D&D Movie/TV Rate the D&D movie

[Parmandur]

But you throw away both the top and the lower 1% at the same time. You can't just ignore the lower outliers.

But then the few 0s or 1s or 2s are probably just review bombs.

Yeah, this isn't a scientific poll, though I do find it interesting that the reception here, Metacritic (72 amongst professional critics), and at IMDb (7.5 unweighted, 7.3 weighted) match pretty well, a solid 3.5 or 4 star movie out of 5, though some like it better or worse.

 

[Parmandur]

But you throw away both the top and the lower 1% at the same time. You can't just ignore the lower outliers.

But then the few 0s or 1s or 2s are probably just review bombs.

Worth noting that if you tossed out the lower and top 15 ratings here, that elimates all reviews under 6, while still leaving a couple 10s, and the average and median results don't change. Same with the IMDB numbers, for that matter. So, yes, a sub-6 entries here can be thrown out when considering the general reception.

 

[billd91]

But you throw away both the top and the lower 1% at the same time. You can't just ignore the lower outliers.

But then the few 0s or 1s or 2s are probably just review bombs.

Again, it depends on what you're analyzing and how you've got your data. If you have widely skewed data, a mean value may be significantly different from a median value. So you'd figure out which gives you a more useful value and whether or not you could toss out the outliers, none of which you have to handle symmetrically. For example, if you were looking at the average income of a cohort of graduates from a college english department, you might consider omitting the outlier who won the lottery or became a professional basketball player since they're definitely an oddball and would skew the usefulness of the data (to the prospective student - though not, perhaps, to the recruiter - and thus we have the potential to lie with true statistics).
In the case above, the outliers at 1-3 (notice how few of them there are and that there's a gap between them and the much larger cluster of responses) have relatively little impact on any analysis of mean or median. But if there was a big spike at 1, you might suspect review bombing and ignore the whole bunch.

 

[UngeheuerLich]

Again, it depends on what you're analyzing and how you've got your data. If you have widely skewed data, a mean value may be significantly different from a median value. So you'd figure out which gives you a more useful value and whether or not you could toss out the outliers, none of which you have to handle symmetrically. For example, if you were looking at the average income of a cohort of graduates from a college english department, you might consider omitting the outlier who won the lottery or became a professional basketball player since they're definitely an oddball and would skew the usefulness of the data (to the prospective student - though not, perhaps, to the recruiter - and thus we have the potential to lie with true statistics).
In the case above, the outliers at 1-3 (notice how few of them there are and that there's a gap between them and the much larger cluster of responses) have relatively little impact on any analysis of mean or median. But if there was a big spike at 1, you might suspect review bombing and ignore the whole bunch.

You still do better by doing it symmetrically, because then you don't push the mean value up or down.

And you don't do any harm by balancing out the 1 person who has won the lottery with a normal guy.

 

[UngeheuerLich]

Worth noting that if you tossed out the lower and top 15 ratings here, that elimates all reviews under 6, while still leaving a couple 10s, and the average and median results don't change. Same with the IMDB numbers, for that matter. So, yes, a sub-6 entries here can be thrown out when considering the general reception.

The average will change. The median (mean value) won't. That is why sometimes the mean value is better.

Cutting off both the top and bottom 15% is something between the average/arithmetic middle and the man value. Probably a good estimate.

 

[UngeheuerLich]

Yeah, this isn't a scientific poll, though I do find it interesting that the reception here, Metacritic (72 amongst professional critics), and at IMDb (7.5 unweighted, 7.3 weighted) match pretty well, a solid 3.5 or 4 star movie out of 5, though some like it better or worse.

View attachment 288289

Looks more or less like the shape of the poll here. So it seems we represent the viewer base quite well.

The only big difference is that we have more 8s and your source has as many 7s as 8s.

So I agree with you.

 

[Parmandur]

The average will change. The median (mean value) won't. That is why sometimes the mean value is better.

Cutting off both the top and bottom 15% is something between the average/arithmetic middle and the man value. Probably a good estimate.

Oh, no, not cutting the top and bottom 15%, I meant the top and bottom 15 individual reaponses: that eliminates all results below 6, but not all the 10s.

 

[Parmandur]

Looks more or less like the shape of the poll here. So it seems we represent the viewer base quite well.

The only big difference is that we have more 8s and your source has as many 7s as 8s.

So I agree with you.

Yeah, I guess we like D&D in these here parts? Go figure.

 

[UngeheuerLich]

Oh, no, not cutting the top and bottom 15%, I meant the top and bottom 15 individual reaponses: that eliminates all results below 6, but not all the 10s.

Yes. That does not change anything in my response. Cutting the top and bottom 15 persons don't change the mean value either. The average will go up a bit, as the very low ratings pull it down more than the slightly higher than average ones.

 

[CleverNickName]

But you throw away both the top and the lower 1% at the same time. You can't just ignore the lower outliers.

But then the few 0s or 1s or 2s are probably just review bombs.

Not always, it depends on what you're measuring and how. Sometimes the lower end is bounded by the laws of physics but the upper end is not--in that case you would only ignore the upper bound, since you have more confidence in the lower boundary condition.

But I need to stress this part: this is not a scientific data set. This is an opinion poll on ENWorld, not a thermometer or mass spectrometer or whatever. Since this is all just a matter of opinion, interpretations can widely depending on the observer and the point the observer wants to make, and all are going to be equally valid. There is no "bad data" to remove (because opinions aren't data) and some opinions can't be more "reliable" or "correct" than others.