When evaluating the significance of calendar effects, such as those associated with Monday and January, it is necessary to control for all possible calendar effects to avoid spurious results. The downside of having to control for a large number of possible calendar effects is that it diminish the power and makes it harder to detect real anomalies. This paper contributes to the discussion of calendar effects and their significance. We derive a test for calendar specific anomalies, which controls for the full space of possible calendar effects. This test achieves good power properties by exploiting a particular correlation structure, and its main advantage is that it is capable of producing data-mining robust significance. We apply the test to stock indices from Denmark, France, Germany, Hong Kong, Italy, Japan, Norway, Sweden, UK, and USA. Our findings are that calendar effects are significant in most series, and it is primarily end-of-the-year effects that exhibit the largest anomalies. In recent years it seems that the calendar effects have diminished except in small cap stock indices.