1938 Campeonato da Liga Season

56 games

Final

Champion

Porto

23 points

Relegated

No relegation

Biggest Overachiever

Porto

5.39 points above expected

23 points · 17.61 expected points

Biggest Disappointment

Os Belenenses (1st)

7.12 points below expected

10 points · 17.12 expected points

League Table

The final standings for the season. vsSim shows actual points minus the simulation's mean — positive means the team overachieved against the model, negative means they underperformed.

# Team GP W D L Pts GF GA GD SimPts vsSim
1 Porto 14 11 1 2 23 43 22 +21 17.61 +5.39
2 Benfica 14 10 3 1 23 34 16 +18 21.40 +1.60
3 Sporting Clube de Portugal 14 10 2 2 22 67 23 +44 19.95 +2.05
4 Carcavelinhos 14 5 1 8 11 18 36 -18 10.67 +0.33
5 Os Belenenses (1st) 14 5 0 9 10 29 28 +1 17.12 -7.12
6 Academica de Coimbra 14 5 0 9 10 23 37 -14 9.85 +0.15
7 Barreirense 14 2 4 8 8 18 34 -16 9.97 -1.97
8 Academico do Porto 14 2 1 11 5 15 51 -36 5.44 -0.44

Form

Each team's 5-game rolling points-per-game across the season. Hot streaks push above the dashed 1.5 PPG reference line; cold spells drop below. Each team gets a distinct color; the legend below the plot lets you read off which line is which. (First 4 games of each team have no rolling window, so the lines start at game 5.)

League Race

Cumulative points across the season for each team. Highlighted teams are drawn in color (top finishers for the Title Race, bottom finishers for the Relegation Race); the rest of the league appears in light gray as context. Switch views with the buttons below.

Season Summary

Every team's regular-season finish compared against 100,000 simulations. Click any column header to sort. Luck is the team's actual points minus the sim's mean — positive means the team beat the model. Percentile is where the actual result fell in the team's sim distribution (e.g. 90% = the team did this well or better in only 10% of sims).

Team Elo Points Avg Luck Percentile Min 5th Q1 Median Q3 95th Max
Sporting Clube de Portugal 2027 22 19.95 +2.05 82.2% 9 15 18 20 22 24 28
Benfica 1916 23 21.40 +1.60 78.1% 10 17 20 22 23 26 28
Porto 1815 23 17.61 +5.39 97.8% 5 13 16 18 20 22 28
Os Belenenses (1st) 1566 10 17.12 -7.12 1.2% 4 12 15 17 19 22 27
Carcavelinhos 1561 11 10.67 +0.33 61.5% 0 6 9 11 13 15 22
Academica de Coimbra 1512 10 9.85 +0.15 60.0% 0 5 8 10 12 15 21
Barreirense 1350 8 9.97 -1.97 30.3% 1 6 8 10 12 15 21
Academico do Porto 1243 5 5.44 -0.44 53.0% 0 2 4 5 7 10 17

Head-to-Head

Each cell shows a team's record in that matchup (row vs column, formatted W-D-L) with the model's expected points on the line below. Navy-tinted cells mean the team beat the model's expectations by more than one point in that matchup; gold-tinted cells mean they fell short by the same margin.

Beat expectations Fell short Within expectations
Team ADC ADP BAR BEN CAR OB( POR SCDP
Academica de Coimbra
2-0-0
3.41
2-0-0
2.96
0-0-2
0.98
1-0-1
2.62
0-0-2
1.27
0-0-2
1.31
0-0-2
1.38
Academico do Porto
0-0-2
2.37
1-1-0
1.12
0-0-2
0.71
0-0-2
1.80
1-0-1
0.64
0-0-2
0.42
0-0-2
0.28
Barreirense
0-0-2
2.81
0-1-1
4.65
0-1-1
0.60
0-1-1
2.17
2-0-0
1.05
0-0-2
1.74
0-1-1
1.16
Benfica
2-0-0
4.80
2-0-0
5.07
1-1-0
5.17
2-0-0
5.09
1-0-1
4.28
1-1-0
3.74
1-1-0
3.18
Carcavelinhos
1-0-1
3.16
2-0-0
3.98
1-1-0
3.60
0-0-2
0.69
1-0-1
1.05
0-0-2
1.94
0-0-2
0.84
Os Belenenses (1st)
2-0-0
4.50
1-0-1
5.13
0-0-2
4.72
1-0-1
1.50
1-0-1
4.73
0-0-2
2.18
0-0-2
2.13
Porto
2-0-0
4.47
2-0-0
5.36
2-0-0
4.03
0-1-1
2.03
2-0-0
3.83
2-0-0
3.59
1-0-1
2.33
Sporting Clube de Portugal
2-0-0
4.40
2-0-0
5.50
1-1-0
4.62
0-1-1
2.60
2-0-0
4.93
2-0-0
3.65
1-0-1
3.45

Points vs. Goals Scored, Allowed, and Differential

Points plotted against goals scored, allowed, and differential. Use the buttons to switch views; hover a team for exact values. The table gives each fit's R² and slope (the change in points per 10 goals).

Fit Metrics

Slope
Scored 0.65 +3.4
Allowed 0.78 -5.9
Differential 0.82 +2.6

Scoreline Distribution

Percentage of games ending with each combination of team-goals (rows) and opponent-goals (columns). The diagonal shows draws; cells below the diagonal are wins from the row team's perspective, cells above are losses. Marginal totals on the right and bottom show how often each goal count occurred regardless of opponent. Use the picker to switch between the league-wide view and any individual team.

↓ Scored | Allowed →012345+Total
01.79%5.36%0.89%0.89%3.57%3.57%16.07%
15.36%1.79%8.04%5.36%4.46%3.57%28.57%
20.89%8.04%7.14%4.46%2.68%23.21%
30.89%5.36%4.46%0.89%11.61%
43.57%4.46%8.04%
5+3.57%3.57%2.68%0.89%1.79%12.50%
Total16.07%28.57%23.21%11.61%8.04%12.50%100%

Summary Statistics

Scored Allowed Difference
Mean 2.21 2.21 +0.00
SD 2.04 2.04 3.24
CV 0.93 0.93
Max 13 13 +13
Min 0 0 -13

Games Played: 56

↓ Scored | Allowed →012345+Total
07.14%7.14%14.29%
114.29%14.29%7.14%7.14%14.29%57.14%
27.14%7.14%
37.14%7.14%
4
5+7.14%7.14%14.29%
Total21.43%14.29%14.29%14.29%14.29%21.43%100%

Summary Statistics

Scored Allowed Difference
Mean 1.64 2.64 -1.00
SD 1.60 2.17 3.31
CV 0.97 0.82
Max 5 7 +5
Min 0 0 -6

Games Played: 14

↓ Scored | Allowed →012345+Total
07.14%7.14%7.14%14.29%14.29%50.00%
17.14%7.14%7.14%21.43%
27.14%7.14%
37.14%7.14%14.29%
47.14%7.14%
5+
Total21.43%14.29%7.14%21.43%35.71%100%

Summary Statistics

Scored Allowed Difference
Mean 1.07 3.64 -2.57
SD 1.38 2.02 2.53
CV 1.29 0.56
Max 4 7 +3
Min 0 1 -6

Games Played: 14

↓ Scored | Allowed →012345+Total
07.14%7.14%14.29%
17.14%14.29%14.29%14.29%50.00%
27.14%14.29%7.14%28.57%
37.14%7.14%
4
5+
Total7.14%21.43%35.71%14.29%14.29%7.14%100%

Summary Statistics

Scored Allowed Difference
Mean 1.29 2.43 -1.14
SD 0.83 1.74 1.70
CV 0.64 0.72
Max 3 7 +1
Min 0 0 -5

Games Played: 14

↓ Scored | Allowed →012345+Total
07.14%7.14%
17.14%7.14%
221.43%14.29%35.71%
37.14%14.29%14.29%35.71%
47.14%7.14%14.29%
5+
Total21.43%42.86%35.71%100%

Summary Statistics

Scored Allowed Difference
Mean 2.43 1.14 +1.29
SD 1.09 0.77 1.38
CV 0.45 0.67
Max 4 2 +4
Min 0 0 -1

Games Played: 14

↓ Scored | Allowed →012345+Total
014.29%7.14%7.14%28.57%
17.14%14.29%7.14%28.57%
27.14%14.29%7.14%7.14%35.71%
3
47.14%7.14%
5+
Total21.43%28.57%7.14%21.43%14.29%7.14%100%

Summary Statistics

Scored Allowed Difference
Mean 1.29 2.57 -1.29
SD 1.14 3.32 3.97
CV 0.89 1.29
Max 4 13 +4
Min 0 0 -13

Games Played: 14

↓ Scored | Allowed →012345+Total
014.29%14.29%
17.14%21.43%28.57%
27.14%14.29%7.14%28.57%
37.14%7.14%
47.14%7.14%
5+7.14%7.14%14.29%
Total21.43%21.43%28.57%14.29%14.29%100%

Summary Statistics

Scored Allowed Difference
Mean 2.07 2.00 +0.07
SD 1.64 1.80 2.16
CV 0.79 0.90
Max 5 6 +5
Min 0 0 -3

Games Played: 14

↓ Scored | Allowed →012345+Total
0
114.29%7.14%7.14%28.57%
27.14%7.14%14.29%
314.29%14.29%
421.43%21.43%
5+7.14%14.29%21.43%
Total14.29%50.00%21.43%7.14%7.14%100%

Summary Statistics

Scored Allowed Difference
Mean 3.07 1.57 +1.50
SD 1.86 1.50 2.56
CV 0.61 0.96
Max 7 6 +5
Min 1 0 -5

Games Played: 14

↓ Scored | Allowed →012345+Total
0
17.14%7.14%
27.14%14.29%7.14%28.57%
37.14%7.14%
47.14%7.14%
5+14.29%14.29%7.14%7.14%7.14%50.00%
Total21.43%28.57%28.57%14.29%7.14%100%

Summary Statistics

Scored Allowed Difference
Mean 4.79 1.64 +3.14
SD 3.19 1.39 3.78
CV 0.67 0.85
Max 13 5 +13
Min 1 0 -1

Games Played: 14

Home-Field Advantage Edge

The simulation applies the same home-field boost to every game across the league, so the per-game home win probabilities bake in the model's idea of HFA. For each team, we sum expected points at home and compare to actual home points, and the same on the road. The bar shows (home points above expected) minus (away points above expected). A tall positive bar means the team's home/road split exceeded what the model predicted — a real fortress effect. A tall negative bar means the reverse: they played worse at home or better on the road than expected.

Top Overachievers & Disappointments

Teams that most beat — or most fell short of — their simulated point projections. A positive vsSim means the team accumulated more points than the model expected on average; a negative one means fewer.

Biggest Overachievers

# Team Actual Sim vsSim
1 Porto 23 17.61 +5.39
2 Sporting Clube de Portugal 22 19.95 +2.05
3 Benfica 23 21.40 +1.60
4 Carcavelinhos 11 10.67 +0.33
5 Academica de Coimbra 10 9.85 +0.15

Biggest Disappointments

# Team Actual Sim vsSim
1 Os Belenenses (1st) 10 17.12 -7.12
2 Barreirense 8 9.97 -1.97
3 Academico do Porto 5 5.44 -0.44
4 Academica de Coimbra 10 9.85 +0.15
5 Carcavelinhos 11 10.67 +0.33

Top Streaks

Ranked by model unlikelihood — the product of pregame W/D/L probabilities over the games in each team's streak. A short streak by a poor team can outrank a longer one by a strong team since the poor team's per-game probabilities were lower going in. Unbeaten counts W or D consecutively; Winless counts L or D consecutively.

Most Unlikely Winning Streaks

# Team Games Dates Probability
1 Academico do Porto 2 Mar 20 – Mar 27 1 in 57
2 Porto 4 Jan 16 – Feb 13 1 in 20
3 Barreirense 1 Feb 20 – Feb 20 1 in 14
4 Carcavelinhos 2 Mar 20 – Mar 27 1 in 7
5 Academica de Coimbra 2 Feb 6 – Feb 13 1 in 5

Most Unlikely Losing Streaks

# Team Games Dates Probability
1 Os Belenenses (1st) 6 Mar 20 – May 8 1 in 699
2 Academico do Porto 6 Feb 6 – Mar 13 1 in 12
3 Barreirense 3 Mar 20 – Apr 3 1 in 8
4 Carcavelinhos 4 Jan 16 – Feb 13 1 in 7
5 Academica de Coimbra 4 Mar 6 – Mar 27 1 in 4

Most Unlikely Unbeaten Streaks

# Team Games Dates Probability
1 Academico do Porto 2 Mar 20 – Mar 27 1 in 16
2 Sporting Clube de Portugal 11 Feb 13 – May 8 1 in 10
3 Porto 4 Jan 16 – Feb 13 1 in 8
4 Benfica 8 Mar 6 – May 8 1 in 7
5 Barreirense 2 Jan 23 – Feb 6 1 in 7

Most Unlikely Winless Streaks

# Team Games Dates Probability
1 Os Belenenses (1st) 6 Mar 20 – May 8 1 in 89
2 Barreirense 6 Feb 27 – Apr 3 1 in 18
3 Academico do Porto 8 Jan 16 – Mar 13 1 in 6
4 Benfica 1 Feb 6 – Feb 6 1 in 6
5 Carcavelinhos 4 Jan 16 – Feb 13 1 in 3

Finish Position Heatmap

Each cell is the probability — across 100,000 simulations — that the team (row) finished at that position (column). Rows are sorted by actual finish (champion at top, bottom of the table at the bottom).

Team12345678
Porto10.50%19.71%32.72%29.46%5.94%1.37%0.27%0.03%
Benfica49.75%30.97%13.83%5.02%0.39%0.03%0.01%
Sporting Clube de Portugal34.22%34.24%20.14%9.94%1.22%0.21%0.03%
Carcavelinhos0.03%0.19%1.47%6.17%32.33%28.80%25.16%5.85%
Os Belenenses (1st)5.49%14.54%29.88%40.11%7.73%1.68%0.51%0.06%
Academica de Coimbra0.23%1.15%4.87%25.38%30.80%28.21%9.36%
Barreirense0.01%0.11%0.81%4.26%25.61%32.06%29.72%7.42%
Academico do Porto0.01%0.17%1.40%5.05%16.09%77.28%

Points Required Per Position

The empirical CDF of simulated point totals per finishing position. Each curve shows, for one position (1st, 2nd, ..., last), the spread of point totals teams accumulated across simulations. Reading the curve at the 50% mark gives the median points typically needed to finish at that position. Steep curves mean the position is tightly clustered around a particular point range; shallow curves mean the position came with a wide variety of point totals.

Points Totals in Context

How did each team's actual results compare to their simulated points, Elo rating, average opponent Elo, and percentile within simulated outcomes? Use the buttons to switch between views. In each chart, dashed crosshairs at the league means split the plot into four quadrants: pastel green (team did well, model agreed), pastel red (team did poorly, model agreed), and pastel yellow (model and reality disagreed).

Season Trends

How each metric evolved across the season - Elo rating, actual and projected points, title/promotion probability, and relegation probability - day by day.

Edges & Scoring

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Home Edge
Share of matches won by the home team minus the share won by the away team.
No Edge: under 5% * Slight Edge: 5% to 15% * Clear Edge: 15% to 25% * Strong Edge: 25% and up.
Elo Value
Number of Elo rating points one goal is worth. A team this many Elo points better than another is expected to win by one goal on a neutral field.
Scoring Tilt
Average home goals minus average away goals per match. The gold line is the home goals edge implied by the scoring value of an Elo point and the home-field Elo bonus.
Road-Tilted: under -0.2 * Neutral: -0.2 to 0.5 * Home-Tilted: 0.5 to 1.2 * Strong Home: 1.2 and up.
Home Edge
HomeDrawAway
+21.43%
Clear Edge
55.36%10.71%33.93%
Elo Value
Home Edge
166 Elo
0.006 goals per Elo point
075.62500
Scoring Tilt
Expected
+0.84 goals
Home-Tilted
-2+0.46+2

Title Race

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Title-Race Openness
Effective number of teams with a live shot at finishing 1st, from the simulation. 1 means the favorite is a near-lock; larger means a wide-open race. Equal to 1 divided by the sum of squared title odds.
One-Team Race: under 2 * Top-Heavy: 2 to 4 * Open: 4 to 6 * Wide Open: 6 and up.
Champion Preseason Odds
Preseason probability that the eventual champion would finish 1st, from the simulation. The dot marks their rank across all teams, from longshot to favorite.
Preseason Favorite: 1st * Among the Favorites: 2nd * Middle of the Pack: 3rd to 4th * Longshot: 5th or lower.
Title Margin
Points-per-game gap between the champion and the runner-up. Shown per game so it reads the same across long and short seasons. The gold line is the winning margin the model expected, so a dot to the right means a more one-sided race than projected. A title won on goal difference shows 0.00.
Photo Finish: under 0.15 * Tight Race: 0.15 to 0.4 * Comfortable: 0.4 to 0.75 * Runaway: 0.75 and up.
Title-Race Openness
2.6
Top-Heavy
12468
Champion Preseason Odds
10%
Porto, 3rd of 8
LongshotFavorite
Title Margin
Expected
0.00/gm
Photo Finish
00.180.5/gm

Simulation-Based Surprises

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Luck Spread
Standard deviation of the gap between each team's actual points and their simulated average points. The gold line is the spread the model expected from chance alone.
As Expected: under 2.23 * Some Luck: 2.23 to 3.34 * Lucky: 3.34 to 4.46 * Wild Swing: 4.46 and up.
Average Finish Error
Average gap between where each team was projected to finish and where they actually finished in the table.
Pinpoint: under 0.65 * Close: 0.65 to 0.97 * Off: 0.97 to 1.29 * Way Off: 1.29 and up.
Biggest Overachiever
The team that finished highest inside its own range of simulated outcomes. The gold line is where the top team in a league of 8 typically lands.
Biggest Underachiever
The team that finished lowest inside its own range of simulated outcomes. The gold line is where the bottom team in a league of 8 typically lands.
Season Outliers
Number of teams that finished above the 95th or below the 5th percentile of their own simulated range. Even a well-calibrated model expects about 10% of teams in the extremes.
Minimal Outliers: under 8 * As Expected: 8 to 12.8 * Several Outliers: 12.8 to 17.6 * Many Outliers: 17.6 and up.
Luck Spread
Expected
3.37 points
Lucky
02.787
Average Finish Error
Expected
1.00
Off
00.812
Biggest Overachiever
Expected 93.75%
97.77%
Porto
50100
Biggest Underachiever
Expected
1.17%
Os Belenenses (1st)
06.25%50
Season Outliers
Expected
2 of 8
Minimal Outliers
00.88

Parity

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Gini Index
How evenly points were spread across the league. Lower means a tight, balanced table; higher means a few teams ran off with most of the points.
Balanced: under 0.12 * Even: 0.12 to 0.18 * Top-Heavy: 0.18 to 0.26 * Lopsided: 0.26 and up.
Noll-Scully
How much more spread out the table was than a league where every match is a coin flip. The gold line at 1 is that coin-flip baseline. Above it, real talent gaps stretched the table; below it, the league was tighter than luck alone would produce.
Coin-Flip Parity: under 1 * Moderate Separation: 1 to 1.6 * Strong Separation: 1.6 to 2.2 * Wide Separation: 2.2 and up.
Interquartile Edge
Chance the team at the 75th percentile of Elo would beat the team at the 25th percentile on a neutral field. Higher means a bigger gap between the upper and lower half of the table.
Even: under 60% * Slight Edge: 60% to 70% * Clear Edge: 70% to 80% * Wide Edge: 80% and up.
Best vs. Worst
Chance the top-rated team would beat the bottom-rated team on a neutral field. The gold line is how large that gap tends to be in a league of this size; a dot to the right flags an unusually dominant or unusually weak team.
Even: under 70% * Clear Edge: 70% to 82% * Strong Edge: 82% to 92% * Dominant: 92% and up.
Close Games
Share of matches decided by 1 goal or fewer, draws included. The gold line is how many close games the matchups and the scoring value of an Elo point predict.
Few: under 30% * Some Drama: 30% to 40% * Frequent: 40% to 50% * Very Frequent: 50% and up.
Blowouts
Share of matches decided by 3 goals or more. The gold line is how many routs the matchups and the scoring model predict.
Rare: under 8% * Occasional: 8% to 14% * Frequent: 14% to 22% * Very Frequent: 22% and up.
Gini Index
0.27
Lopsided
00.120.180.260.5
Noll-Scully
Coin-flip
1.98
Strong Separation
01.003
Interquartile Edge
89%
Wide Edge
50%60%70%80%100%
Best vs. Worst
Baseline 99%
99%
Dominant
50%100%
Close Games
Expected
48%
Frequent
0%35%100%
Blowouts
Expected
39%
Very Frequent
0%44%100%

Predictability

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Brier Score
How close the pregame probabilities landed to the actual result, averaged over the season. Confident, correct calls are rewarded most; confident misses are punished most. Lower is better; since draws are possible, a score under 0.66 beats guessing the base rate.
Highly Predictable: under 0.56 * Predictable: 0.56 to 0.62 * Hard to Predict: 0.62 to 0.66 * Coin-Flip: 0.66 and up.
Matchup Imbalance
How lopsided the matchups were on paper, averaging the gap between the two win probabilities over their sum. 0 means every match was a toss-up; 1 means every match was a heavy favorite against a big underdog.
Very Even: under 0.1 * Slight Separation: 0.1 to 0.18 * Notable Separation: 0.18 to 0.28 * Lopsided: 0.28 and up.
Strangeness
How wild the final table was versus what the model expected. A value of 1 means teams landed about one standard deviation from their projections on average. Above 1 is a stranger season; below 1 hugged the projections.
Very Predictable: under 0.8 * As Expected: 0.8 to 1.1 * Wilder Than Modeled: 1.1 to 1.4 * Chaotic: 1.4 and up.
Repeatability
How closely the final table order matched the preseason Elo order, by Spearman rank correlation. Higher means last season's ratings strongly predicted this season's finish. Shows N/A for an inaugural season.
Weak Carryover: under 0.3 * Some Carryover: 0.3 to 0.6 * Strong Carryover: 0.6 to 0.85 * Near-Lock: 0.85 and up.
Upset Rate
Share of matches the underdog won. The gold line is how often the model expected underdogs to win; a dot to the right means upsets ran hotter than expected.
Chalky: under 25% * As Expected: 25% to 33% * Upset-Prone: 33% to 42% * Very Upset-Prone: 42% and up.
Clear Favorite Upset Rate
Share of matches the underdog won, counting only games with a clear favorite (at least 60% likely to win once a draw is set aside). The gold line is how often the model expected these favorites to slip.
Solid Favorites: under 15% * As Expected: 15% to 25% * Shaky Favorites: 25% to 35% * Very Shaky: 35% and up.
Brier Score
Expected
0.43
Highly Predictable
00.432
Matchup Imbalance
0.58
Lopsided
00.10.180.280.5
Strangeness
Expected
1.37
Wilder Than Modeled
01.002
Repeatability
0.52
Some Carryover
00.30.60.851
Upset Rate
Expected
21%
Chalky
0%18%50%
Clear Favorite Upset Rate
Expected
15%
Solid Favorites
0%14%50%

Calibration

How these are measured

The navy dot is the actual value, the gold line and key are the model's reference where one applies, and the slate ticks are the cutoffs between read labels listed under each metric.

Probability calibration
An all-in-one chi-square test of the model's probabilities. Matches are grouped by how confident the model was, and within each group the predicted and actual counts of home wins, draws, and away wins are compared. The p-value is plotted; above 0.05 means well-calibrated.
Miscalibrated: under 0.05 * Borderline: 0.05 to 0.1 * Well Calibrated: 0.1 to 0.5 * Excellent: 0.5 and up.
Calibration slope
Checks whether the spread of the probabilities is right. Each probability is turned into log-odds and a line is fit predicting the actual results. A slope of 1.00 is perfect; below 1 is overconfidence (favorites lost more than their odds implied); above 1 is under-confidence.
Overconfident: under 0.85 * Calibrated: 0.85 to 1.15 * Underconfident: 1.15 to 1.3 * Very Underconfident: 1.3 and up.
Calibration error (ECE)
The average gap between the model's stated chances and how often the predicted result actually happened. Smaller is better. The gold line is the noise ceiling, the error luck alone can produce even with perfect probabilities; below it, the model's error is no larger than chance.
Well Within Noise: under 0.18 * Near Noise Ceiling: 0.18 to 0.27 * Above Noise: 0.27 to 0.36 * Well Above Noise: 0.36 and up.
Probability calibration
0.87
Excellent
0.010.050.10.51
Calibration slope
Ideal
0.89
Calibrated
0.51.001.5
Calibration error (ECE)
Noise ceiling
0.105
Well Within Noise
00.1810.4

Next-Season Status

Across 100,000 regular-season simulations, the probability of each team's next-season status. Columns appear in best-to-worst outcome order: promotion-positive on the left, relegation-positive on the right. Cells with darker shading indicate higher likelihood.

Team Same level
Academica de Coimbra 100%
Academico do Porto 100%
Barreirense 100%
Benfica 100%
Carcavelinhos 100%
Os Belenenses (1st) 100%
Porto 100%
Sporting Clube de Portugal 100%

Overall Game Log

Summary of every completed game this season. Sort any column by clicking its header.

Date Opponent Score Pre Elo Opp Elo Win % Tie % Loss % Elo Δ Points
1938-01-16 Os Belenenses (1st) L 2-3 1495 1791 21.5% 11.3% 67.1% -16.7 0
1938-01-16 @ Academica de Coimbra W 3-2 1791 1495 67.1% 11.3% 21.5% +16.6 2
1938-01-16 Benfica L 0-4 1457 1818 15.8% 11.3% 72.9% -49.9 0
1938-01-16 @ Academico do Porto W 4-0 1818 1457 72.9% 11.3% 15.8% +49.9 2
1938-01-16 Porto L 0-1 1498 1565 51.0% 11.4% 37.6% -40.8 0
1938-01-16 @ Carcavelinhos W 1-0 1565 1498 37.6% 11.4% 51.0% +40.8 2
1938-01-16 Barreirense W 7-2 1730 1636 69.5% 11.3% 19.2% +51.0 2
1938-01-16 @ Sporting Clube de Portugal L 2-7 1636 1730 19.2% 11.3% 69.5% -51.0 0
1938-01-23 Academico do Porto D 1-1 1585 1407 75.9% 11.3% 12.8% -12.7 1
1938-01-23 @ Barreirense D 1-1 1407 1585 12.8% 11.3% 75.9% +12.7 1
1938-01-23 Carcavelinhos W 4-0 1808 1458 83.7% 11.2% 5.1% +16.7 4
1938-01-23 @ Os Belenenses (1st) L 0-4 1458 1808 5.1% 11.2% 83.7% -16.7 0
1938-01-23 Sporting Clube de Portugal W 3-2 1868 1781 68.8% 11.3% 19.9% +15.4 4
1938-01-23 @ Benfica L 2-3 1781 1868 19.9% 11.3% 68.8% -15.4 2
1938-01-23 Academica de Coimbra W 5-1 1605 1479 72.2% 11.3% 16.4% +43.0 4
1938-01-23 @ Porto L 1-5 1479 1605 16.4% 11.3% 72.2% -43.0 0
1938-02-06 Carcavelinhos W 1-0 1436 1441 58.9% 11.4% 29.8% +25.1 2
1938-02-06 @ Academica de Coimbra L 0-1 1441 1436 29.8% 11.4% 58.9% -25.1 0
1938-02-06 Academico do Porto W 1-0 1825 1420 85.0% 11.2% 3.8% +3.5 6
1938-02-06 @ Os Belenenses (1st) L 0-1 1420 1825 3.8% 11.2% 85.0% -3.5 1
1938-02-06 Barreirense D 0-0 1883 1572 82.4% 11.2% 6.3% -17.5 5
1938-02-06 @ Benfica D 0-0 1572 1883 6.3% 11.2% 82.4% +17.5 2
1938-02-06 Sporting Clube de Portugal W 2-1 1648 1765 43.8% 11.4% 44.9% +34.3 6
1938-02-06 @ Porto L 1-2 1765 1648 44.9% 11.4% 43.8% -34.3 2
1938-02-13 Academica de Coimbra L 1-5 1416 1461 53.9% 11.4% 34.7% -128.2 1
1938-02-13 @ Academico do Porto W 5-1 1461 1416 34.7% 11.4% 53.9% +128.2 4
1938-02-13 Benfica L 1-4 1416 1866 10.1% 11.2% 78.6% -20.9 0
1938-02-13 @ Carcavelinhos W 4-1 1866 1416 78.6% 11.2% 10.1% +20.9 7
1938-02-13 Porto L 1-4 1589 1683 47.2% 11.4% 41.5% -87.8 2
1938-02-13 @ Barreirense W 4-1 1683 1589 41.5% 11.4% 47.2% +87.8 8
1938-02-13 Os Belenenses (1st) W 2-1 1731 1828 46.7% 11.4% 42.0% +32.3 4
1938-02-13 @ Sporting Clube de Portugal L 1-2 1828 1731 42.0% 11.4% 46.7% -32.3 6
1938-02-20 Sporting Clube de Portugal L 0-4 1589 1764 35.8% 11.3% 52.9% -106.3 4
1938-02-20 @ Academica de Coimbra W 4-0 1764 1589 52.9% 11.3% 35.8% +106.3 6
1938-02-20 Carcavelinhos L 0-4 1288 1395 45.3% 11.4% 43.4% -131.1 1
1938-02-20 @ Academico do Porto W 4-0 1395 1288 43.4% 11.4% 45.3% +131.1 2
1938-02-20 Barreirense L 2-3 1796 1501 81.8% 11.2% 6.9% -58.7 6
1938-02-20 @ Os Belenenses (1st) W 3-2 1501 1796 6.9% 11.2% 81.8% +58.7 4
1938-02-20 Porto W 3-1 1887 1770 71.4% 11.3% 17.3% +24.7 9
1938-02-20 @ Benfica L 1-3 1770 1887 17.3% 11.3% 71.4% -24.7 8
1938-02-27 Porto L 1-4 1157 1746 4.8% 11.1% 84.0% -10.1 1
1938-02-27 @ Academico do Porto W 4-1 1746 1157 84.0% 11.1% 4.8% +10.1 10
1938-02-27 Sporting Clube de Portugal L 1-3 1526 1870 17.2% 11.3% 71.5% -24.6 2
1938-02-27 @ Carcavelinhos W 3-1 1870 1526 71.5% 11.3% 17.2% +24.7 8
1938-02-27 Academica de Coimbra L 1-3 1560 1483 67.9% 11.3% 20.7% -88.1 4
1938-02-27 @ Barreirense W 3-1 1483 1560 20.7% 11.3% 67.9% +88.1 6
1938-02-27 Benfica W 2-1 1737 1912 35.8% 11.3% 52.8% +39.8 8
1938-02-27 @ Os Belenenses (1st) L 1-2 1912 1737 52.8% 11.3% 35.8% -39.8 9
1938-03-06 Benfica L 1-2 1571 1872 21.1% 11.3% 67.6% -17.2 6
1938-03-06 @ Academica de Coimbra W 2-1 1872 1571 67.6% 11.3% 21.1% +17.2 11
1938-03-06 Barreirense D 2-2 1501 1472 62.9% 11.3% 25.7% -5.4 3
1938-03-06 @ Carcavelinhos D 2-2 1472 1501 25.7% 11.3% 62.9% +5.4 5
1938-03-06 Os Belenenses (1st) W 5-2 1756 1777 56.9% 11.4% 31.7% +53.2 12
1938-03-06 @ Porto L 2-5 1777 1756 31.7% 11.4% 56.9% -53.2 8
1938-03-06 Academico do Porto W 6-0 1894 1147 88.6% 10.8% 0.5% +2.6 10
1938-03-06 @ Sporting Clube de Portugal L 0-6 1147 1894 0.5% 10.8% 88.6% -2.6 1
1938-03-13 Sporting Clube de Portugal D 2-2 1477 1897 11.8% 11.3% 76.9% +9.8 6
1938-03-13 @ Barreirense D 2-2 1897 1477 76.9% 11.3% 11.8% -9.8 11
1938-03-13 Academica de Coimbra W 5-0 1724 1554 75.4% 11.3% 13.3% +51.9 10
1938-03-13 @ Os Belenenses (1st) L 0-5 1554 1724 13.3% 11.3% 75.4% -51.9 6
1938-03-13 Academico do Porto W 3-0 1889 1144 88.6% 10.8% 0.6% +1.4 13
1938-03-13 @ Benfica L 0-3 1144 1889 0.6% 10.8% 88.6% -1.4 1
1938-03-13 Carcavelinhos W 3-1 1809 1496 82.5% 11.2% 6.3% +9.3 14
1938-03-13 @ Porto L 1-3 1496 1809 6.3% 11.2% 82.5% -9.3 3
1938-03-20 Porto L 1-4 1502 1818 19.6% 11.3% 69.1% -39.3 6
1938-03-20 @ Academica de Coimbra W 4-1 1818 1502 69.1% 11.3% 19.6% +39.3 16
1938-03-20 Barreirense W 4-1 1143 1487 17.2% 11.3% 71.5% +131.4 3
1938-03-20 @ Academico do Porto L 1-4 1487 1143 71.5% 11.3% 17.2% -131.4 6
1938-03-20 Os Belenenses (1st) W 1-0 1487 1776 22.3% 11.3% 66.4% +52.7 5
1938-03-20 @ Carcavelinhos L 0-1 1776 1487 66.4% 11.3% 22.3% -52.7 10
1938-03-20 Benfica D 2-2 1887 1890 59.2% 11.4% 29.5% -4.2 12
1938-03-20 @ Sporting Clube de Portugal D 2-2 1890 1887 29.5% 11.4% 59.2% +4.2 14
1938-03-27 Os Belenenses (1st) W 3-2 1274 1723 10.2% 11.2% 78.6% +56.2 5
1938-03-27 @ Academico do Porto L 2-3 1723 1274 78.6% 11.2% 10.2% -56.2 10
1938-03-27 Academica de Coimbra W 2-1 1539 1462 67.9% 11.3% 20.8% +17.0 7
1938-03-27 @ Carcavelinhos L 1-2 1462 1539 20.8% 11.3% 67.9% -17.0 6
1938-03-27 Benfica L 1-2 1356 1895 6.3% 11.2% 82.5% -5.4 6
1938-03-27 @ Barreirense W 2-1 1895 1356 82.5% 11.2% 6.3% +5.4 16
1938-03-27 Porto W 6-1 1883 1858 62.5% 11.3% 26.2% +81.5 14
1938-03-27 @ Sporting Clube de Portugal L 1-6 1858 1883 26.2% 11.3% 62.5% -81.5 16
1938-04-03 Academico do Porto W 5-0 1445 1330 71.3% 11.3% 17.4% +67.1 8
1938-04-03 @ Academica de Coimbra L 0-5 1330 1445 17.4% 11.3% 71.3% -67.1 5
1938-04-03 Sporting Clube de Portugal L 5-6 1667 1965 21.4% 11.3% 67.3% -15.8 10
1938-04-03 @ Os Belenenses (1st) W 6-5 1965 1667 67.3% 11.3% 21.4% +15.8 16
1938-04-03 Carcavelinhos W 3-2 1900 1556 83.5% 11.2% 5.3% +4.3 18
1938-04-03 @ Benfica L 2-3 1556 1900 5.3% 11.2% 83.5% -4.3 7
1938-04-03 Barreirense W 3-1 1776 1350 85.5% 11.2% 3.4% +5.0 18
1938-04-03 @ Porto L 1-3 1350 1776 3.4% 11.2% 85.5% -5.0 6
1938-04-10 Academico do Porto W 2-0 1552 1263 81.6% 11.2% 7.1% +12.2 9
1938-04-10 @ Carcavelinhos L 0-2 1263 1552 7.1% 11.2% 81.6% -12.2 5
1938-04-10 Os Belenenses (1st) W 2-1 1345 1651 20.6% 11.3% 68.0% +50.9 8
1938-04-10 @ Barreirense L 1-2 1651 1345 68.0% 11.3% 20.6% -51.0 10
1938-04-10 Benfica D 2-2 1781 1904 43.0% 11.4% 45.7% +0.4 19
1938-04-10 @ Porto D 2-2 1904 1781 45.7% 11.4% 43.0% -0.4 19
1938-04-10 Academica de Coimbra W 7-1 1980 1513 86.2% 11.1% 2.7% +10.6 18
1938-04-10 @ Sporting Clube de Portugal L 1-7 1513 1980 2.7% 11.1% 86.2% -10.6 8
1938-04-17 Os Belenenses (1st) W 2-1 1904 1600 82.2% 11.2% 6.6% +5.6 21
1938-04-17 @ Benfica L 1-2 1600 1904 6.6% 11.2% 82.2% -5.6 10
1938-04-17 Academico do Porto W 7-2 1782 1251 87.1% 11.1% 1.9% +5.3 21
1938-04-17 @ Porto L 2-7 1251 1782 1.9% 11.1% 87.1% -5.3 5
1938-04-17 Carcavelinhos W 13-0 1991 1564 85.5% 11.2% 3.4% +33.8 20
1938-04-17 @ Sporting Clube de Portugal L 0-13 1564 1991 3.4% 11.2% 85.5% -33.8 9
1938-04-24 Barreirense W 1-0 1502 1396 70.5% 11.3% 18.2% +15.9 10
1938-04-24 @ Academica de Coimbra L 0-1 1396 1502 18.2% 11.3% 70.5% -15.9 8
1938-05-08 Sporting Clube de Portugal L 3-6 1246 2025 1.7% 10.9% 87.4% -2.8 5
1938-05-08 @ Academico do Porto W 6-3 2025 1246 87.4% 10.9% 1.7% +2.8 22
1938-05-08 Carcavelinhos L 1-2 1380 1530 39.1% 11.4% 49.5% -30.3 8
1938-05-08 @ Barreirense W 2-1 1530 1380 49.5% 11.4% 39.1% +30.3 11
1938-05-08 Porto L 0-1 1594 1787 33.4% 11.3% 55.2% -27.9 10
1938-05-08 @ Os Belenenses (1st) W 1-0 1787 1594 55.2% 11.3% 33.4% +27.9 23
1938-05-08 Academica de Coimbra W 3-1 1910 1518 84.7% 11.2% 4.1% +6.1 23
1938-05-08 @ Benfica L 1-3 1518 1910 4.1% 11.2% 84.7% -6.1 10

Biggest Upsets

The 25 games where the underdog won despite the lowest pregame win probability. Underdog Win % is the winner's pregame chance of winning the game (lower = bigger upset). @ before a team name indicates the away side. An asterisk (*) after the date marks a playoff game.

# Date Underdog Win % Winning Team Losing Team
Team Elo Score Team Elo Score
1 1938-02-20 6.93% Barreirense 1501 3 @ Os Belenenses (1st) 1796 2
2 1938-03-27 10.19% @ Academico do Porto 1274 3 Os Belenenses (1st) 1723 2
3 1938-03-20 17.18% @ Academico do Porto 1143 4 Barreirense 1487 1
4 1938-04-10 20.64% @ Barreirense 1345 2 Os Belenenses (1st) 1651 1
5 1938-02-27 20.74% Academica de Coimbra 1483 3 @ Barreirense 1560 1
6 1938-03-20 22.27% @ Carcavelinhos 1487 1 Os Belenenses (1st) 1776 0
7 1938-02-13 34.74% Academica de Coimbra 1461 5 @ Academico do Porto 1416 1
8 1938-02-27 35.82% @ Os Belenenses (1st) 1737 2 Benfica 1912 1
9 1938-01-16 37.65% Porto 1565 1 @ Carcavelinhos 1498 0
10 1938-02-13 41.46% Porto 1683 4 @ Barreirense 1589 1
11 1938-02-20 43.38% Carcavelinhos 1395 4 @ Academico do Porto 1288 0
12 1938-02-06 43.79% @ Porto 1648 2 Sporting Clube de Portugal 1765 1

Biggest Elo Changes

The 25 games that resulted in the largest shift in Elo rating.

# Date Elo Δ Winning Team Losing Team Tie %
Team Score Elo Win % Team Score Elo Win %
1 1938-03-20 131.36 @ Academico do Porto 4 1143 17.18% Barreirense 1 1487 71.52% 11.30%
2 1938-02-20 131.10 Carcavelinhos 4 1395 43.38% @ Academico do Porto 0 1288 45.26% 11.36%
3 1938-02-13 128.25 Academica de Coimbra 5 1461 34.74% @ Academico do Porto 1 1416 53.90% 11.36%
4 1938-02-20 106.26 Sporting Clube de Portugal 4 1764 52.86% @ Academica de Coimbra 0 1589 35.79% 11.35%
5 1938-02-27 88.10 Academica de Coimbra 3 1483 20.74% @ Barreirense 1 1560 67.91% 11.34%
6 1938-02-13 87.85 Porto 4 1683 41.46% @ Barreirense 1 1589 47.18% 11.36%
7 1938-03-27 81.52 @ Sporting Clube de Portugal 6 1883 62.47% Porto 1 1858 26.18% 11.35%
8 1938-04-03 67.12 @ Academica de Coimbra 5 1445 71.29% Academico do Porto 0 1330 17.38% 11.33%
9 1938-02-20 58.72 Barreirense 3 1501 6.93% @ Os Belenenses (1st) 2 1796 81.82% 11.25%
10 1938-03-27 56.18 @ Academico do Porto 3 1274 10.19% Os Belenenses (1st) 2 1723 78.57% 11.24%
11 1938-03-06 53.25 @ Porto 5 1756 56.92% Os Belenenses (1st) 2 1777 31.72% 11.36%
12 1938-03-20 52.73 @ Carcavelinhos 1 1487 22.27% Os Belenenses (1st) 0 1776 66.41% 11.32%
13 1938-03-13 51.87 @ Os Belenenses (1st) 5 1724 75.43% Academica de Coimbra 0 1554 13.26% 11.31%
14 1938-01-16 51.02 @ Sporting Clube de Portugal 7 1730 69.49% Barreirense 2 1636 19.17% 11.34%
15 1938-04-10 50.95 @ Barreirense 2 1345 20.64% Os Belenenses (1st) 1 1651 68.04% 11.32%
16 1938-01-16 49.85 Benfica 4 1818 72.86% @ Academico do Porto 0 1457 15.84% 11.29%
17 1938-01-23 43.02 @ Porto 5 1605 72.25% Academica de Coimbra 1 1479 16.43% 11.33%
18 1938-01-16 40.84 Porto 1 1565 37.65% @ Carcavelinhos 0 1498 50.99% 11.36%
19 1938-02-27 39.80 @ Os Belenenses (1st) 2 1737 35.82% Benfica 1 1912 52.83% 11.35%
20 1938-03-20 39.35 Porto 4 1818 69.09% @ Academica de Coimbra 1 1502 19.60% 11.31%
21 1938-02-06 34.27 @ Porto 2 1648 43.79% Sporting Clube de Portugal 1 1765 44.85% 11.36%
22 1938-04-17 33.78 @ Sporting Clube de Portugal 13 1991 85.49% Carcavelinhos 0 1564 3.36% 11.15%
23 1938-02-13 32.30 @ Sporting Clube de Portugal 2 1731 46.67% Os Belenenses (1st) 1 1828 41.96% 11.36%
24 1938-05-08 30.35 Carcavelinhos 2 1530 49.50% @ Barreirense 1 1380 39.14% 11.36%
25 1938-05-08 27.91 Porto 1 1787 55.24% @ Os Belenenses (1st) 0 1594 33.41% 11.35%