample. In Criticker terms, that would be: (# o...

Not sure if anyone has mentioned this yet, but since the change to percentiles, the blue bar at the top of the page looks like this for me:

paulofilmo wrote:until we're able to rate purely in colour

Man, that would be cool...

One more quick thought... When converting from percentiles into PSIs for a given user, would it be possible to interpolate? I think that would further improve prediction accuracy, especially for users who don't assign many different scores. So for example, a user might only assign 100, 90, 80, and s...