Beyond Weeks Closed: Reassessing Pandemic Educational Disruption with TIMSS 2003–2023

Using six TIMSS cycles (2003–2023), UNESCO school-closure data, and World Bank GDP indicators, we estimate deviation-from-trend and continuous-treatment Difference-in-Differences models for mathematics achievement, liking learning mathematics, and confidence in mathematics. Mathematics achievement declined substantially relative to pre-pandemic trends, but closure duration did not consistently explain cross-national variation in achievement losses. Unexpectedly, longer closures were associated with slightly higher liking learning mathematics, particularly among Grade 4 students in higher-GDP countries, while confidence in mathematics remained largely unchanged. These findings suggest a decoupling of cognitive and affective outcomes during the pandemic and indicate that school-closure duration alone is an insufficient measure of educational harm. Comparative evaluations of pandemic education policies should therefore incorporate indicators of instructional continuity, remote-learning quality, and recovery efforts alongside formal school-closure measures.