Whenever possible, standard methodological approaches should be applied in the design and analysis of a clinical trial that warrant adequate informative value. However, there are circumstances when the number of experimental subjects is unavoidably small. In such circumstances it is justified to consider abandoning standard statistical methodology in place of alternative approaches. Performing a small clinical trial however it should be pointed out, that a such trial can never be as meaningful and provide as much evidence as a larger trial. In the present text, basic concepts are presented, that apply to small clinical trials in general. Moreover, several specific methodological approaches are presented, that either enhance the efficiency of standard statistical procedures or evolve from the idea of abandoning classical paradigms in the design and analysis of clinical trials. Within the scope of the former approach, (Bayesian) adaptive randomisation, group sequential (adaptive) designs, repeated measurement designs for longitudinal data, and meta-analyses are illustrated and discussed. The latter approach comprises alternative strategies such as (non-randomised) risk-based allocation designs, statistical prediction designs, ranking and selection designs, as well as the application of Bayesian statistics.