You've got three problems with your analysis:

1) Y/C isn't the best measure of a RBs skill. Football Outsiders DPAR or DVOA have some problems as well, but they're much better metrics.

2) You're mixing all RBs together. There are plenty of RBs that will never be successful for other reasons than their 40-yard index score. If you eliminate all RBs likely to fail for those reasons, or at least group them together based on those criteria, Barnwell's index becomes much more predictive.

3) It's not a linear variable. RBs with index scores above ~93.0 have the physical tools to succeed in the NFL. Those below 88.0 or so almost certainly do not. In-between it becomes much more a matter of the situation the RB is in.

I agree with the first comment. This post seems like a pretty reckless interpretation of both the article and the table.

First, let's look at the article:

The statement made in the Times article is that Barnwell's equation yields "a number that is, on average, about 100 for an N.F.L. running back, with big, fast players having higher numbers and small, slow players having lower numbers." The claim is that there is a range of index values, with 100 as the average, and that the index has some relationship to body weight and speed.

Now the table:

The table shows the top 15 players in the last 10 years, all of whom have an index higher than 115. This is an extremely small subset, with an average index of 119, almost 20% higher than the average N.F.L. running back. The table clearly states that this is a small subset of the highest index values.

And now let's look at your analysis:

You say that the table presumably contains all the data needed to "cinch the case" and prove that the average index is 100, and that higher numbers are equated with more success. The table itself does not claim to contain enough data for a proof, nor does the article. In fact nowhere does it say that the table is meant to explicitly prove the correlation between index and success.

You then claim that the index should directly predict yards per carry. Nowhere in the article or the table is this stated, so it's puzzling where you get that assumption from. (Yes, yards per carry is one measure of success, but it's unclear how you get from there to expecting a linear relationship among the top 15 values in a large data set.) You then make a chart to disprove your own assumption.

After that, you go on to extrapolate a relationship between 40 time and weight, again using only the top 15 data points from a large data set. We already know that the index has, by definition, some relationship with weight, but claiming that weight alone predicts speed is a surprisingly broad claim given only 15 data points.

What are the flaws here? You take a small set of maximum values and treat it as a complete set of data. You base an analysis on only 15 data points. You claim to disprove linear relationships where none are claimed to exist. You don't make any attempt to acquire the full set of data.

I'm extremely skeptical that your analysis proves or disproves anything at all. Junk charts indeed.

http://www.igegold.com the professional RuneScape money shop igegold to buy your cheap Runescape money,cheap Runescape items,cheap Runescape gold,Runescape gp,Runescape coin, in runescape.

This is only a preview. Your comment has not yet been posted.

Your comment could not be posted. Error type:
Your comment has been posted. Post another comment

The letters and numbers you entered did not match the image. Please try again.

As a final step before posting your comment, enter the letters and numbers you see in the image below. This prevents automated programs from posting comments.

Having trouble reading this image? View an alternate.

(Name is required. Email address will not be displayed with the comment.)

## NEW BOOTCAMP

See our curriculum, instructors. Apply.
Marketing analytics and data visualization expert. Author and Speaker. Currently at Columbia. See my full bio.

## Book Blog

Graphics design by Amanda Lee