2010 US Open Predictatron

I did these last year. They are back by popular demand, if you define “popular” very broadly.

In the meantime, I haven’t made any improvements on my very simple method for predicting the outcome of a men’s tennis match.  Thus, these aren’t terribly advanced, and they would be easy (if time-consuming) to improve upon.

As a quick reminder: The method uses the ATP ranking points of each player.  Thus, it takes into account performance over the last 12 months.  There are some quirks in the ranking system, and I haven’t made any attempt to iron them out.

Because both the seedings and my method are based on the ATP rankings, there aren’t many surprises here.  What mainly interests me are (a) the degree to which the seeds are favored against differing levels of opponents, and (b) who the draw favors.  It would be interesting to know what the odds would look like for the top players if the draw were strictly seeded, e.g. #1 vs. #128 in the first round, and #1 vs. the winner of #64 vs. #65 in the second round, and so on.

The biggest caveats apply to the lowest-ranked players here.  American wild cards Jack Sock and Bradley Klahn have very few ranking points–they are very successful juniors who haven’t played a lot of pro tennis.  I haven’t the foggiest idea whether their ~36 ranking points are an accurate estimate of their current likelihood of beating a tour pro.  Someone like Dmitri Tursunov is tough, too, since his ranking has suffered due to injury.

Ranking points are a week old; they don’t incorporate the results from New Haven this week. For what it’s worth, they also don’t incorporate the points that will accrue to qualifiers due to their success in the qualifying rounds. So it’s possible that qualifiers are somewhat underrated.

All that aside, here are the numbers.  Everything except for “points” is a percentage; Nadal’s “96.44″ under “2nd” means that he has a 96.44% chance of reaching the second round.

Player              points    2nd    3rd    4th     QF     SF      F      W  

Nadal (1)            10745  96.44  91.05  84.50  75.34  62.50  48.85  33.63
Gabashvili             539   3.56   1.48   0.49   0.13   0.02   0.00   0.00
Gonzalez M             253  18.91   0.50   0.09   0.01   0.00   0.00   0.00
Istomin                955  81.09   6.97   3.38   1.31   0.37   0.08   0.01
Simon                 1055  67.86  34.10   3.97   1.64   0.51   0.13   0.02
Young D (WC)           534  32.14  10.55   0.72   0.18   0.03   0.01   0.00
Kamke                  607  29.94  12.34   0.90   0.26   0.06   0.01   0.00
Kohlschreiber (29)    1315  70.06  43.00   5.95   2.79   1.01   0.30   0.06  

Lopez F (23)          1515  66.33  51.53  25.22   4.58   1.81   0.59   0.13
Giraldo                818  33.67  21.58   7.29   0.84   0.22   0.05   0.01
Schuettler             588  67.48  21.02   5.65   0.50   0.10   0.02   0.00
Paire (Q)              303  32.52   5.86   0.91   0.04   0.01   0.00   0.00
Stakhovsky             953  69.75  23.32  11.36   1.46   0.42   0.10   0.02
Luczak                 447  30.25   5.87   1.80   0.12   0.02   0.00   0.00
Ljubicic (15)         2120  92.51  69.26  47.50  10.79   5.12   2.06   0.59
Harrison R (Q)         214   7.49   1.55   0.27   0.01   0.00   0.00   0.00  

Ferrer (10)           3065  77.47  64.87  48.96  29.04   9.29   4.62   1.72
Dolgopolov             997  22.53  13.50   6.46   2.12   0.31   0.07   0.01
Becker                 702  51.01  11.19   4.35   1.11   0.13   0.02   0.00
Brands                 678  48.99  10.44   3.95   0.99   0.10   0.02   0.00
Nieminen               830  49.99  19.88   6.03   1.76   0.23   0.05   0.01
Gimeno                 828  50.01  19.80   6.06   1.74   0.23   0.05   0.01
Chardy                 785  32.65  15.81   4.65   1.29   0.16   0.03   0.00
Gulbis (24)           1515  67.35  44.50  19.54   8.25   1.67   0.55   0.12  

Nalbandian (31)       1235  87.95  51.69  18.10   7.42   1.30   0.37   0.07
De Voest (Q)           202  12.05   1.97   0.17   0.02   0.00   0.00   0.00
Serra                  780  43.38  18.59   4.84   1.49   0.18   0.03   0.00
Mayer F                995  56.62  27.75   8.47   3.05   0.44   0.10   0.02
Riba                   678  69.14  13.47   5.22   1.44   0.16   0.03   0.00
Mannarino (Q)          326  30.87   3.22   0.72   0.10   0.01   0.00   0.00
Fognini                626  13.37   7.18   2.64   0.69   0.07   0.01   0.00
Verdasco (8)          3430  86.63  76.13  59.83  39.49  13.54   7.09   2.86  

Murray (4)            5125  90.02  83.11  69.41  54.52  38.02  17.10   8.61
Lacko                  691   9.98   5.68   2.09   0.63   0.14   0.02   0.00
Ramirez-Hidalgo        587  56.15   6.80   2.23   0.61   0.12   0.01   0.00
Brown D                468  43.85   4.41   1.21   0.26   0.04   0.00   0.00
Chela                  914  46.37  19.95   4.28   1.58   0.46   0.06   0.01
Lu                    1045  53.63  24.93   5.85   2.37   0.74   0.11   0.02
Kukushkin              625  27.45  10.43   1.69   0.49   0.10   0.01   0.00
Wawrinka (25)         1510  72.55  44.69  13.25   6.61   2.64   0.55   0.12  

Querrey (20)          1705  98.55  70.75  38.87  13.60   5.87   1.32   0.33
Klahn (WC)              36   1.45   0.05   0.00   0.00   0.00   0.00   0.00
Granollers             583  40.23   9.85   2.80   0.47   0.10   0.01   0.00
Seppi                  835  59.77  19.34   7.15   1.56   0.42   0.06   0.01
Garcia-Lopez           900  53.67  18.26   7.27   1.67   0.47   0.06   0.01
Kubot                  788  46.33  14.33   5.20   1.08   0.28   0.04   0.00
Starace                870  27.02  13.73   5.31   1.20   0.33   0.05   0.01
Almagro (14)          2150  72.98  53.68  33.40  13.35   6.50   1.74   0.51  

Youzhny (12)          2620  72.59  57.20  39.51  21.61  10.17   3.09   1.06
Goloubev              1078  27.41  16.06   7.52   2.51   0.69   0.11   0.02
Sela                   583  37.33   7.79   2.46   0.53   0.09   0.01   0.00
Malisse                933  62.67  18.95   8.22   2.51   0.62   0.09   0.01
Sock (WC)               30   2.68   0.04   0.00   0.00   0.00   0.00   0.00
Chiudinelli            787  97.32  34.16  10.85   2.94   0.63   0.08   0.01
Gil                    635  23.99  10.98   3.02   0.69   0.13   0.01   0.00
Isner (18)            1805  76.01  54.82  28.42  12.97   4.96   1.16   0.30  

Stepanek (28)         1320  54.14  33.11  11.69   5.17   1.62   0.30   0.06
Benneteau             1135  45.86  26.26   8.42   3.41   0.96   0.17   0.03
Robredo               1075  81.35  37.59  11.62   4.54   1.24   0.20   0.03
Rosol (Q)              282  18.65   3.04   0.32   0.05   0.00   0.00   0.00
Hanescu                870  62.62  13.56   5.82   1.97   0.46   0.06   0.01
Berlocq                544  37.38   5.45   1.70   0.41   0.07   0.01   0.00
Llodra                1185  21.47  13.48   6.93   2.87   0.83   0.15   0.03
Berdych (7)           3860  78.53  67.51  53.49  37.81  21.31   8.20   3.54  

Davydenko (6)         4285  88.76  74.50  60.63  40.64  21.45  10.27   4.28
Russell                654  11.24   4.56   1.74   0.40   0.06   0.01   0.00
Greul                  633  34.47   5.21   1.96   0.44   0.07   0.01   0.00
Gasquet               1135  65.53  15.73   8.19   2.82   0.70   0.14   0.02
Anderson K             677  56.30  19.96   3.85   0.90   0.15   0.02   0.00
Devvarman              538  43.70  13.35   2.16   0.44   0.06   0.01   0.00
Smyczek (WC)           269  13.26   3.84   0.34   0.03   0.00   0.00   0.00
Bellucci (26)         1480  86.74  62.85  21.14   8.59   2.55   0.60   0.12  

Monfils (17)          2070  87.90  67.91  33.31  14.84   5.36   1.65   0.44
Kendrick (Q)           344  12.10   3.94   0.54   0.07   0.01   0.00   0.00
Andreev                520  38.51   8.91   1.76   0.31   0.05   0.00   0.00
Zeballos               795  61.49  19.24   5.27   1.27   0.24   0.03   0.00
Tipsarevic            1020  60.81  17.05   7.06   2.05   0.47   0.08   0.01
Rochus O               685  39.19   8.13   2.60   0.57   0.10   0.01   0.00
Robert                 675  15.17   6.51   2.08   0.44   0.08   0.01   0.00
Roddick (9)           3225  84.83  68.31  47.37  26.19  12.12   4.93   1.74  

Baghdatis (16)        2095  76.51  58.63  38.16  13.18   5.60   1.73   0.46
Clement                716  23.49  11.87   4.56   0.79   0.16   0.02   0.00
Schwank                840  63.26  21.06   8.92   1.71   0.38   0.05   0.01
Ginepri                513  36.74   8.44   2.63   0.34   0.05   0.00   0.00
Cuevas                 615  76.52  23.12   7.15   1.08   0.19   0.02   0.00
Silva J (Q)            210  23.48   2.85   0.37   0.02   0.00   0.00   0.00
Hajek                  644  24.94  14.32   4.58   0.71   0.13   0.02   0.00
Fish (19)             1751  75.06  59.71  33.64  10.43   3.96   1.07   0.25  

Monaco (30)           1235  85.80  66.28  14.55   6.66   1.98   0.42   0.07
Polansky (Q)           240  14.20   5.44   0.31   0.04   0.00   0.00   0.00
Vliegen                129  18.84   2.13   0.07   0.00   0.00   0.00   0.00
Blake (WC)             485  81.16  26.16   2.79   0.68   0.10   0.01   0.00
Petzschner             910  78.18  11.08   5.68   2.17   0.52   0.08   0.01
Lojda (Q)              285  21.82   1.06   0.26   0.04   0.00   0.00   0.00
Troicki                980  10.77   6.25   3.33   1.34   0.34   0.06   0.01
Djokovic (3)          6665  89.23  81.62  73.02  60.81  43.13  25.47  13.37  

Soderling (5)         4910  96.76  86.02  72.53  53.02  27.69  15.17   6.90
Haider-Maurer (Q)      223   3.24   0.68   0.12   0.01   0.00   0.00   0.00
Dent                   699  46.99   5.96   2.43   0.66   0.10   0.01   0.00
Falla                  780  53.01   7.33   3.17   0.94   0.15   0.03   0.00
de Bakker              895  77.31  35.20   6.80   2.25   0.41   0.08   0.01
Gicquel (Q)            294  22.69   4.84   0.37   0.05   0.00   0.00   0.00
Gonzalez F (27)       1340  81.99  54.20  14.11   5.93   1.43   0.36   0.07
Dodig (Q)              337  18.01   5.76   0.49   0.08   0.01   0.00   0.00  

Montanes (21)         1600  74.62  64.67  29.67   9.88   2.72   0.78   0.17
Przysiezny             602  25.38  17.53   4.39   0.73   0.10   0.01   0.00
Ball (WC)              346  65.33  13.50   2.21   0.22   0.02   0.00   0.00
Raonic (Q)             194  34.67   4.30   0.42   0.03   0.00   0.00   0.00
Korolev                690  68.72  15.73   6.37   1.15   0.16   0.03   0.00
Nishikori (Q)          337  31.28   3.94   1.00   0.10   0.01   0.00   0.00
Marchenko              670  16.86   9.29   3.69   0.67   0.09   0.01   0.00
Cilic (11)            2855  83.14  71.03  52.26  24.27   9.60   3.98   1.31  

Melzer (13)           2470  98.31  85.13  58.60  20.22   8.83   3.33   1.00
Tursunov                62   1.69   0.17   0.01   0.00   0.00   0.00   0.00
Sweeting (WC)          478  53.14   8.15   2.36   0.26   0.03   0.00   0.00
Berankis (Q)           428  46.86   6.55   1.74   0.17   0.02   0.00   0.00
Phau                   553  45.48  12.87   2.82   0.34   0.05   0.01   0.00
Mello                  652  54.52  17.21   4.27   0.60   0.10   0.01   0.00
Ferrero (22)          1560  92.90  68.65  30.12   7.84   2.59   0.71   0.15
Klizan (Q)             151   7.10   1.28   0.09   0.00   0.00   0.00   0.00  

Hewitt (32)           1215  73.04  50.86   9.76   3.85   1.07   0.24   0.04
Mathieu                491  26.96  12.69   1.18   0.24   0.03   0.00   0.00
Mayer L                697  76.75  32.09   4.03   1.08   0.20   0.03   0.00
Rufin (WC)             236  23.25   4.37   0.21   0.02   0.00   0.00   0.00
Berrer                 942  66.43   8.48   4.49   1.49   0.33   0.06   0.01
Beck A                 506  33.57   2.53   0.93   0.19   0.02   0.00   0.00
Federer (2)           7215  94.12  86.51  78.40  63.44  44.20  28.41  15.51
Dabul                  577   5.88   2.49   1.00   0.23   0.04   0.01   0.00

Marcel spreadsheets for pitchers

I’ve now uploaded year-by-year spreadsheets with Marcel projections for pitchers, dating back to 1906.  Each set of projections relies on the previous three years of data and uses Tango’s algorithm exactly, barring mistakes in my coding or interpretation.

I started with 1906 because the Baseball Databank spreadsheet only has batters faced (BF) back to 1903.  It would be easy enough to estimate BF, but for now, I’ve only projected years where I can use BF for all seasons the projections draw upon.

As with hitters, I’ve made no league-specific adjustments.  ERA is calculated using Marcel-projected IP and ER; I didn’t do any kind of DIPS or BsR adjustments.