Panama v Croatia · Oxford Football Forecasting

🇵🇦 Panama CONCACAF Elo 1,730 · world 32nd

11 / 23 / 66 win · draw · win most likely 0–1

🇭🇷 Croatia UEFA Elo 1,911 · world 17th

Group: L
Date: Tuesday 23 June 2026
Kick-off: 23:00 UTC
Venue: Toronto Stadium, Toronto

§ 01

The scoreline grid

The ensemble's full distribution over exact scorelines — Panama goals down the side, Croatia goals across the top. This is the same 11×11 grid the tournament simulator samples.

Fig. V7 Ensemble · Group L

Panama v Croatia — scoreline probabilities

Cells show P(exact scoreline); the right column and bottom row are the marginal totals P(Panama scores k) and P(Croatia scores k). Grid runs 0–7 goals per side; the 8–10-goal tail holds 0.07% of the mass and is omitted from the cells (not from the totals).

The grid makes Croatia favourites at 65.8%, with a 22.8% draw. The single most-likely scoreline is 0–1 (14.3%), but no exact score clears 14% — the distribution is broad, as it should be.

Source · Oxford Football Forecasting model

§ 02

Result, goals & totals

The grid marginalised into the outcome split, expected goals each side, and the goal-total markets — every figure read straight off the same distribution.

Win · draw · loss

11.4% 22.8% 65.8%

🇵🇦 Panama 11.4% Draw 22.8% 🇭🇷 Croatia 65.8%

Rounded values sum to exactly 100%.

Expected goals (λ)

🇵🇦Panama 0.65

🇭🇷Croatia 1.87

Poisson means feeding the grid; combined expected goals 2.51.

46.0% Over 2.5 goals P(3 or more goals in the match)

54.0% Under 2.5 goals complement of over-2.5

41.1% Both teams to score P(each side scores ≥ 1)

0–1 Most-likely scoreline modal exact score · 14.3%

§ 03

Venue context

The conditions at Toronto Stadium, Toronto — the same environment layer the dossiers' climate exposure draws on.

BMO Field Toronto, Canada

Heat index 25°C apparent temperature (June–July)

Max temperature 25°C June–July daily high

Humidity 71% relative humidity

Altitude 81m above sea level

Source · Open-Meteo & venue records. Travel and time-zone exposure are per-team — see each side's dossier.

§ 04

Why the model leans this way

The inputs behind the grid — each side's strength signals laid side by side. The forecast is the ensemble's, not a hand-weighting of these; this panel is the descriptive read.

1,730 Elo rating 1,911

1.67 Recent NT form 2.13

€38M Squad value €370M

0.123 Squad form (global) 0.334

0.572 Fitness readiness 0.844

−0.35 Decoupling g +0.46

Croatia carry the Elo edge (181 points). On the decoupling axis, Croatia is the side whose squad is valued higher relative to its record.

How a single-match forecast is built

The pairing is scored by the ensemble — Dixon-Coles bivariate-Poisson, the Bayesian hierarchical model and the global LightGBM-Poisson, log-pooled — yielding the 11×11 scoreline grid above. Win/draw/loss, expected goals (λ), over-2.5 and both-teams-to-score are all marginals of that one grid, so they are mutually consistent by construction. The strength inputs shown here feed the models; the forecast is their pooled output, not a manual weighting of these rows. The model matches the market out-of-sample (RPS 0.1891 vs 0.1905); it does not significantly beat it at n = 3. The ensemble, in full →