It seems I can’t stop writing about Bill Barnwell (here, here, and here) and his article, Mere Mortals, which presents “evidence” that baseball players who played during the years 1959 through 1988 have a higher mortality rate than football players.  it seemed immediately obvious to me when I read the article that the two groups he was comparing were not directly comparable, and it seemed likely that the difference in mortality rates was probably due to differences in ages between the cohort, rather than the sport itself.  Up to this point, however, I was just making well educated guesses as to how to explain the results.

So, I went and collected data myself and ran a quick analysis to check.  The findings?  When age is added to a model predicting death, the effect of the sport on mortality rate completely disappears.  This means that if two players are the exact same age and one played professional football and the other played professional baseball for at least five years and one of those years was between 1959 and 1988 there is no evidence that the football player nor the baseball player is more likely to be deceased.  

Data collection

Football

Using R, I scraped http://www.football-almanac.com to get a list of players names.  I then used this list of players names to scrape http://www.pro-football-reference.com to get information about each players date of birth, age at death (if they have died), the start and end years of their careers, height, and weight.  (A note about a shortcoming of my data collection for football: If a player had the same name as another player, I only collected one. I believe this is a small issue and will not affect the overall results, but it is worth noting.)  In total, the football player data set had 14, 396 players.

Baseball

Using R, I scraped http://www.baseball-almanac.com to get a list of players names.  I then used this list of players names to scrape http://www.baseballl-reference.com to get information about each players date of birth, age at death (if they have died), the start and end years of their careers, height, and weight.  For baseball players, I was able to collect all players, including those who had the same name as another player.  In total, the baseball player data set had 5,587 players.

Time Frame

Both the baseball and football data sets were whittled down to only consider players who played at least five seasons and any of those seasons fell between 1959 and 1988.  (These are slightly different standards than in the Barnwell article, but, again, the larger point should remain the same.)  This left  2,436 football players and 967 baseball players.  The mean age of baseball players in my sample was 64.19 while the mean age of football players was 60.91.  (Barnwell tweeted that the difference in ages between his two groups, which were defined slightly differently, was about 24 months.)  The mean ages of my two groups is significantly different with a p-value of <0.00000000000001.  That’s a big deal.

The distributions of the ages of the football and baseball players is displayed below using a density estimator in R.  You’ll notice that there are many more young players in the football group than in the baseball group.  This indicates that mortality rates cannot be compared directly to one another as is done in the Barnwell article.

Think for a minute about the graph below.  Without knowing anything about which color represents which sport, which of these two groups should have a higher mortality rate?  (Hint: The blue one)

Analysis

Fisher Exact Test

259 out of the 2436 qualifying football players was deceased according to http://www.pro-football-reference.com for a mortality rate of 10.63%.  Among baseball players, 137 out of 967 were dead for a mortality rate of 14.17%.  Both of these rates are lower than Barnwell’s, but are of similar relative magnitudes.  Using a Fisher exact test, the null hypothesis of no association is rejected with a p-value of 0.004407, which is essentially identical to Barnwell’s p-value of 0.004.  So there is a statistically significant difference between these groups.  That’s a fact. But….

Logistic Regression

This type of analysis estimates the probability of a certain event, in this case, death, while taking into account multiple factors that could be related to the event.  Running a logistic regression model with death as an outcome and only sport as a dummy variable predictor yields a p-value of 0.00384 for the significance of sport being associated with death.  This is largely the same result as the Fisher exact test as neither are controlling for any other variables besides sport.

When age, actually, it’s technically years since birth since some people are deceased, is added to the model, the effect of sport disappears entirely.  The p-value for age is and the p-value for sport is 0.441, which is not significant.

Conclusions and Future work

To reiterate, what we can conclude from this is that if two players are the exact same age and one played professional football and the other played professional baseball for at least five years and one of those years was between 1959 and 1988 that neither the football player nor the baseball player is more likely to be deceased.

The purpose of this work is to demonstrate that the conclusions reached in Barnwell’s article Mere Mortals is at the very least misleading.  The author makes the case that baseball players are dying more often than football players.  While it is true that baseball players from this time period are more likely to be deceased than their football counterparts, I have demonstrated that it is not BECAUSE they played baseball, rather it is their age, a pretty serious risk factor for death, that is a more significant predictor of being deceased.

I think a more interesting analysis than the one presented here by myself would be to look at survival times after retiring from each of the sports looking at risk factors including age, BMI, and years in the respective league.

A Final Request

Is it possible that baseball players die at a younger age than football players?  I suppose it is possible, but I think it’s unlikely.  What is for sure is that Bill Barnwell’s article, due to the flawed application of statistical methods, does not in any way demonstrate that baseball players are dying more often than football players.  I believe it to be irresponsible to present work which falsely understates the potential dangers of playing football especially with the recent concussion and CTE studies involving NFL players.  Therefore, I am requesting that Bill Barnwell openly retract his article, Mere Mortals, in writing on Grantland.com due the major statistical flaws of the study.

Bill Barnwell demonstrated what many are calling a stunning result when he showed that the mortality rate of baseball players was actually higher than that of football players who played at least five seasons during the years 1959 through 1988. How can this be explained?  Especially with all of the recent news about head injuries and player suicides in football.  Football sure seems like it should be more dangerous.  But the comparison of baseball players to football players doesn’t make any sense to me. I think a better comparison is baseball players and Supreme Court justices.  Football players are in peak physical condition during their playing days, whereas Supreme Court justices just sit and wait.  Their levels of physical activity are probably more comparable to that of a baseball player standing and waiting for something to happen.  Then, after all that waiting in the Supreme Court, a high profile case come along and raises stress levels.  Similarly, baseball players, after long periods of waiting in games, must sprint all out at certain times.  In this way, the healthcare hearings in the Supreme Court are very much like hitting a double or a triple in baseball.  These similarities make comparing baseball players to Supreme Court justices more “apples to apples” than baseball to football players.

The methodology

I’ll be using the same methodology in Barnwell et al. to compare mortality rates.

Justice/Player Pool

Since, data on baseball players has already  been collected, there is no need to collect the data again.  I will include any Justice in the pool who served at least one year between 1959 and 1988.  This includes Tom C. Clark, Earl Warren, John Marshall Harlan II, William J. Brennan, Charles Evans Whitaker, Potter Stewart, Byron White, Arthur Goldberg, Abe Fortas, Thurgood Marshall, Warren E. Burger, Harry Blackmun, Lewis F. Powell, Jr., William Rehnquist, John Paul Stevens, Sandra Day O’Connor, Antonin Scalia, and Anthony Kennedy.

The Findings

That’s correct: Supreme court justices who served any years between 1959 and 1988 died at a much higher rate than  baseball players from the same time frame.  The difference between the two is statistically significant and allows us to reject the nul hypothesis.  Therefore, there is a meaningful difference between the mortality reates of baseball players and supreme court justices.

The 95% confidence interval for baseball players is 14.1% to 17.8% and for the Supreme court justices it is 58.6% to 96.98% and the p-value for the Fisher exact test is .000224!  Highly significant.

Conclusions

Football is safer than baseball, and baseball is safer than the serving on the Supreme Court.  So, why is it that Supreme Court justices from the ’60s, ’70s, and ’80s are dying more frequently than baseball players from the same era? Well, in the words of Barnwell:

Truthfully, as a layman, I can’t say with any certainty, and I don’t think it’s appropriate to speculate.

Cheers?

On Monday, I posted in response to Bill Barnwell’s article on Grantland called “Mere Mortals” where he makes the claim that regular NFL players who played between 1959 and 1988 have a statistically significantly lower mortality rate than regular baseball players of the same era.  I suspect all that has been demonstrated is that older people die more often than younger people because the groups are not directly comparable, since age was not controlled for in the comparison.  What I believe we are dealing with here is correlation and not causation.  Baseball, almost surely, is not killing people faster than baseball players.  And even if it was, it has not been demonstrated.  Not even close.

So, I’ve been reading some other stuff by Barnwell (which I really enjoy) including his Twitter feed lately and two particular tweets interested me greatly.  The first one:

Appreciate the kind words about the study. For those who asked: Average age of MLB player at time of passing was 60.9; for NFL, it was 58.8.

And the second one:

Went back and looked at age for all players in my study by request; MLB players in sample were on average 24 months older than NFL players.

The first tweet should make someone pause and think about how this can be, while at the same time, baseball players have a higher mortality rate.  I suspected, originally, and still do, that it was because one group was simply older than the other group.  Which…..is exactly what was tweeted in the second tweet.  MLB players in the sample were TWO YEARS older than NFL players in the sample.  Can you name something that 62 year olds do more often than 60 year olds?  I can.  They die more often.

So, it seems to me like all that the study has actually demonstrated is that older people die more often.  So, maybe Barnwell will dial back his “stunning” claims?  Maybe not.  This is the tweet directly before tweet number 2:

ICYMI: Wrote about the stunning respective mortality rates of MLB and NFL players from 1959-88 on @grantland33. http://ow.ly/d1QGH

Cheers.