Speaking as a Jets fan: the true value of Glenn’s strategy is to minimize the chance that any fan has to see this horrible team play in overtime. Glen is both an analytics genius and a true humanitarian.
> As we discussed in class, a major part of the cost-benefit framework is transparency so all stakeholders can examine the assumptions that go into computing the ratio of costs to benefits. A secret computer program that argues for maximum aggression at all times doesn’t fit the bill.
Wouldn't a similar argument apply to any market price? It's a black box. Who knows what's in it?
I feel guilty offering two digits of precision, when the relative margin of error (however you want to define it) is almost always >10%. But i can at least prohibit my students from reporting three. And that's in a formal model with heaps of data.
Considering the "infinite complexity" of going for it on 4th down or going for two, how much sense does it make to compile and report descriptive summary stats on failure/success? Much less use those descriptions as probabilistic predictions?
Speaking as a Jets fan: the true value of Glenn’s strategy is to minimize the chance that any fan has to see this horrible team play in overtime. Glen is both an analytics genius and a true humanitarian.
> As we discussed in class, a major part of the cost-benefit framework is transparency so all stakeholders can examine the assumptions that go into computing the ratio of costs to benefits. A secret computer program that argues for maximum aggression at all times doesn’t fit the bill.
Wouldn't a similar argument apply to any market price? It's a black box. Who knows what's in it?
I feel guilty offering two digits of precision, when the relative margin of error (however you want to define it) is almost always >10%. But i can at least prohibit my students from reporting three. And that's in a formal model with heaps of data.
I don’t know if our dumbass OC nick caley (Texans) subscribes to this mentality but I wouldn’t be surprised.
Considering the "infinite complexity" of going for it on 4th down or going for two, how much sense does it make to compile and report descriptive summary stats on failure/success? Much less use those descriptions as probabilistic predictions?