Northern Japanese children tend to have larger physiques; however, the underlying cause remains unknown. Previous geographical correlation analyses revealed an unusual trend; effective day length was negatively correlated with height and positively correlated with weight (adjusted for height). This paradoxical relationship suggests a thyroid hormone-like effect and possible photoperiodic response. This study aimed to determine whether this phenomenon remains consistent over time and across different regions of Japan. We used geographically and temporally weighted regression (GTWR) to examine whether the relationship between height and effective day length, which differs from the relationship between weight and effective day length, varies by location and time. GTWR models each observation point separately, allowing for spatial and temporal variations. The analysis included the average height and weight data of children and adolescents by prefecture from 1989 to 2019, along with effective day length considering illuminance above 5000 lx derived from the agrometeorological grid square data. Height was used as the dependent variable, whereas weight and effective day length were used as independent variables. For height estimation, the coefficients of weight and effective day length were consistently positive and negative, respectively, although the regression coefficients showed minor geographical and temporal variations. The opposite correlation between height and effective day length and that between weight and effective day length were consistent. This suggests that the phenomenon is more likely driven by environmental factors than by economic or genetic influences.