Back when I was working on Basketball-Reference.com, I built a Hall of Fame probability model. I was a little surprised how popular it became, as the results of that model were cited quite often (for better and for worse). The model has been slightly tweaked since I left Sports Reference, but the framework remains the same.
I decided to look into this topic again, basically starting from scratch. My player pool consisted of players who met the following criteria:
Played at least 10 seasons in the NBA.
Had the entirety of their NBA career fall between the 1968-69 and 2019-20 seasons. I chose to start with the 1968-69 season because that’s the first time the NBA named All-Defensive teams. The 2019-20 season was chosen as the stopping point because players who retired after that are not yet eligible.
That gave me a pool of 691 players, 77 of whom are Hall of Famers. The response variable in my model was simply Hall of Fame status, with electees assigned a value of one and all other assigned a value of zero.
After much experimentation, I settled on five predictor variables:
Career value, which is a weighted sum of the player’s individualized wins for each season. The player’s best season received a weight of 1.00, their second-best season received a weight of 0.95, their third-best season received a weight of 0.90, and so on.
Number of All-Star Game selections.
Number of All-NBA points, where a First Team selection earns the player five points, a Second Team selection is worth three points, and a Third Team selection is worth one point.
Number of All-Defensive points, where a First Team selection earns the player two points and a Second Team selection is worth one point.
Number of championships won. The player must have appeared in at least one postseason game for the league champion to receive credit in a given season.
Those factors produced a logistic regression model with the following parameters:
Intercept = –9.63926
Career Value = 0.04991
All-Star Games = 0.85433
All-NBA Points = 0.18568
All-Defensive Points = 0.28016
Championships = 1.03844
Let’s use one of Marc Stein’s favorites, former Buffalo Braves star Bob McAdoo, as an example. Here are McAdoo’s values for each predictor:
Career Value = 85.3
All-Star Games = 5
All-NBA Points = 8
All-Defensive Points = 0
Championships = 2
These are used to calculate McAdoo’s logit:
L = –9.63926 + 0.04991 * 85.3
+ 0.85433 * 5
+ 0.18568 * 8
+ 0.28016 * 0
+ 1.03844 * 2Which is then converted into a probability:
P = 1 / (1 + e^-L)
= 1 / (1 + e^-2.452)
= 0.921If the model produced a probability of 0.5 or higher for a player, then I predicted they were a Hall of Famer, otherwise not. I’ll summarize the results:
There were 614 non-Hall of Famers in the player pool. The model correctly classified 610 of them, or 99.3%.
There were 77 Hall of Famers in the player pool. The model correctly classified 72 of them, or 93.5%.
Overall, the model correctly classified 682 of the 691 players, or 98.7%.
Let’s take a closer look at the misses, starting with the five Hall of Famers who were not pegged as such by the model:
Jamaal Wilkes (P = 0.4051): Wilkes was only selected to two All-Star Games and did not earn a single All-NBA point. Both are extremely low totals for a Hall of Famer.
Bill Walton (0.2015): Walton was an all-time great when he was healthy enough to play. Walton barely met the minimum in terms of seasons played (exactly 10), and he appeared in less than 70% of his team’s games in six of those seasons. Walton is an extreme case, so I’m not going to sweat this miss.
Toni Kukoc (0.0188): Kukoc had a legendary international career, which isn’t accounted for here. Again, not a miss to worry about.
Vlade Divac (0.0053): Divac is another international star who was elected for his overall contributions to the game rather than his NBA career (which was very good, but not great).
Calvin Murphy (0.0048): Murphy is a puzzling selection. He was only named to a single All-Star Game, and has zero All-NBA points, zero All-Defensive points, and zero championships won. Murphy was a star collegian, earning three All-America selections at Niagara University. Maybe the voters gave his amateur career a lot of weight.
Now let’s look at the four players the model identifies as Hall of Famers but, to date, have not been elected:
Amar’e Stoudemire (0.9503): Stoudemire is lifted by his 17 All-NBA points (one First Team and four Second Team selections). He’s one of 41 players in the pool with at least a dozen All-NBA points. In that subgroup, only Stoudemire and Kevin Johnson (0.3795) have not been elected to the Hall of Fame.
Shawn Kemp (0.7494): Fair or not, perceptions matter, and Kemp was a bloated shadow of his former self by the end of his career. Is that being held against him? When Kemp was at his peak from 1992-93 through 1996-97, he was a five-time All-Star selection and earned three All-NBA Second Team nods.
Marques Johnson (0.5956): I have written extensively about Johnson’s case for the Hall of Fame.
Horace Grant (0.5893): Grant managed to contribute a lot to the bottom line even though his traditional statistics, while good, were not especially eye-popping (see this post for much more on the topic). Grant never earned All-NBA honors, but he was a four-time All Defensive Second Team selection and a member of four championship squads.
Looking forward, the model identifies five players whose careers ended after the 2019-20 season as probable Hall of Famers:
Dwight Howard (1.0000)
Carmelo Anthony (0.9965)
LaMarcus Aldridge (0.9411)
Blake Griffin (0.8094)
Rajon Rondo (0.5635)
I’m very confident the first two names above will be elected, but less confident about the rest. In particular, I do not share the model’s enthusiasm for Aldridge. By the way, I recently wrote about Griffin’s case for enshrinement.
There are two more interesting names who don’t make the cut above. Shawn Marion (0.4821) has what I consider to be a compelling case, while Robert Horry (0.4059) does not have the individual accolades (no All-Star, All-NBA, or All-Defensive selections) but owns seven championship rings.
Finally, there are 20 active players pegged as likely Hall of Fame selections. I might as well list all of them:
LeBron James (1.0000)
Kevin Durant (1.0000)
Chris Paul (1.0000)
Stephen Curry (1.0000)
Giannis Antetokounmpo (1.0000)
James Harden (1.0000)
Anthony Davis (1.0000)
Kawhi Leonard (0.9999)
Russell Westbrook (0.9999)
Damian Lillard (0.9979)
Paul George (0.9966)
Draymond Green (0.9876)
Kyrie Irving (0.9642)
Jimmy Butler (0.9548)
Rudy Gobert (0.8836)
Klay Thompson (0.8743)
DeMar DeRozan (0.7898)
Kyle Lowry (0.7170)
Kevin Love (0.6860)
Al Horford (0.5194)
The discussion surrounding the last four names will be particularly interesting. DeRozan is the only one of those four without a championship to his credit, but his seven All-NBA points are just one fewer than the other three combined (Love totals six points, while Lowry and Horford have just one apiece).