On the Robustness of the Balance Statistics with respect to Nonresponse

Business cycle indicators based on the balance statistics are a widely used method tomonitor the actual economic situation. In contrast to official data, indicators frombusiness surveys are early available and typically not revised after their first publication.But as surveys can be in general affected by distortions through the response behaviour,these indicators can also be biased. In addition, time-dependent nonresponse patternscan produce even more complex forms of biased results. This paper examines aframework which kind of nonresponse patterns lead to biases and decreases in performance.We perform an extensive Monte Carlo study to analyse their effects on the indicators.Our analyses show that these indicators are extremely stable towards selection biases.