According to the real business cycle theory, business cycles mainly result from random exogenous shocks. In this paper, this argument is tested. I extend the Wald–Wolfowitz runs test under the assumption that a recession lasts for two periods at least and an expansion lasts for $k$ periods at least with k ≥ 2. I apply the extended runs test to the three two-valued data recession-expansion series generated by the National Bureau of Economic Research and the Center for Economic and Policy Research. The test results reject the null hypothesis that they are generated in a random way for any $k$ even at the 1% significance level.

A selection of ten uni- and multivariate, nonparametric statistical methods thought to be useful for assessing trends in indicators estimated from trawl surveys is described. Nonparametric methods make minimal assumptions about the data and can therefore be suitable when parametric modelling methods, as typically preferred by fisheries scientists, are not suitable. The various methods described are sensitive to a variety of specific features of a trend thereby allowing many different forms of variation over time to be identified, e.g. changes in level, sloping straight or curved lines, and differing cyclicities. In contrast, model-based investigations can be constrained in this regard if the single model which is adopted and fitted to the trend is a simplification of its form.