Levels of evidence in studies of competition, predation, and disease

The primary aim of a scientific investigation is to find the most likely model for a situation out of a host of alternative explanations. The strength of evidence provided by anecdote, logical argument, mathematical modelling, observation, and designed studies (manipulative and observational) are discussed and the effectiveness of randomisation and orthogonal designs in separating hypotheses compared. Pseudoreplication is shown to be often misunderstood. It consists of two concepts: the importance of adequate replication and the independence of the sampling units. While replication is necessary to separate out the effects of different factors and to provide an error term for inference, contrary to popular belief independence of sampling units is not necessary. Finally the interpretation of evidence is discussed and the distinction made between formal and informal generalisation to a population.