WC 2026 · Forecasting Oxford Football Forecasting
🇧🇦

Bosnia and Herzegovina

UEFA Group B
0.0% Champion probability ±0.00 MC-SE
Coach
Sergej Barbarez home · Bosnian
Elo (model)
1,595 world 86th
Squad value
€118M
Power → Reality
37th 36th +0.01 pp · neutral draw

§ 01

The forecast

How far Bosnia and Herzegovina goes — the survival probability at each stage of the bracket, from the tournament Monte-Carlo simulation. Each bar carries its ±1.96·MC-SE interval.

Fig. D1 Fixture-aware · 100k sims

Bosnia and Herzegovina — stage progression

Round of 32: 60.14% (95% MC 59.83%–60.44%; MC-SE ±0.15 pts) Round of 32 reach 60.1% ±0.15 Round of 16: 19.24% (95% MC 19.00%–19.49%; MC-SE ±0.12 pts) Round of 16 reach 19.2% ±0.12 Quarter-final: 4.58% (95% MC 4.46%–4.71%; MC-SE ±0.07 pts) Quarter-final reach 4.6% ±0.07 Semi-final: 0.74% (95% MC 0.69%–0.80%; MC-SE ±0.03 pts) Semi-final reach 0.7% ±0.03 Final: 0.13% (95% MC 0.10%–0.15%; MC-SE ±0.01 pts) Final reach 0.1% ±0.01 Champion: 0.02% (95% MC 0.01%–0.03%; MC-SE ±0.00 pts) Champion reach 0.0% ±0.00

On the central forecast, Bosnia and Herzegovina more likely than not reaches the Round of 32 (60%). Champion probability is 0.0% ± 0.00 pts.

Source · Oxford Football Forecasting model

§ 02

The group & the path

Group B advancement odds, the bracket half Bosnia and Herzegovina sits in, and the earliest round they could meet each leading side.

Group B Confed Advance (top 2) Reach R32
1🇨🇭SwitzerlandUEFA60.6%96.2%
2🇨🇦CanadaCONCACAF44.4%91.8%
3🇧🇦Bosnia and HerzegovinaUEFA19.2%60.1%
4🇶🇦QatarAFC2.8%18.2%

Source · Oxford Football Forecasting model

Bracket position Half 1 · Quadrant 3

Earliest possible meetings

No collision rows recorded for this team.

Collision = the earliest round the bracket wiring could pit Bosnia and Herzegovina against that side. Full bracket & collision matrix →

§ 03

Match by match

Bosnia and Herzegovina's three group fixtures, each with the predicted win / draw / loss split and the single most-likely scoreline. Probabilities are this team's own orientation; they sum to 100%.

Match 3 · 2026-06-12 · Toronto Stadium away
Bosnia and Herzegovina Canada
17.8% win 26.4% draw 55.8% loss
Most likely 0–1 (13.0%) λ 0.83–1.64 Over 2.5 45% · BTTS 46%
Match 26 · 2026-06-18 · Los Angeles Stadium away
Bosnia and Herzegovina Switzerland
13.6% win 24.2% draw 62.2% loss
Most likely 0–1 (13.9%) λ 0.71–1.78 Over 2.5 45% · BTTS 43%
Match 52 · 2026-06-24 · Seattle Stadium home
Bosnia and Herzegovina Qatar
53.4% win 27.7% draw 18.9% loss
Most likely 1–0 (13.8%) λ 1.53–0.81 Over 2.5 42% · BTTS 44%
How a match forecast is built

Each pairing is scored by the ensemble (Dixon-Coles bivariate-Poisson, the Bayesian hierarchical model and the global LightGBM-Poisson, log-pooled), producing an 11×11 scoreline grid that is marginalised into win/draw/loss, expected goals (λ), over/under 2.5 and both-teams-to-score. These are the same distributions the tournament simulator consumes, oriented here to Bosnia and Herzegovina. Knockout fixtures are not shown — their occupants are still probabilistic, so there is no single pairing to forecast yet.

§ 04

Strength profile

Where Bosnia and Herzegovina stands against the median of the 48-team field, metric by metric. The dot is Bosnia and Herzegovina; the dashed line is the field median (1.0×).

Fig. D2 Relative to the 48-team median

Bosnia and Herzegovina vs the field

Elo rating: 1595 vs field median 1780 (0.90× the field) Elo rating 1595 med 1780 Recent NT form: 1.67 ppg vs field median 1.87 ppg (0.89× the field) Recent NT form 1.67 ppg med 1.87 ppg Squad value: €118M vs field median €286M (0.41× the field) Squad value €118M med €286M Squad form (global): 0.219 vs field median 0.211 (1.04× the field) Squad form (global) 0.219 med 0.211 Fitness readiness: 0.732 vs field median 0.707 (1.04× the field) Fitness readiness 0.732 med 0.707 Familiarity / chemistry: 0.006 vs field median 0.015 (0.40× the field) Familiarity / chemistry 0.006 med 0.015 Experience (mean caps): 21 vs field median 25 (0.83× the field) Experience (mean caps) 21 med 25

Read each row as a multiple of the field median: dots to the right of the dashed line are above-field, to the left below. Raw values are labelled on the right so the comparison is transparent.

Source · Oxford Football Forecasting model

§ 05

History vs squad

The decoupling residual g — whether the squad’s market value sits above, or below, what the team’s record predicts.

Fig. D3 Bayesian projection residual g

Bosnia and Herzegovina on the decoupling axis

aligned (0) ← record > squad price squad valued > record →

g = −0.15 ± 0.08: the record outruns the squad price — the team has achieved more than its comparatively modest squad value would predict.

Source · Oxford Football Forecasting model
What g means — and its limits

g is the residual from regressing a team’s current squad market value on its history-based strength in the Bayesian hierarchical model. Positive g means the squad is valued above what the team’s record predicts; negative means the record outruns the squad’s price (the side achieves more than its market value implies). Regressed on out-of-sample success the slope is positive — squad-rich sides go a touch further — but not statistically significant at n = 3 tournaments, so treat a single team’s g as a descriptive read, not a hard prediction. The full decoupling essay →

§ 06

The squad

All 26 selected players — club, league (with relative strength), club-season minutes and goals, caps. Sort any column.

26players
25.2mean age
21mean caps
42%in a top-5 league
24distinct clubs
2largest club bloc
# Player Pos Club League Club min Gls Caps NT gls
1Nikola VasiljGKFC St. PauliBundesliga +1.84z3,2700260
2Nihad MujakićDFGaziantepSüper Lig +0.49z8540121
3Dennis HadžikadunićDFSampdoriaSerie B +1.70z2,2200320
4Tarik MuharemovićDFSassuoloSerie A +1.70z2,9252141
5Sead KolašinacDFAtalantaSerie A +1.70z1,8120650
6Benjamin TahirovićMFBrøndbySuperliga −0.53z1,5371282
7Amar DedićDFBenficaPrimeira Liga +1.14z3,2621281
8Armin GigovićMFYoung BoysSuper League −0.07z2,4462201
9Samed BaždarFWJagiellonia BiałystokEkstraklasa −0.29z5513131
10Ermedin DemirovićFWVfB StuttgartBundesliga +1.84z2,44615404
11Edin Džeko (captain)FWSchalke 042. Bundesliga +1.84z599614873
12Mladen JurkasGKBorac Banja Luka—— no club data—00
13Ivan BašićMFAstanaPremier League2691170
14Ivan ŠunjićMFPafos—— no club data—110
15Amar MemićMFViktoria PlzeňCzech Liga +0.20z3,4093131
16Amir HadžiahmetovićMFHull CityChampionship +2.21z2,3370360
17Dženis BurnićMFKarlsruher SC2. Bundesliga +1.84z2,0971200
18Nikola KatićDFSchalke 042. Bundesliga +1.84z2,4511172
19Kerim AlajbegovićFWRed Bull SalzburgBundesliga +0.26z2,36011101
20Esmir BajraktarevićFWPSV EindhovenEredivisie +0.74z1,4157161
21Stjepan RadeljićDFRijekaHNL +0.34z2,624250
22Martin ZlomislićGKRijekaHNL +0.34z3,794030
23Haris TabakovićFWBorussia MönchengladbachBundesliga +1.84z2,65915104
24Nidal ČelikDFLens—— no club data—20
25Jovo LukićFWUniversitatea Cluj—— no club data—30
26Ermin MahmićMFSlovan LiberecCzech Liga +0.20z1,559720

Source · Official squad announcements · API-Football (global club coverage). 4 of 26 players have no club season matched in API-Football — shown as “— no club data”, not imputed. Form coverage for this squad: 85%.

§ 07

Tournament context

The host-nation environment this team meets — diaspora support, climate and altitude exposure at their venues, language familiarity.

Diaspora in the hosts

143,042

45.0 per 1,000 of home population

Host-language familiarity

Foreign

primary language Bosnian

Climate adaptation gap

−2.0°C

home-vs-venue heat differential

Venue extremes

29°C

peak heat index · altitude up to 81 m

Travel

9h

max time-zone shift · nearest venue 6,908 km

Source · UN DESA international migrant stock · US Census Bureau · Open-Meteo & venue records

§ 08

Elo trajectory

Bosnia and Herzegovina's long-run strength against the qualified-field median, 1995–2026.

Fig. D4 eloratings.net method · year-end values

Bosnia and Herzegovina — Elo since 1995

1651 world #86
Bosnia and Herzegovina Qualified-field median

Bosnia and Herzegovina ends the series at 1651 Elo, the world’s 86th-ranked side — below the qualified-field median.

Source · eloratings.net
Which Elo is this?

This line is the public eloratings.net series (year-end ratings), which terminates exactly at the current rating and world rank shown on the marker. It is a different number from the Elo shown in the header band (a panel-normalised rating used inside the forecast); the two are ~0.99 correlated but on different scales. We keep them distinct rather than blend them.

§ 09

Data coverage

85% Squad club-form coverage Share of this squad with a matched club season feeding the global form layer.
85% Fitness-readiness coverage Where below 100%, part of the fitness signal is imputed by the de-biasing layer.
n = 3 Out-of-sample tournaments The model is validated on three held-out World Cups; it matches the market, it does not beat it.

Validated on n=3 held-out tournaments; coverage below 1.0 means part of this squad's club-form/fitness is imputed (the global de-biasing layer). For Bosnia and Herzegovina, 4 of 26 players are shown as “— no club data”. Full validation, calibration & conformal coverage →