[CTcard]

[quote author=CTcard link=topic=18293.msg217258#msg217258 date=1512533847]I have to admit I was wondering that as I was writing.

I believe that awhile back, WIM looked at season to season consistency and noted Stanford was not.

I don't believe WiM compared us to other programs, which is really what you want to do. Anyway, giant table incoming, here's every programs' average offensive game efficiency (per BCF Toys, so you have to accept that their method is capturing game efficiency reasonably) and the standard deviation between games. I bolded Stanford so we'd stand out (also I'm going to break this up into two posts, since it exceeded the character limit...):
[/quote]

Thanks for the effort.


I'll have to think a bit about what I think these numbers really mean.
One issue that comes to mind is whether standard deviation is a good measure of the kind of occasional face-plants I am trying to analyze; particularly if the underlying sample doesn't follow a normal distribution and in the presence of very small samples.
So, how does a bimodal distribution with two small spreads show up versus a single broad distribution?
Not sure if that is significant or not.


Glancing at the BCFtoys chart, I see Stanford with an OFEI average of 3.01 had one game with a negative OFEI - which seems very rare among better offenses. (In fact, Stanford's -0.16 vs OSU was the third worst OFEI I saw in the chart of all BCS games this year). On the other hand, Stanford's next worst games were 1.75 and 2.49, which don't seem so out of the ordinary.


[And off topic but interesting - by OFEI, Stanford's offensive performances in the two $C games were identical and both just over our average. Didn't feel that way to me watching.]

[CTcard]

[quote author=CTcard link=topic=18293.msg217258#msg217258 date=1512533847]I have to admit I was wondering that as I was writing.

I believe that awhile back, WIM looked at season to season consistency and noted Stanford was not.

I don't believe WiM compared us to other programs, which is really what you want to do. Anyway, giant table incoming, here's every programs' average offensive game efficiency (per BCF Toys, so you have to accept that their method is capturing game efficiency reasonably) and the standard deviation between games. I bolded Stanford so we'd stand out (also I'm going to break this up into two posts, since it exceeded the character limit...):
[/quote]

Thanks for the effort.


I'll have to think a bit about what I think these numbers really mean.
One issue that comes to mind is whether standard deviation is a good measure of the kind of occasional face-plants I am trying to analyze; particularly if the underlying sample doesn't follow a normal distribution and in the presence of very small samples.
So, how does a bimodal distribution with two small spreads show up versus a single broad distribution?
Not sure if that is significant or not.


Glancing at the BCFtoys chart, I see Stanford with an OFEI average of 3.01 had one game with a negative OFEI - which seems very rare among better offenses. (In fact, Stanford's -0.16 vs OSU was the third worst OFEI I saw in the chart of all BCS games this year). On the other hand, Stanford's next worst games were 1.75 and 2.49, which don't seem so out of the ordinary.


[And off topic but interesting - by OFEI, Stanford's offensive performances in the two $C games were identical and both just over our average. Didn't feel that way to me watching.]