CONTENTS 3.1 Detecting Patterns and Assessing Their Significance 28 3.2 Assessing Causality 30 3.3 Correlation versus Dependence 31 3.4 Probability in Science 32 3.5 Cosmic Variance 33 Appendix: Tales of Statistical Malfeasance 34 References 36
Statistical issues peculiar to astronomy have implications for machine learning and data mining. It should be obvious that statistics lies at the heart of machine learning and data mining. Further it should be no surprise that the passive observational nature of astronomy, the concomitant lack of sampling control, and the uniqueness of its realm (the whole universe!) lead to some special statistical issues and problems.