Hacker News Reader

Comment by incision | Hacker News Reader

Craig M. Booth has done some very nice visualizations on this subject [1]. I found this chart comparing height/weight of 2013 rosters by position [2] particularly interesting and this set [3] covers a question that anyone who has read Outliers has probably wondered about.

1: http://www.craigmbooth.com/category/nfl/

2: http://www.craigmbooth.com/height-and-weight-of-every-active...

3: http://www.sportsballweekly.com/the-relative-age-effect-in-p...

View on HN

Ugh, on [3], watch out for the non-zero axes. NHL and NBA start their axes at 0, while the others do not. Very tricky, and very deceiving. I think NFL would look very similar to NBA if plotted the same way (they're both within ~10-15% of the expected value).

My guess with NBA players would be that the proportional increase in their heights would be higher.

Does anyone know changes to average weight/height for the population in the US?

I think it would be average weight for NBA players. Modern NBA players are a lot more muscular.

The author points out in the text that the NFL result is statistically significant and the NBA result is not.

A larger random sample ought to fall closer to the line than a smaller sample: it would be statistically highly remarkable if the graphs did look similar with zeroed axes - the larger sample should look much flatter.

Starting both graphs from zero is unhelpful if the goal is correct visual interpretation.

One could argue that the large difference in sample sizes (more than fivefold) justifies scale manipulation to bring the variances into line, but it doesn't appear to me that the author normalized on variance at all (the axis should be something like 800-2000).

I agree with what you say.

To correctly compare the variances, the scale should be adjusted according to the square root of the ratio of sample sizes.

The author has not done this correctly, but I claim that zeroing the axis would be further from the correct graph.

I generally feel that zeroing the axis is never wrong, but yes, in this instance a (properly) cut axis would be better than correct. However, it should be apparent at a glance, and the presence of the other two graphs complicates things as well, so I have some reservations.

Ah, you are correct, thank you. Apparently I wasn't thinking clearly when I normalized the axes to have the same absolute ranges.

With broad correlational data like this, it's important to know what significance threshold is being used, and what the significance value actually is. There are many possible analyses that can be run, and there will be some subset of those analyses that produce significant results by chance, which is why you need hypothesis-driven analysis and/or very conservative corrections for post-hoc analysis.

Without the details, we can't evaluate significance claims.

For number 3 and NBA players, wouldn't the fact that having to be so tall would trump the age effect? Being 7 feet tall is an extremely rare statistic event, so whether the player is born in January or December isn't material.

Heh. This is far better than the explanation I could think of. Thanks.

A lot of this can be explained by the differences in the leagues and how they group kids by age.

NHL: You play by year. An under 17 team (U17) this year will have everyone born in the 1997. If you're born in Jan-May, you're already 17 playing in the under 17 league. This is a small advantage. It is a huge advantage in the U6 league and gets the earlier born into club teams and youth programs where they receive special attention and better hopes of a professional future. This same model applies to soccer.

Basketball: Basketball is unusual in that a tremendous amount of the players growth consists of playing pick up games against other players. Playing against better players is simply a matter of being able to keep up. It is the closest to a meritocracy among these sports.

NFL: Football is unusual in that it is not club dominated but scholastic in nature. The age cutoff is typically Sep 1st, or nearby. I would be curious about those in the July/Aug band and how many were held back a year so they could be older

Reply on news.ycombinator.com