Forecasting Post-Pandemic Tourism Recovery: Counterfactual Benchmarks, Intervention Models and Value–Volume Asymmetry in Greece

Whether tourism has recovered from the COVID-19 shock depends on the benchmark used. This study combines interrupted time-series models, structural-break detection, an event-study specification and counterfactual forecasts to quantify the shock and recovery of Greek tourism using 132 monthly observations for 2015–2025. A counterfactual path is forecast from a trend–seasonal model estimated on pre-pandemic data, validated out of sample against seasonal-naïve, exponential-smoothing and SARIMA benchmarks, and compared with SARIMA, damped-trend ETS and growth-scenario alternatives; a sieve bootstrap quantifies the uncertainty of shortfalls and recovery dates. Travel receipts, inbound traveler flows and receipts per traveler are compared. Receipts and arrivals contracted by approximately 83%, a finding that was robust across intervention dates, HAC bandwidths and serially correlated-error specifications, whereas a single constant recovery slope is not supported. Both indicators regained their 2019 levels in April 2023 under all rules. Relative to the counterfactual, receipts met a three-month criterion in February 2024 while arrivals had not by end-2025; receipts cross first with probability 0.64, but the dates depend on the run-length rule and the assumed pre-pandemic growth, and in real terms the post-2022 lead of receipts reflects prices, not higher spending per traveler. Domestic accommodation demand resisted the shock better; foreign demand rebounded faster.