This paper investigates the impact of temporally aggregated data on the power and significance level of Ramsey’s RESET test, which is commonly used to assess the functional form of a model by examining nonlinear relationships. Through Monte Carlo techniques, we analyze the influence of temporal aggregation on the effectiveness of the test. Our findings demonstrate that temporal aggregation significantly affects both the power and significance level of the test, potentially leading to distortions in detecting nonlinear relationships and erroneous conclusions about model specifications. However, empirical analysis reveals that the effect of temporal aggregation on the RESET test varies across different pairs of stock market indexes and temporal aggregation levels. This underscores the importance of carefully considering the choice of stock market indexes and the level of temporal aggregation when conducting the RESET test, ensuring the accuracy and reliability of empirical research employing this statistical test.