Category Archives: Data Crunch

Data Crunch Super Bowl — What Does It Take To Win

IMG_8750The actual trophy that will be awarded in a few days.  It lives at the NFL Hall of Fame where we saw it this summer. It was pretty fun.

It’s almost here and it can’t come soon enough.  Both 1. the suspense is killing me, and 2. I’m ready for some basketball!

Back when we were pontificating over whether or not Peyton can play in the cold (yeah, he can!) We began to wonder if cold weather teams had an advantage GETTING to the Super Bowl.  Since the playoff games are played in January, they are usually the coldest games played all season.  We thought this would benefit teams who are accustomed to cold weather.  If this was true, we would expect once they got to the Super Bowl, the cold weather teams would lose more often, as until this year, Super Bowl games were played at warm weather location, and any leg up they had from having more experience in the cold would be gone?

So did they?  Click through to see, and for more fun stats on who wins at the Super Bowl!

Continue reading


Data Crunch — The Benefit of Brothers

Watching my three boys playing sports outside nearly non-stop made me seriously consider the effect of having mini-trainers living at home with you. After reading about Jimmer’s brother running NBA preparation drills, I really began to wonder: Does having an older sibling, or even more siblings, increase your chances of being an elite athlete?  Or is that benefit offset by the additional demands multiple children place on family time and resources?

We decided to look at top 10 draft picks in the NFL and NBA for data.  And of, course, it was fascinating.

According to the Census Bureau, 28% of households in America have 3 or more children.  If family size didn’t affect developing athletes, we would expect approximately 25% of top 10 draftees to come from families of 3 or more children.

Revealingly, not even close.


61% of draftees had 3 or more siblings.  Pretty impressive.

Conversely, let’s see if being an only sibling was a boom or a bust for major league dreams.  Only children do get all the attention and resources, does it help?

click below for more revealing to see, and find out if having an older brother seems to make a difference

Continue reading

Data Crunch — Home Field Advantage?

Sorry for the delay!  I am told there are only two more football weekends, so by popular vote, we are going to stay chatting about football data through the remainder of the season.  Let’s do this.

After last weeks eye opening stats on how badly we (the Broncos and I) do not want to play in Foxborough, (we may or may not have started using derivatives of “Fox” in our family vernacular to indicate a place you don’t want to go), we wanted to look and see if other teams struggled on the road.  Is home field advantage a real thing?

To look at the question, we used all the games from the 2013 NFL season (256 games). As a simple start, we wanted to look at the number of home wins vs. visitor wins, because if the home team won only 50% of the time, then this would be easy to prove.

Home Team Performance


This turns out to not be the case.  The home team won nearly 60% of the games, which has a P-value of .0018 (p-value is the probability of something happening by chance if the factor you are studying actually does not affect the outcome — making this extremely unlikely to happen by random chance)
Next we drilled down to see if, for the 2013 season, it just so happen that the best teams played against the worst teams on the road — for example the Denver Broncos (13-3) playing against the woeful Houston Texans (2-14).  To examine this we looked at each team to see how many home wins they had vs road wins.  If home field advantage is a myth, then bad teams would lose equally at home, or on the road, and vis versa for good teams.
This ratio of home wins to road wins is shown below.
This plot show the ratio of home wins to road wins for each team. The ratio would be 1 if home field advantage doesn’t exist — you would expect teams to have as many wins on the road as they did at home i.e. 4 wins at home:4 wins on the road = 1.  The higher the ratio number, the more games were won at home as on the road.   If their ratio is 2, they won twice as many games at home as they did on the road. i.e. 6 wins at home:3 wins on the road = 2. You can see most teams performed better at home.
It appears as though the teams with the highest ratios seem to be those teams in the bottom third of league like the Vikings (6-10) with 5 home wins or the NY Jets (8-8) with 6 home wins.  It is also interesting to note the teams who perform worse at home, Jacksonville, Philadelphia, and Tennessee.  What do you think that is?
For more gory details, click below!

Data Crunch — Can Peyton Win in the Cold?

Jared and I met in Calculus, and boy it’s been a great match.  Our common love for pragmatism, efficiency, beach houses, and great food have served us well.  I am thrilled to collaborate together on a series, Data Crunch that looks at the data behind long held pieces of popular conceptions.  Can Peyton Manning throw in the cold?  Does the color of tie really influence a Presidential debate?  Visit us every Monday to see what we’ll look at next! Suggestions for future posts?  Suggest above!


For full disclosure, our family bleeds blue and orange.  And what a great year to be a Bronco’s fan.  As the playoffs have approached, we have spent more than a moment fretting about — How will Peyton play in the cold? Will it be warm in New York?  And I’m not the only one.  If you ask Google, “Can Peyt-” it fills in the rest. Can Peyton Manning play in the cold.

We’ve read the articles.  We’ve seen him play.  Is there any truth to the rumor?  And if not, why does it persist?

Peyton Manning began his career in Indianapolis, playing at home in a dome at home for 13 years.  He has been dogged by the story that he can’t play outside in the cold.  So we set to looking at the data to see how closely we need to monitor the weather in East Rutherford, NY in the weeks leading up to Super Bowl XLVIII.


The process

We took Manning’s win-loss record, measured statistics from every game, game day temperature and ran a logistic regression. [for those racking their brain back to college statistics — since the important outcome of each game will be one of two things, win or loss, you can use logistics regression to identify the important factors that determine whether it will be a win or a loss, and evaluate how much each factor influences the final game result. The resulting table shows you which factors you might want to look at more closely.]

Regression analysis indicated air temperature was a significant factor, so we took a closer look at game time temperature, results pictured below.

Peyton’s Win/Loss Percentages, broken down into three temperature ranges 

(10°-40°, 40°-70° and 70°-100°)


Well, data doesn’t lie and this does not look good for January play.

*We decided to label anything colder than Denver “cold.”  This makes us nervous, as we wouldn’t say Denver is warm, but we are  using “cold” to mean colder than Manning typically plays in.

Let’s see how this can be explained.

Click below to see what may be behind this.
Continue reading