2 Batting

TODO: INTRODUCE STAR FORMULAS. TABLE OF ONLY VARIABLES ASSOCIATED WITH STARS MAYBE. SAME FOR PITCHING

PLEASE NOTE: p.BY IS A CALCULATION THAT ADJUSTS P-VALUES WHEN THERE ARE MANY MANY P-VALUES BEING USED THIS ADJUSTMENT IS BEING MADE SINCE THERE ARE HUNDREDS OF COMBINATIONS OF STLATS/STATS/WHATEVER

Somebody thought it was a good idea to calculate baseball player statistics for blaseball players.

An examination of the batting statistics produced via SIBR doing a great job will now begin.

2.1 Batting STATS versus STLATS

The correlations you are about to see are calculated using a method referred to as Kendall’s \(\tau\) (tau). Kendall was some fancy mathstats person that did something and people liked it.

The basic premise of this \(\tau\) value is that it measures the proportion (sort of…) of times that an increase in the \(x\) variable occurred with a increase in \(y\) (positve \(\tau\)) or decrease in \(y\) (negative \(\tau\)).

The closer to 1 or -1, the stronger the relation ship.

2.1.1 Batting Correlations.

2.1.2 “Strong” Correlations \((p < 0.0001)\)

Note, the cutoff criteria \(p < 0.0001\) is to ensure that there is very little chance that any of the listed relationships are spurious given that out of 532(?) different relations, one might have appeared by chance.

2.1.3 Graphs of Batting STATS versus STLATS

2.2 Batting STATS versus STATS

2.2.1 Correlations

Cooking up some more correlations.

2.2.2 “Strongly” Correlations (\(p < 0.0001\))

2.2.3 Graphs of Batting STATS versus Themselves

Here is all the plots of STATS versus STATS.