Loading ...
Sorry, an error occurred while loading the content.

Re: Well, admittedly the name Amos Tversky didn't ring a bell, so I ...

Expand Messages
  • Mike G
    ... was ... I m with Carlos here. I d go a bit further and say, if research shows players shooting to be no more variable than flipped coins, that research
    Message 1 of 27 , Dec 29, 2003
    • 0 Attachment
      --- In APBR_analysis@yahoogroups.com, "carlos12155"
      >... But the "hot hand" is a psychological effect, isn't it? What I
      was
      > trying to say was that some players should be streaky and research
      > should show it.

      I'm with Carlos here. I'd go a bit further and say, if research
      shows players' shooting to be no more variable than flipped coins,
      that research is wack.
    • igor eduardo küpfer
      ... From: Mike G To: Sent: Monday, December 29, 2003 9:00 AM Subject: [APBR_analysis] Re: Well,
      Message 2 of 27 , Dec 29, 2003
      • 0 Attachment
        ----- Original Message -----
        From: "Mike G" <msg_53@...>
        To: <APBR_analysis@yahoogroups.com>
        Sent: Monday, December 29, 2003 9:00 AM
        Subject: [APBR_analysis] Re: Well, admittedly the name Amos Tversky didn't
        ring a bell, so I ...


        > --- In APBR_analysis@yahoogroups.com, "carlos12155"
        > >... But the "hot hand" is a psychological effect, isn't it? What I
        > was
        > > trying to say was that some players should be streaky and research
        > > should show it.
        >
        > I'm with Carlos here. I'd go a bit further and say, if research
        > shows players' shooting to be no more variable than flipped coins,
        > that research is wack.
        >

        I'm trying to read that comment in such a way which doesn't say "screw the
        facts, I just KNOW I'm right," but failing. It's true that research is much
        easier when you can just assume your conclusion, and then drum up evidence
        in support while ignoring anything that contradicts it, but it doesn't seem
        like a promising direction for future research.

        ed
      • Mike G
        ... say screw the ... ..Sigh... I guess I was striving for a concise comment that expressed what I thought should be obvious. People aren t robots, and they
        Message 3 of 27 , Dec 29, 2003
        • 0 Attachment
          --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
          <igorkupfer@r...> wrote:
          >
          > ----- Original Message -----
          > From: "Mike G" <msg_53@h...>
          > > ... if research shows players' shooting to be no more variable
          >than flipped coins,
          > > that research is wack.
          > >
          >
          > I'm trying to read that comment in such a way which doesn't
          say "screw the
          > facts, I just KNOW I'm right," ...


          ..Sigh...

          I guess I was striving for a concise comment that expressed what I
          thought should be obvious. People aren't robots, and they aren't
          dice.

          Perhaps a player can experience a Very Hot Hand, and pour in 15
          points in a quarter, and end up shooting 10-22 for the game. Maybe
          he attracted defensive adjustments, or took it too far and attempted
          wild shots. "Hot" may not completely come through in the box score.

          DeanO flatly stated that Mr. Tversky had shown the Hot Hand does not
          exist. Then he described his own personal experience with it. I
          think maybe there's a contradiction.

          Some people have never played basketball; Sometimes I think I can
          tell that from their opinions on the game. When someone is
          convinced by a quantitative study that defies first-hand experience,
          he may be throwing out evidence that is more substantial than that
          which he is accepting.

          (So much for a concise comment.)
        • sultanoswat@yahoo.com
          ... experience, ... Like that the earth isn t the center of the universe? Five hundred years ago people would have laughed at the notation of a rotating
          Message 4 of 27 , Dec 29, 2003
          • 0 Attachment
            > When someone is
            > convinced by a quantitative study that defies first-hand
            experience,
            > he may be throwing out evidence that is more substantial than that
            > which he is accepting.
            >
            > (So much for a concise comment.)

            Like that the earth isn't the center of the universe? Five hundred
            years ago people would have laughed at the notation of a rotating
            earth, which defies first-hand experience (except of course for a
            couple of astronauts).

            Personally, I would love to believe in a force or psychological trait
            that allows players at the highest levels of competition to improve
            their abilities at certain times. In fact these abilities are always
            granted post-performance, which seems to be reading into something
            that isn't there. Not only have I not seen any studies that prove the
            hot hand, but have seen numerous studies that do the opposite, in
            both baseball & basketball. Until I see some proof, I'm liable to
            believe the opposite.

            Mike
          • carlos12155
            ... There are, in fact, a good number of cases when first hand experience contradicted preliminary research and first hand experience was right. The Shaq
            Message 5 of 27 , Dec 30, 2003
            • 0 Attachment
              --- In APBR_analysis@yahoogroups.com, sultanoswat@y... wrote:
              >
              > > When someone is
              > > convinced by a quantitative study that defies first-hand
              > experience,
              > > he may be throwing out evidence that is more substantial than that
              > > which he is accepting.
              > >
              > > (So much for a concise comment.)
              >
              > Like that the earth isn't the center of the universe? Five hundred
              > years ago people would have laughed at the notation of a rotating
              > earth, which defies first-hand experience (except of course for a
              > couple of astronauts).

              There are, in fact, a good number of cases when first hand experience
              contradicted preliminary research and first hand experience was right.
              The "Shaq test" mentioned often here is an example. If some ratings
              showed you that Charlie Ward is the best point guard in the league
              you would think that the ratings were wrong, right?


              > Personally, I would love to believe in a force or psychological trait
              > that allows players at the highest levels of competition to improve
              > their abilities at certain times. In fact these abilities are always
              > granted post-performance, which seems to be reading into something
              > that isn't there. Not only have I not seen any studies that prove the
              > hot hand, but have seen numerous studies that do the opposite, in
              > both baseball & basketball. Until I see some proof, I'm liable to
              > believe the opposite.

              Personally I believe in a force or psychological trait that makes some
              players more inconsistent than other players.



              > Mike
            • Mike G
              ... I guess there will always be people who laugh at common sense. The Earth s shadow crosses the moon. The moon passes between us and the Sun. Egocentrism
              Message 6 of 27 , Dec 30, 2003
              • 0 Attachment
                --- In APBR_analysis@yahoogroups.com, sultanoswat@y... wrote:
                > ...the earth isn't the center of the universe? Five hundred
                > years ago people would have laughed at the notation of a rotating
                > earth, which defies first-hand experience (except of course for a
                > couple of astronauts).

                I guess there will always be people who laugh at common sense. The
                Earth's shadow crosses the moon. The moon passes between us and the
                Sun. Egocentrism nonetheless keeps people at the center of their
                universe.

                >
                > Personally, I would love to believe in a force or psychological
                trait
                > that allows players at the highest levels of competition to
                improve
                > their abilities at certain times. In fact these abilities are
                always
                > granted post-performance, which seems to be reading into something
                > that isn't there.

                It seems intuitively clear to me that Certain players have this
                trait much more strongly than others do.


                > Not only have I not seen any studies that prove the
                > hot hand, but have seen numerous studies that do the opposite, in
                > both baseball & basketball. Until I see some proof, I'm liable to
                > believe the opposite.
                >
                > Mike

                I for one would doubt it's possible to Prove the Hot Hand. And I
                would wonder about someone who would attempt such a proof.

                Proving the Opposite is quite as impossible for me to fathom. Even
                if you have play-by-play details, you don't know if a guy was
                getting wide-open looks, or if he was just unstoppable.

                You make a valid point, that in post-performance one could say, "we
                thought he was hot, but he wasn't", or "he got hot and stayed hot",
                for example. But as an operational definition, I'm getting the ball
                to the guy who Seems to be hot.
              • Mike G
                ... Should have said: .. to the person who Seems to be hot. There s a lot of anecdotal evidence that certain players enhance their teammates performance; or
                Message 7 of 27 , Dec 30, 2003
                • 0 Attachment
                  Correction:

                  --- In APBR_analysis@yahoogroups.com, "Mike G" <msg_53@h...> wrote:
                  > ... I'm getting the ball
                  > to the guy who Seems to be hot.

                  Should have said: .. to the person who Seems to be hot.

                  There's a lot of anecdotal evidence that certain players enhance
                  their teammates' performance; or detract from them.

                  Getting into the flow of a game, you might deliberately feed the
                  ball to a player that you Know From Experience may well get_it_going
                  if shown some confidence.

                  On that level, a team may actually Prompt a player to get the Hot
                  Hand. It won't work every single time, but it's still a worthwhile
                  goal if it works often enough.

                  Reggie Miller may only take 5 shots thru 3 quarters. Then in the
                  4th quarter, he starts to flex. Not that he invariably becomes hot,
                  but he often does.

                  It's good for a team to recognize that a player is going good, or
                  even that he Might.


                  I wonder what percentage of NBA players would accept the conclusion
                  of studies purporting to "show the hot hand does not exist" ?
                • igor eduardo küpfer
                  ... From: Mike G To: Sent: Monday, December 29, 2003 2:50 PM Subject: [APBR_analysis] Re: Well,
                  Message 8 of 27 , Dec 30, 2003
                  • 0 Attachment
                    ----- Original Message -----
                    From: "Mike G" <msg_53@...>
                    To: <APBR_analysis@yahoogroups.com>
                    Sent: Monday, December 29, 2003 2:50 PM
                    Subject: [APBR_analysis] Re: Well, admittedly the name Amos Tversky didn't
                    ring a bell, so I ...


                    <snip>

                    > I guess I was striving for a concise comment that expressed what I
                    > thought should be obvious. People aren't robots, and they aren't
                    > dice.
                    >

                    Nobody says that. What some say is that dice produce results that look an
                    awful lot like those produced by the players being studied.

                    > Perhaps a player can experience a Very Hot Hand, and pour in 15
                    > points in a quarter, and end up shooting 10-22 for the game. Maybe
                    > he attracted defensive adjustments, or took it too far and attempted
                    > wild shots. "Hot" may not completely come through in the box score.
                    >
                    > DeanO flatly stated that Mr. Tversky had shown the Hot Hand does not
                    > exist. Then he described his own personal experience with it. I
                    > think maybe there's a contradiction.
                    >

                    I can't believe Tversky would ever say that. In the Gilovich et al. paper,
                    he and his colleagues went to some lengths to detect a hot hand, and found
                    nothing (well, they found one cold hand). There is a big difference between
                    saying something is undetectable and saying it doesn't exist. May I add here
                    that taking the position that something doesn't exist is the default
                    position in science, until existence has been documented.

                    Further, the point of Gilovich at al. was that since these streaks are if
                    not nonexistent, then extremely difficult to detect, why do so many people
                    see them so often? Answer: the bunching of hits and misses is a cognitive
                    illusion, like seeing a face in the clouds or the likeness of Jesus on a
                    cinnamon bun.

                    > Some people have never played basketball; Sometimes I think I can
                    > tell that from their opinions on the game. When someone is
                    > convinced by a quantitative study that defies first-hand experience,
                    > he may be throwing out evidence that is more substantial than that
                    > which he is accepting.
                    >

                    This is the kind of thing that drives me crazy. The "you wouldn't know
                    because you aren't a player defense." Ignoring for now whether I am a
                    player, nobody is denying your first-hand experience. We are simply saying
                    that it means something different than you think it means. You think it
                    means that your ability to hit a shot is higher than it is in non-hot hand
                    situations. I think it means that human pattern-detecting software is very
                    sensitive, and is very likely to see meaningful patterns where they do not
                    exist.

                    (Thomas Gilovich's book "How We Know What Isn't So" describes many examples
                    of mental "false positives," like people who believe that couples who cannot
                    have biological children and subsequently adopt are more likely to then
                    conceive a baby than couples who can't conceive and don't adopt. The
                    phenomenon does not exist, of course, and it is of great interest to
                    cognitive psychologists like Gilovich to ask why people believe in something
                    when there is no evidence to its existence -- thus, his interest in the hot
                    hand.)

                    ed
                  • harlanzo
                    ... know ... am a ... simply saying ... think it ... hot hand ... is very ... they do not ... Doesn t the existence of hot hand really depend on definining
                    Message 9 of 27 , Dec 30, 2003
                    • 0 Attachment
                      --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                      <igorkupfer@r...> wrote:

                      > This is the kind of thing that drives me crazy. The "you wouldn't
                      know
                      > because you aren't a player defense." Ignoring for now whether I
                      am a
                      > player, nobody is denying your first-hand experience. We are
                      simply saying
                      > that it means something different than you think it means. You
                      think it
                      > means that your ability to hit a shot is higher than it is in non-
                      hot hand
                      > situations. I think it means that human pattern-detecting software
                      is very
                      > sensitive, and is very likely to see meaningful patterns where
                      they do not
                      > exist.

                      Doesn't the existence of hot hand really depend on definining your
                      terms? Hot Hand might assume player x shoots the same way all the
                      time and that sometimes, based on a feeling you just
                      shoot "better." I don't think that exists. But I definitely think
                      there are times, based on either faitgue or concecntration, that a
                      person's shooting mechanics are more sound and shooting percentange
                      goes up. That's not hot hand (as I infer the definition to be) but
                      it definitely indicates that people shoot better in certain
                      scenarios.

                      >
                      > (Thomas Gilovich's book "How We Know What Isn't So" describes many
                      examples
                      > of mental "false positives," like people who believe that couples
                      who cannot
                      > have biological children and subsequently adopt are more likely to
                      then
                      > conceive a baby than couples who can't conceive and don't adopt.
                      The
                      > phenomenon does not exist, of course, and it is of great interest
                      to
                      > cognitive psychologists like Gilovich to ask why people believe in
                      something
                      > when there is no evidence to its existence -- thus, his interest
                      in the hot
                      > hand.)
                      >
                      > ed
                    • Dean Oliver
                      ... If I said that here, I didn t mean to. The book states it very much the way Ed does below -- that, if it exists, it doesn t seem to show up in the tests
                      Message 10 of 27 , Dec 30, 2003
                      • 0 Attachment
                        --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                        <igorkupfer@r...> wrote:
                        > > DeanO flatly stated that Mr. Tversky had shown the Hot Hand does not
                        > > exist. Then he described his own personal experience with it. I
                        > > think maybe there's a contradiction.

                        If I said that here, I didn't mean to. The book states it very much
                        the way Ed does below -- that, if it exists, it doesn't seem to show
                        up in the tests that Tversky looked for it.

                        Regardless, it always brings me back to, "If it exists or doesn't
                        exist, does it change the way you do compete against it or work with
                        it?" Instinctively, I'd say yes. Teams that sense a hot hand would
                        do more defensively against a guy to stop him. Teams that know they
                        have a hot shooter will keep feeding that person. The defensive
                        response would serve to hide any statistical evidence that it exists
                        (if defense can indeed stop a hot hand). The offensive one would also
                        probably serve to hide it because of the general rule that the larger
                        percentage of an offense a guy uses, the less efficient they become.
                        But do teams actually do these things? That's what I mentioned some
                        time ago as the kind of test it would be nice to do....

                        DeanO
                        www.basketballonpaper.com

                        > >
                        >
                        > I can't believe Tversky would ever say that. In the Gilovich et al.
                        paper,
                        > he and his colleagues went to some lengths to detect a hot hand, and
                        found
                        > nothing (well, they found one cold hand). There is a big difference
                        between
                        > saying something is undetectable and saying it doesn't exist. May I
                        add here
                        > that taking the position that something doesn't exist is the default
                        > position in science, until existence has been documented.
                        >
                        > Further, the point of Gilovich at al. was that since these streaks
                        are if
                        > not nonexistent, then extremely difficult to detect, why do so many
                        people
                        > see them so often? Answer: the bunching of hits and misses is a
                        cognitive
                        > illusion, like seeing a face in the clouds or the likeness of Jesus on a
                        > cinnamon bun.
                        >
                        > > Some people have never played basketball; Sometimes I think I can
                        > > tell that from their opinions on the game. When someone is
                        > > convinced by a quantitative study that defies first-hand experience,
                        > > he may be throwing out evidence that is more substantial than that
                        > > which he is accepting.
                        > >
                        >
                        > This is the kind of thing that drives me crazy. The "you wouldn't know
                        > because you aren't a player defense." Ignoring for now whether I am a
                        > player, nobody is denying your first-hand experience. We are simply
                        saying
                        > that it means something different than you think it means. You think it
                        > means that your ability to hit a shot is higher than it is in
                        non-hot hand
                        > situations. I think it means that human pattern-detecting software
                        is very
                        > sensitive, and is very likely to see meaningful patterns where they
                        do not
                        > exist.
                        >
                        > (Thomas Gilovich's book "How We Know What Isn't So" describes many
                        examples
                        > of mental "false positives," like people who believe that couples
                        who cannot
                        > have biological children and subsequently adopt are more likely to then
                        > conceive a baby than couples who can't conceive and don't adopt. The
                        > phenomenon does not exist, of course, and it is of great interest to
                        > cognitive psychologists like Gilovich to ask why people believe in
                        something
                        > when there is no evidence to its existence -- thus, his interest in
                        the hot
                        > hand.)
                        >
                        > ed
                      • Mike G
                        ... wrote: ... percentange ... but ... The factors that go into making a shot are actually infinite, so I won t attempt even a partial listing. The fact that
                        Message 11 of 27 , Dec 31, 2003
                        • 0 Attachment
                          --- In APBR_analysis@yahoogroups.com, "harlanzo" <harlanzo@y...>
                          wrote:
                          ....
                          > there are times, based on either fatigue or concentration, that a
                          > person's shooting mechanics are more sound and shooting
                          percentange
                          > goes up. That's not hot hand (as I infer the definition to be)
                          but
                          > it definitely indicates that people shoot better in certain
                          > scenarios.

                          The factors that go into making a shot are actually infinite, so I
                          won't attempt even a partial listing.

                          The fact that some shots "feel better", and that game totals are
                          whatever they end up, aren't contradictory. Defining "hot streaks"
                          by the game summary rather broadly misses, by my own definition.

                          A streak can last a month or a quarter -- or a minute, really. Nick
                          Anderson missed 4 FT, and went into a shooting funk for a couple of
                          years. (He was a .704 FT shooter stepping to the line, and would go
                          on to a .404 season.)


                          >
                          > > > --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                          > <igorkupfer@r...> wrote:

                          >> ... it is of great interest
                          > to
                          > > cognitive psychologists like Gilovich to ask why people believe
                          in
                          > something
                          > > when there is no evidence to its existence -- thus, his interest
                          > in the hot
                          > > hand.)

                          On the Hot Hand page, I found a serious Debunker. Trouble is, he's
                          trying to debunk some of the wrong things.

                          Now I'm as skeptical as the next guy. And I don't like bad science,
                          bad advice, bad statistics, etc. In fact I've campaigned against
                          such things.

                          On the debunking page, you'll find that the guy has picked
                          statistical tests that corroborate his hypotheses. And as I knew
                          before looking, they are _Way_Wack_.

                          If the burden of proof is on the person who sees what's obviously
                          there, I'm surprised. If you can't prove to Yourself it's there,
                          then I wish you luck.
                        • dlirag@hotmail.com
                          ... didn t ... Maybe ... attempted ... score. ... not ... paper, ... and found ... They found statistical evidence of a cold streak?
                          Message 12 of 27 , Jan 6, 2004
                          • 0 Attachment
                            --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                            <igorkupfer@r...> wrote:
                            >
                            > ----- Original Message -----
                            > From: "Mike G" <msg_53@h...>
                            > To: <APBR_analysis@yahoogroups.com>
                            > Sent: Monday, December 29, 2003 2:50 PM
                            > Subject: [APBR_analysis] Re: Well, admittedly the name Amos Tversky
                            didn't
                            > ring a bell, so I ...

                            > > Perhaps a player can experience a Very Hot Hand, and pour in 15
                            > > points in a quarter, and end up shooting 10-22 for the game.
                            Maybe
                            > > he attracted defensive adjustments, or took it too far and
                            attempted
                            > > wild shots. "Hot" may not completely come through in the box
                            score.
                            > >
                            > > DeanO flatly stated that Mr. Tversky had shown the Hot Hand does
                            not
                            > > exist. Then he described his own personal experience with it. I
                            > > think maybe there's a contradiction.
                            > >
                            >
                            > I can't believe Tversky would ever say that. In the Gilovich et al.
                            paper,
                            > he and his colleagues went to some lengths to detect a hot hand,
                            and found
                            > nothing (well, they found one cold hand).

                            They found statistical evidence of a cold streak?
                          • Stephen Greenwell
                            They found statistical evidence of a cold streak? There s a preponderence of evidence that the other end of the spectrum is attainable. See in baseball: Rich
                            Message 13 of 27 , Jan 6, 2004
                            • 0 Attachment
                              They found statistical evidence of a cold streak?

                              There's a preponderence of evidence that the other end of the spectrum is attainable.  See in baseball: Rich Ankiel, Steve Sax, Chuck Knoblauch.  In basketball, Clifford Robinson has been shown to be a vastly inferior player in the postseason as opposed to the regular season.  The same goes for Damon Stoudamire; the proof is in Hollinger's Pro Basketball Prospectus.

                              Steve Greenwell
                            • Mike G
                              ... spectrum is attainable. Unless I m missing something, a streak is a streak. Either you do or don t accept that human beings have more variability than
                              Message 14 of 27 , Jan 6, 2004
                              • 0 Attachment
                                --- In APBR_analysis@yahoogroups.com, Stephen Greenwell
                                <sgre6768@p...> wrote:
                                > > They found statistical evidence of a cold streak?

                                > There's a preponderence of evidence that the other end of the
                                spectrum is attainable.

                                Unless I'm missing something, a streak is a streak. Either you do
                                or don't accept that human beings have more variability than tossed
                                coins and dice.

                                Accepting the validity of a cold streak implies that there is such
                                variability. And since "cold" has to be relative to some average,
                                it implies other "hotter-than-average" periods.


                                >.., Clifford Robinson has been shown to be a vastly inferior player
                                in the postseason as opposed to the regular season. The same goes
                                for Damon Stoudamire; the proof is in Hollinger's Pro Basketball
                                Prospectus.

                                Stoudamire actually beat the rap (though briefly) last season; while
                                Cliff is still Cliff.

                                Meanwhile, Reggie Miller and Robert Horry both stunk in last year's
                                postseason, thus losing their "perennial overachiever" status.

                                You can "prove" the past, but not the future.
                              • Mikey Stewart
                                Heh. Robert Horry s reputation as a great playoff performer, even prior to last year, has been ridiculously overblown. His career playoff numbers aren t any
                                Message 15 of 27 , Jan 6, 2004
                                • 0 Attachment
                                  Heh. Robert Horry's reputation as a great playoff performer, even prior
                                  to last year, has been ridiculously overblown. His career playoff numbers
                                  aren't any better than his modest regular season numbers. When you get
                                  lucky at the ends of a few close games in the playoffs, people tend to
                                  overrated you considerably. Hey, he's a "winner", right?


                                  On Tue, 6 Jan 2004, Mike G wrote:

                                  > --- In APBR_analysis@yahoogroups.com, Stephen Greenwell
                                  > <sgre6768@p...> wrote:
                                  > > > They found statistical evidence of a cold streak?
                                  >
                                  > > There's a preponderence of evidence that the other end of the
                                  > spectrum is attainable.
                                  >
                                  > Unless I'm missing something, a streak is a streak.  Either you do
                                  > or don't accept that human beings have more variability than tossed
                                  > coins and dice.
                                  >
                                  > Accepting the validity of a cold streak implies that there is such
                                  > variability.  And since "cold" has to be relative to some average,
                                  > it implies other "hotter-than-average" periods.
                                  >
                                  >
                                  > >.., Clifford Robinson has been shown to be a vastly inferior
                                  > player
                                  > in the postseason as opposed to the regular season.  The same goes
                                  > for Damon Stoudamire; the proof is in Hollinger's Pro Basketball
                                  > Prospectus.
                                  >
                                  > Stoudamire actually beat the rap (though briefly) last season;
                                  > while
                                  > Cliff is still Cliff.
                                  >
                                  > Meanwhile, Reggie Miller and Robert Horry both stunk in last year's
                                  > postseason, thus losing their "perennial overachiever" status.
                                  >
                                  > You can "prove" the past, but not the future.
                                  >
                                  >
                                  >
                                  > __________________________________________________________________________
                                  > Yahoo! Groups Links
                                  > * To visit your group on the web, go to:
                                  > http://groups.yahoo.com/group/APBR_analysis/
                                  >  
                                  > * To unsubscribe from this group, send an email to:
                                  > APBR_analysis-unsubscribe@yahoogroups.com
                                  >  
                                  > * Your use of Yahoo! Groups is subject to the Yahoo! Terms of
                                  > Service.
                                  >
                                  >
                                • Mike G
                                  ... prior ... numbers ... you get ... tend to ... I don t know what s been blown or overblown. Horry has never been more than a decent role player, but his
                                  Message 16 of 27 , Jan 6, 2004
                                  • 0 Attachment
                                    --- In APBR_analysis@yahoogroups.com, Mikey Stewart <mlstewar@f...>
                                    wrote:
                                    > Heh. Robert Horry's reputation as a great playoff performer, even
                                    prior
                                    > to last year, has been ridiculously overblown. His career playoff
                                    numbers
                                    > aren't any better than his modest regular season numbers. When
                                    you get
                                    > lucky at the ends of a few close games in the playoffs, people
                                    tend to
                                    > overrated you considerably. Hey, he's a "winner", right?

                                    I don't know what's been blown or overblown. Horry has never been
                                    more than a decent role player, but his postseason play has in fact
                                    been significantly more substantial than his regular-season play.

                                    In 165 playoff games (totalling 5255 minutes), his per-minute
                                    production and efficiency are all better than his norm:

                                    Per-36, pace-adjusted:

                                    R. Horry eff% Sco. Reb Ast Stl (T.O) Blk - total
                                    Reg Seas .519 10.1 6.9 3.2 1.5 (1.9) 1.3 - 22.9
                                    Playoffs .540 11.0 7.4 3.3 1.6 (1.5) 1.1 - 24.5


                                    Though modest, his across-the-board improvements are noticeable; and
                                    they occurred every year except '97 (played only the last 22 G with
                                    LA, and the playoffs); and last year.

                                    Since the typical player produces only about 94% of his norm, in
                                    playoffs, Horry's improvement of 6% is even more outstanding -- 12%
                                    above expectations.

                                    In 5 Finals appearances, Horry has outpaced the typical player's 92%
                                    production rate, every time.
                                  • Stephen Greenwell
                                    ... statistical evidence of a cold streak? ... spectrum is attainable. Unless I m missing something, a streak is a streak. Either you do or don t accept that
                                    Message 17 of 27 , Jan 6, 2004
                                    • 0 Attachment
                                      > > They found statistical evidence of a cold streak?

                                      > There's a preponderence of evidence that the other end of the
                                      spectrum is attainable.

                                      Unless I'm missing something, a streak is a streak.  Either you do
                                      or don't accept that human beings have more variability than tossed
                                      coins and dice.

                                      Accepting the validity of a cold streak implies that there is such
                                      variability.  And since "cold" has to be relative to some average,
                                      it implies other "hotter-than-average" periods.

                                      The existence of one side of the spectrum (mental breakdowns and disorders which lead to vastly reduced performance) does not lead to proof of the other side.  Of course, human beings have more variability than tossed coins.  However, this doesn't mean that the magical clutch ability exists.  I still haven't seen anything that would put "hot streaks" or "clutch ability" of vastly significant size past the reasoning of small sample size or statistical uneveness (blah brain fart on that word). 

                                      You can "prove" the past, but not the future.

                                      If I could prove the future, I wouldn't be here :P

                                      Steve Greenwell
                                    • igor eduardo küpfer
                                      ... From: To: Sent: Tuesday, January 06, 2004 4:22 AM Subject: [APBR_analysis] Re: Well, admittedly the
                                      Message 18 of 27 , Jan 6, 2004
                                      • 0 Attachment
                                        ----- Original Message -----
                                        From: <dlirag@...>
                                        To: <APBR_analysis@yahoogroups.com>
                                        Sent: Tuesday, January 06, 2004 4:22 AM
                                        Subject: [APBR_analysis] Re: Well, admittedly the name Amos Tversky didn't
                                        ring a bell, so I ...


                                        >--- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                                        ><igorkupfer@r...> wrote:
                                        >>

                                        <snip>

                                        >>
                                        >>I can't believe Tversky would ever say that. In the Gilovich et al. paper,
                                        >>he and his colleagues went to some lengths to detect a hot hand, and found
                                        >>nothing (well, they found one cold hand).

                                        >They found statistical evidence of a cold streak?

                                        Well, the found one statistically significant instance of a cold streaky
                                        players: Darryl Dawkins's 80-81 season. Here, I'll reproduce the Table 1
                                        from Gilovich et al.:

                                        Probability of Making a Shot Conditioned on the Outcome of Previous Shots
                                        for Nine Members of the Philadelphia 76ers

                                        P(hit| P(hit| P(hit| P(hit| P(hit| P(hit| Serial
                                        Player 3 miss) 2 miss) 1 miss) P(hit) 1 hit) 2 hits) 3 hits) correl.
                                        r
                                        Richardson .50 .47 .56 .50 .49 .50 .48 -.020
                                        Earving .52 .51 .51 .52 .53 .52 .48 .016
                                        Hollins .50 .49 .46 .46 .46 .46 .32 -.004
                                        Cheeks .77 .60 .60 .56 .55 .54 .59 -.038
                                        Jones .50 .48 .47 .47 .45 .43 .27 -.016
                                        Toney .52 .53 .51 .46 .43 .40 .34 -.083
                                        Jones .61 .58 .58 .54 .53 .47 .53 -.049
                                        Mix .70 .56 .52 .52 .51 .48 .36 -.015
                                        Dawkins .88 .73 .71 .62 .57 .58 .51 -.142**

                                        Wt means .56 .53 .54 .52 .51 .50 .46 -.039

                                        * P < .05
                                        ** P < .01

                                        The column headers represent each player's FG% in the specified situations;
                                        after 3 missed shots, after two misses, etc. Notice that none of the players
                                        have a positive r -- showing that these players tended to shoot _worse_
                                        after making shots, and better after missing shots, the opposite of the
                                        hot-hand theory. Of course, none of those correlations were statistically
                                        significant, except for Dawkins.

                                        Since I'm at it, I'll reproduce table 2, which was a Runs Test on the same
                                        data.

                                        Runs Test-Philadelphia 76ers
                                        Expected
                                        Players Hits Misses Number of runs number of runs Z

                                        Clint Richardson 124 124 128 125.0 -0.38
                                        Julius Erving 459 425 431 442.4 0.76
                                        Lionel Hollins 194 225 203 209.4 0.62
                                        Maurice Cheeks 189 150 172 168.3 -0.41
                                        Caldwell Jones 129 143 134 136.6 0.32
                                        Andrew Toney 208 243 245 225.1 -1.88
                                        Bobby Jones 233 200 227 216.2 -1.04
                                        Steve Mix 181 170 176 176.3 0.04
                                        Daryl Dawkins 250 153 220 190.8 -3.09**

                                        M = 218.6 203.7 215.1 210.0 -0.56

                                        * p < .05.
                                        ** p < .01.

                                        ed
                                      • Mike G
                                        ... wrote: ? ... 3ms 2ms 1ms all 1md 2md 3md .88 .73 .71 .62 .57 .58 .51 -.142** Ed,
                                        Message 19 of 27 , Jan 8, 2004
                                        • 0 Attachment
                                          --- In APBR_analysis@yahoogroups.com, igor eduardo küpfer
                                          <igorkupfer@r...> wrote:
                                          ?
                                          >
                                          > ...found one statistically significant instance of a cold streaky
                                          > players: Darryl Dawkins's 80-81 season....> from Gilovich et al.:
                                          >
                                          > Probability of Making a Shot Conditioned on the Outcome of
                                          >Previous Shots

                                          >Dawkins
                                          3ms 2ms 1ms all 1md 2md 3md
                                          .88 .73 .71 .62 .57 .58 .51 -.142**

                                          Ed, I've inserted "column headers" over Dawkins' numbers. I hope I
                                          got them right.

                                          This situation seemed mighty curious to me. Why did Darryl shoot
                                          almost 90% after 3 missed shots?

                                          My source shows that he averaged just over 9 FGA per game, in '81.

                                          9 FGA is a rather finite number; it's also hard to hit 62% of 9
                                          shots.

                                          Let's suppose Darryl's average game is 8 FGA, with 5 made (.625
                                          shooting). That leaves 3 misses per game.

                                          After 1 made shot, he's 4-7 (.571) for the remainder of the sample,
                                          for this game.

                                          After 1 missed shot, he's 5-7 (.714).

                                          These numbers are startlingly close to the above "revelations" about
                                          his inverted hot hand.

                                          Consider a game in which the guy is 2-3. After his miss, there is
                                          0% chance of a miss. After a hit, the chances are 50%.

                                          Dawkins was a high-%, low-volume shooter. As such, he serves the
                                          purpose of refuting the "hot hand"; and then he serves to spoil the
                                          party.


                                          If you evaluate the 3-point-shootout charts (subtracting the miss/
                                          make from the sample totals), you might find a similar self-
                                          contradiction. The samples are bigger, but as expected, the
                                          conclusions are less dramatic.



                                          > The column headers represent each player's FG% in the specified
                                          situations;
                                          > after 3 missed shots, after two misses, etc. Notice that none of
                                          the players
                                          > have a positive r -- showing that these players tended to shoot
                                          _worse_
                                          > after making shots, and better after missing shots, the opposite
                                          of the
                                          > hot-hand theory. Of course, none of those correlations were
                                          statistically
                                          > significant, except for Dawkins.
                                        Your message has been successfully submitted and would be delivered to recipients shortly.