The CardBoard
The Shot, Part II - Printable Version

+- The CardBoard (https://thecardboard.org/board)
+-- Forum: C-House! (https://thecardboard.org/board/forum-4.html)
+--- Forum: The CardBoard (https://thecardboard.org/board/forum-5.html)
+--- Thread: The Shot, Part II (/thread-6726.html)

Pages: 1 2 3

Re: The Shot, Part II - BostonCard - 02-11-2014

(02-11-2014, 05:21 PM)burger link Wrote:[quote author=Boston Card link=topic=9542.msg83734#msg83734 date=1392162270]I don't know how you can accuses Monty of systematic underperformance when he also took a team to the Final 4.  The NCAA tourney (and, in fact, any one and done tourney) is going to have its share of upsets.  To the extent that we were upset victims during the latter stages of Monty's career at Stanford is due to the fact that we were frequently a higher seed.
I can't recall exactly where I saw this, but near the end of Monty's tenure, ESPN or SI or someone did an analysis of how big-name coaches had done in the Tourney relative to their seeds.  If you were a 2, breaking even would be losing in the Elite 8, losing earlier would be a negative, and making the Final 4 would be bonus points.  Monty came out towards the bottom of the rankings.  And I think that was before the 2004 fiasco (which I was present for--sigh).

Also, his UC East Bay record in the Tourney is so-so:
2009: lost in the 1st round as a 7 seed
2010: lost in the 2nd round as an 8 seed
2012: lost the play-in game as a 12 seed vs. another 12
2013: better--as a 12 seed, beat the 5 in the first round, lost to the 4 in round two

Of course, that's 4 more appearances than we've made since 2009.
[/quote]

How exactly does that prove anything.  Aside from the problem that you are trying to draw conclusions based on a sample size of 4, you have the following:
2009: 7 seed losing to a 10 seed; A 10 seed has won 36% of the time.
2010: 8 seed losing to a 1 seed in the second round (first off, an eight seed wins its first round matchup less than 50% of the time; despite being the better seed, they advance only 46% of the time, so Monty gets credit).  Eight seeds advance to the sweet 16 only 10% of the time, so hardly a surprise.
2012: 12 seed versus a 12 seed; should be about even odds, right?
2013: 12 seed beating a 5 seed happens 31.5% of the time; they make it past the second round 15% of the time.

So, in four outings, once he beat the expected (2013), once he was beaten when he was expected to win (2009), and in two games when the chances of advancing were about 50/50, he won one and lost one. His two appearances in the second round he was a decided underdog and lost.

And for the assessment of "breaking even", here is the problem: If you are a two seed, you have three chances to fall shy and (if you win those three) one chance to exceed your expectations.  Compare to a 10 seed, which cannot possibly fall shy compared to expectations.  Thus, a coach who is a 10 seed four times and goes 1-3 has "exceeded expectations", while a coach who is, say, a 4 seed four times and goes 7-4 has fallen shy of expectations.

This site compiles the probabilities of advancing to each round given a particular seed: http://www.collegehoopsnet.com/ncaa-tournament-odds-a-seed-advancing-166169

You will see that a number one seed survives the elite eight 41% of the time; thus counterintuitively, a number one seed that makes the final four has exceeded the odds (not merely done as well as expected).  Likewise, #3 seeds advance past the second round only 47.8% of the time, so a #3 seed that makes the sweet sixteen has actually beaten the odds.

BC

Re: The Shot, Part II - dabigv13 - 02-11-2014

The eternal Monty debate.....

BC, you may be right that a #1 seed getting to the FF is still perhaps beating the odds, but being a #2 seed, #1,#1,#8,#4, and #1 and only getting past the 1st weekend once is DEFINITELY performing below your seed.

I'm of the opinion that without Monty we probably wouldn't have gotten the regular season wins to earn those seeds in the first place, and in my ideal world Monty would've been the Stanford bball coach for life, but the evidence is pretty clear that we were not a great tournament team under Monty (still better to be a not great NCAA tournament team than a not great no-tournament team obviously).

Re: The Shot, Part II - BostonCard - 02-11-2014

I'm only continuing this because the statistics interests me, not because I'm trying to argue anything about our former coach.

First, there is some selective data going on. 

In 1995 we made the second round despite being a 10 seed; 36% probability
In 1996 we made the second round despite being a 9 seed (we exceeded our seeding, but not our probability); 54% probability
In 1997 we made the sweet sixteen despite being a 6 seed; 36% probability
In 1998 we made the final four despite being a 3 seed; 13% probability

Not surprisingly, we had a tendency to exceed our seed when we had low seeds.  When we were seeded better, we tended to underperform our seedings
In 1989 we were a three seed and lost in the first round (16% probability)
In 1999 we were a two seed and lost in the second round (37% probability)
In 2000 we were a one seed and lost in the second round (13% probability)
In 2001 we were a one seed and lost in the elite eight (29% probability)
In 2003 we were a four seed and lost in the second round (57% probability)
In 2004 we were a one seed and lost in the second round (13% probability)

Let's call 1992 (12 seed losing in the first round), 1996 (9 seed losing in the second round), 2001 (8 seed losing in the second round), and 2003 (4 seed losing in the second round) to be doing about what was expected statistically.

During Montgomery's tenure, then, we exceeded expectations three times (1995, 1997, 1998) met expectations three times (1992, 1996, 2001), and missed expectations four times (1989, 2000, 2001, and 2004).  It is really hard to say that Monty systematically missed expectations.

BC

Re: The Shot, Part II - burger - 02-11-2014

Two #1 seeds and a #2 seed lost in the second round.  That's terrible.  Yes, there was the elite 8 team, but having 75% of your top-seeded teams fail to reach the second round is ignominious.  I'd wager that no other coach has such as a bad record with 1 or 2 seeds. 

Like Boston Card pointed out, we overachieved a few times, but so have other coaches.  Whoever did that quantitative analysis (which I haven't looked for--it's probably still out there someplace if anyone cares to search) concluded that Monty was subpar in the Tourney.  I agree.

Re: The Shot, Part II - BostonCard - 02-11-2014

And because I am a statistics geek, I decided to use the probabilities given in the table to simulate what would happen if we could relive the 12 NCAA tournaments that Monty was in 10,000 times (the magic of computers!)

First, given our distribution of seeds, we slightly underperformed.  In my simulations, we win at least one national championship 45% of the time (and 8% of the time we win 2 championships, 1% we win three championships and 6/10,000 times we win 4 national championships!).  The mean number of national championships we win across the simulations is 0.57.
In an additional 23% of simulations our best performance is getting to the national championship game, and another 23% of simulations our best performance is getting to the final four at least once.

In addition, the average number of total wins across all the simulations is 21.  Monty had a 16-12 record in the tournament.  In my simulations, 14% of the time we have 16 or fewer total wins.  What this tells me is that although Monty nominally underperformed his seeding come NCAA tournament time, the deviation from what would have been expected given the probabilities, the underperformance is not beyond what might have been observed by chance.

Here's a histogram of the number of wins we have in each simulation:

[Image: skitch.png]

The arrow points to how many wins (16) Monty had.  Worse than expected, but within reason statistically.

BC

Re: The Shot, Part II - BostonCard - 02-11-2014

(02-11-2014, 08:05 PM)burger link Wrote:Two #1 seeds and a #2 seed lost in the second round.  That's terrible.  Yes, there was the elite 8 team, but having 75% of your top-seeded teams fail to reach the second round is ignominious.  I'd wager that no other coach has such as a bad record with 1 or 2 seeds. 

Like Boston Card pointed out, we overachieved a few times, but so have other coaches.  Whoever did that quantitative analysis (which I haven't looked for--it's probably still out there someplace if anyone cares to search) concluded that Monty was subpar in the Tourney.  I agree.

Getting to the final four as a #3 seed is about as big a surprise to the upside as losing in the second round as a #1 seed.  A #2 seed losing in the second round is actually pretty common; it's about as common as getting to the sweet sixteen as a six seed.  By simulation, you would not be able to say that Monty's results were so out of whack that they could not be explained by mildly bad luck.

BC

Re: The Shot, Part II - burger - 02-11-2014

BC, love the stats, but my original comment was that Monty was worse than other comparable coaches that have had many high-seeded teams.  So, the real question is: how does Monty compare to coach K or Tom Izzo or Boeheim or <other lauded coach>?  I don't expect you or anyone else to crunch the numbers, but I have trouble imagining that Monty comes out looking good in those comparisons.

Re: The Shot, Part II - BostonCard - 02-11-2014

You would have to compare it to the entire universe of coaches, not just the ones who are household names (in part because they've been especially successful).  For what it's worth Duke has outperformed expectations; simulations would show a median number of wins of 72, while Mike Krzyzewski has actually won 86 tournament games (this is almost statistically significant; the probability of seeing 86 or more wins is about 5.5%).  Most impressively, he has won 8 national championships; in 10,000 simulations, that only happened 7 times.  But there is a reason that Mike Krzyzewski is a hall of fame coach.

By the way, to give you an idea of a comparable coach to Monty, look at Mark Few of Gonzaga.  Based on his championship seeding, he would have expected to get about 17.4 wins; he actually got 15.  He never made it to the elite eight, though teams with comparable profiles would be expected to make the elite eight 96% of the time and the final four 72% of the time.  Twice he's been a 1 or 2 seed, and neither time did he get out of the second round (OTOH, he also made it to the sweet sixteen as a 10 and 12 seed, as well as when he was a 3 and a 4 seed).  Like Monty, he exceeded his seed a couple times, and fell flat a couple times, but on the balance his teams have nominally underperformed their seeding.

BC

Re: The Shot, Part II - BostonCard - 02-11-2014

By the way, this Washington Post site has been invaluable in compiling the seeds and results by team:

http://apps.washingtonpost.com/sports/apps/live-updating-mens-ncaa-basketball-bracket/

I'd be happy to look up anyone.

BC

Re: The Shot, Part II - Papa John - 02-11-2014

(02-11-2014, 09:31 PM)Boston Card link Wrote:You would have to compare it to the entire universe of coaches, not just the ones who are household names (in part because they've been especially successful).  For what it's worth Duke has outperformed expectations; simulations would show a median number of wins of 72, while Mike Krzyzewski has actually won 86 tournament games (this is almost statistically significant; the probability of seeing 86 or more wins is about 5.5%). 

BC, please forgive me for asking, but how can you claim almost statistical significance in this case? You are not taking random samples from a population, you actually know the entire population of data. So aren't we dealing with descriptive rather than inferential probabilities?

And before you laugh at me, let me warn you that I have a doctorate...in Music (OK, go ahead and laugh).

Re: The Shot, Part II - BostonCard - 02-11-2014

Not bad for a musician.  ;)

You are correct that we can chose to describe Montgomery's performance using descriptive statistics, which is why I have said that he has nominally underperformed.  But there is also an element of inferential statistics involved, in that Monty's performance could be considered a sample (where the population is a hypothetically very large number of tournament trips). We are trying to answer the question of whether Monty's performance could be explained by chance or whether we think it is due to something intrinsic in his coaching style.  To give you an idea, suppose we were a casino testing a pair of dice to see if they were weighted.  Yeah, we could use descriptive statistics to say that 11 comes up 9% of the time (you would expect it to come 2/36 or 7.7% on average).  Whether the excess of 11 rolls is due to chance or a flaw of the dice is something that can be answered statistically.  Likewise you can try to answer statistically whether Monty's underperformance is due to bad luck, or if he is just a bad tournament coach.

BC

Re: The Shot, Part II - Papa John - 02-11-2014

OK, then let me ask you about this. From 1998 to 2011 the NFC won the coin toss in the Super Bowl every time. If I am not mistaken, the probability of that happening is 1/2^14 or 0.006%. So this would fall far below any alpha level used in behavioral research. But we wouldn't say that the 14-year run is statistically significant, even though it is extracted from a larger population of coin tosses over 48 Super Bowls, would we? Or if we would claim statistical significance, what's the point (other than claiming that the NFC must have cheated during that time period)? That 14-year run has no bearing on future coin tosses.

Re: The Shot, Part II - BostonCard - 02-11-2014

Well, it is not really a valid hypothesis because the data was cherry picked.  And nobody made a serious accusation of the NFC systematically cheating.  But, hypothetically, if systematic NFC cheating had been an issue, you could test the hypothesis that the NFC disproportionately won the coin toss (but again, you would need to use non-cherry picked data, which is the data on all the Super Bowls).  [As an aside, note the tendency to cherry pick data by some people here; at least one poster wanted to consider only the data after we made the final four].  On the other hand, people are suggesting, and I am quoting, that "Monty the Traitor can't win the big games in the tourney and it's time for both parties to move on".  That is a testable hypothesis; the null hypothesis is that Monty's tournament underperformance can be attributed to chance alone; the alternative hypothesis is that "Monty the Traitor can't win big games" (or, statistically speaking, that we can disprove the null hypothesis to whatever alpha floats your boat).  "Can't win" does imply a future outcome (and "can't" refers to an indefinite time horizon), so inferential statistics are warranted.  Because if our NCAA performance really was due to something intrinsic to Mike Montgomery, then that would have been an argument for both parties moving on; otherwise, it might have been an argument for patience.

Ultimately, it doesn't matter; Monty left for Golden State, and eventually for Cal.  I am thankful for what he did while he was here, but I don't really want to resuscitate a long dead horse. I'm only interested in the statistical question (so it would be just as reasonable to substitute Mark Few for Monty), and really to answer the question as to whether you can really draw conclusions about a coach from tournament performance. And I give both a descriptive answer, "First, given our distribution of seeds, we slightly underperformed." and an inferential one, "the underperformance is not beyond what might have been observed by chance." (or, put more succinctly, "we underperformed, but I wouldn't read too much into Monty's talents as a coach based on the results")

BC

Re: The Shot, Part II - Papa John - 02-12-2014

Thanks for your thoughtful replies, BC! I'll go back to my music now. Only need to count to four (sometimes three)...

Re: The Shot, Part II - FarmBoy - 02-12-2014

I won't argue stats with someone who's obviously much more versed than myself, but overall, it seems MM's sample is too small to make too many statistically based conclusions. However, as a fan, it was a disheartening trend. And reconsidering the topic, the goal isn't really to "outplay your seed." The goal is to win the NCAA (or at least get to the FF). Outplaying your seed as a #8 is nice, but it doesn't really get you any closer to the FF unless you truly defy the odds. What you need is a 1-4 seed and to play up to your potential. On a small sample, it appears that MM was not able to do that.

Of course, I would prefer MM's regular season excellence followed by an NCAA fizzle to the current regime. But given our current success in football, I'm hopeful we can have our cake and eat it too, in basketball as well.

Re: The Shot, Part II - GoodGrief - 02-12-2014

I think MM's general underperformance in the NCAA Tourney was due to a few things:

1. MM always had his team prepared and ready to win the next game. This resulted in us winning a lot of regular-season games which got us into the dance.

2. MM always had his team prepared and ready to win the next game. This resulted in us sometimes playing safe-and-steady over higher-risk/higher-upside, so we would plateau instead of peaking. See: Tony Giovacchini and Julius Barnes. (interesting--just saw that Julius is now the head coach at SF's Academy of the Arts.).

3. MM made the best of his talent, which often times was big, slow, and bruising. Our beat-and-bash technique worked great, but sometimes in the Dance, we'd just run into some really fast guards that we just had no answer for.

4. There's that thing about Pac-10 ref tendencies to call ticky-tack fouls. It's been said that Pac-10 players get used to playing with whistle-happy refs, and then aren't used to the Tourney where the refs let allow a lot more contact.

I do wish we had MM instead of those yutzes across the bay.

Re: The Shot, Part II - Leftcoast - 02-13-2014

Yeah, that awful Mike Montgomery.  All he brought us were PAC 12 titles, NCAA invites every year, #1 rankings and #1 tourney seeds, multiple takedowns of other #1 ranked teams, unbeaten seasons at Maples in front of adoring crowds and Stanford's only final four appearance in my lifetime.

What a clown.

I miss him.

Re: The Shot, Part II - shinsengumi - 02-13-2014

(02-13-2014, 01:58 AM)Leftcoast link Wrote:Yeah, that awful Monty the Traitor.  All he brought us were PAC 12 titles, NCAA invites every year, #1 rankings and #1 tourney seeds, multiple takedowns of other #1 ranked teams, unbeaten seasons at Maples in front of adoring crowds and Stanford's only final four appearance in my lifetime.

What a clown.

I miss him.

This.

That 2003-04 season remains etched in my memory despite the early tourney exit.

Re: The Shot, Part II - Papa John - 02-13-2014

In my lifetime, the Monty era constituted the glory days. Not the perfect days, but glory days nonetheless. For every anguishing event like the game on March 20, 2004 (the only time I've had a sports-induced migraine on my birthday), there were more many more moments like Robinson's/Lottich's miracle shots versus UA/WSU, beating Duke, beating Kansas, making the Final Four, and so on.

I also believe that the Harbaugh/Shaw era constitutes the glory days for Stanford football in my lifetime. As with the Monty era, I hope that I enjoy the ride much more often than I curse the potholes.

Re: The Shot, Part II - GoodGrief - 02-13-2014

(02-13-2014, 01:17 PM)Papa John link Wrote:In my lifetime, the Monty era constituted the glory days. Not the perfect days, but glory days nonetheless. For every anguishing event like the game on March 20, 2004 (the only time I've had a sports-induced migraine on my birthday), there were more many more moments like Robinson's/Lottich's miracle shots versus UA/WSU, beating Duke, beating Kansas, making the Final Four, and so on.

Oh that victory over #1 (i think) Duke brings back such memories (actually I think that happened twice? too lazy to look it up). Anyway, the turning point of that game was Nate James going up for a dunk and getting completely rejected by a Stanford guy who appeared out of nowhere. The announcers initially called it as a rejection by one of the Collins twins. And then on the replay, they were like, "Wait, that was LITTLE Julius Barnes!!!" Julius went on to lead us to a brobdingnagian come-from-a-ton-behind victory.

Ahh, Julius, I loved that guy.

http://www.youtube.com/watch?v=hUXuxIskkaE&list=PLq4wDKnWPKipHJb1s0xVumx0aCAhdyFJQ&index=1#t=05m10s