What do these mean: Avg star score, etc.

[pink haze]

I still haven't figured this out. What do the numbers in the star score area mean, and how are they calculated? (I'm just asking about the ones indicated by the arrows--I know the others.) I often organize my vid searches by star rating, so I'm curious.



Is this explained elsewhere (like, officially)? I checked around a few times, but I couldn't find anything.

[Nya-chan Production]

The star averages formulas are written in Top 10% statistics, iirc.

The numbers in brackets are percentiles, meaning how high does that vid lie among other vids based on that star rate. So 60th (87th, 85th) in your example means, that it's rated better than 60% (87%, 85%) of all vids in number of stars (star average, star raw average).

[pink haze]

Oh, those are percentiles. That makes sense. Thanks!

The star averages formulas are written in Top 10% statistics, iirc.

You don't mean these equations, do you? (copied from Top 10% Rated Videos page)

Qualified = count(opinions) >= 10

compscore = sum(avg(nonNULL(opinion.category))/count(avg(nonNULL(opinion.category)) except Overall and Re-view

Note: The top and bottom 10% scores are removed from the average calculation (also known as the "Olympic Average")

score = Bayesian Average(avg(compscore+overall+review))

Bayesian Average = (v ÷ (v + m)) × R + (m ÷ (v + m)) × C

where:
R = average for the video (mean) = (old score)
v = number of votes for the video = (votes)
m = minimum votes required to be listed in the top 10% (10)
C = the mean score across all videos (average all vids)

The scores on the top 10% list go up to 10, but the numbers under "Avg (score)" in the star ratings field never exceed 5, so they can't be the same (unless you're supposed to divide one by 2 to get the other). Am I looking in the wrong place?

[Nya-chan Production]

Oh, those are percentiles. That makes sense. Thanks!

The star averages formulas are written in Top 10% statistics, iirc.

You don't mean these equations, do you? (copied from Top 10% Rated Videos page)

Qualified = count(opinions) >= 10

compscore = sum(avg(nonNULL(opinion.category))/count(avg(nonNULL(opinion.category)) except Overall and Re-view

Note: The top and bottom 10% scores are removed from the average calculation (also known as the "Olympic Average")

score = Bayesian Average(avg(compscore+overall+review))

Bayesian Average = (v ÷ (v + m)) × R + (m ÷ (v + m)) × C

where:
R = average for the video (mean) = (old score)
v = number of votes for the video = (votes)
m = minimum votes required to be listed in the top 10% (10)
C = the mean score across all videos (average all vids)

The scores on the top 10% list go up to 10, but the numbers under "Avg (score)" in the star ratings field never exceed 5, so they can't be the same (unless you're supposed to divide one by 2 to get the other). Am I looking in the wrong place?

Yep, I'd expect the formulas being very simmilar, only instead of inserting vote numbers from 0-10, you insert stars from 0-5 (and thus can never go over 5) and of course, there's probably no limit.