Superbowl 51, Feb 5 2017
From Wikipedia: Super Bowl LI (51) was an American football game played between the American Football Conference (AFC) champions New England Patriots and the National Football Conference (NFC) champions Atlanta Falcons, to decide the National Football League (NFL) champion for the 2016 season. The Patriots defeated the Falcons, 34–28, in the first Super Bowl ever to go into an overtime period.
Super Bowl LI was played at NRG Stadium in Houston, Texas, on Sunday, February 5, 2017. It was the second Super Bowl to be held at NRG Stadium, the other being Super Bowl XXXVIII in 2004, which also featured the New England Patriots; and also the third time the Super Bowl has been played in Houston, with Super Bowl VIII in 1974 having been held at Rice Stadium.
Thirty NFL records were either broken or matched in Super Bowl LI. The Patriots rallied from a 25-point deficit to win (trailed 28–3 with 8:31 left in the third quarter), breaking the record for the largest deficit overcome to win the Super Bowl.
Specific Hypothesis and Results
The GCP event was set for 6 hours beginning at 6 pm EST (23:00 Feb 5 to 05:00 UTC on 6 Feb). The timing is corrected, thanks to Bryan Williams, who noted the original timing was based on CST instead of EST. The corrected result is Chisquare 21893 on 21600 df, for p = 0.080 and Z = 1.407.
The following graph is a visual display of the statistical result. It shows the second-by-second accumulation of small deviations of the data from what’s expected. Our prediction is that deviations will tend to be positive, and if this is so, the jagged line will tend to go upward. If the endpoint is positive, this is evidence for the general hypothesis and adds to the bottom line. If the endpoint is outside the smooth curve showing 0.05 probability, the deviation is nominally significant. If the trend of the cumulative deviation is downward, this is evidence against the hypothesis, and is subtracted from the bottom line. For more detail on how to interpret the results, see The Science and related pages, as well as the standard caveat below.
It is important to keep in mind that we have only a tiny statistical effect, so that it is always hard to distinguish signal from noise. This means that every
success might be largely driven by chance, and every
null might include a real signal overwhelmed by noise. In the long run, a real effect can be identified only by patiently accumulating replications of similar analyses.