This chapter considers factors that contribute to poor scientific quality in the design and conduct of research: bias and threats to validity. It reviews strategies to avoid bias in research methodologies that greatly influence the evidence base and clinical practice: randomised controlled trials (RCTs); single-case designs; systematic reviews; and clinical practice guidelines. The chapter describes a systematic review of the evidence for the effectiveness of computerised cognitive rehabilitation interventions. It focuses on the biases that have greatest pertinence to neuropsychological rehabilitation. The RCT is widely regarded as the 'gold standard' research design because of its capacity to minimise the risk of bias in the experimental design. The main, but not the only, strategies to reduce risks of bias in the RCT are randomisation and blinding, which are sufficiently powerful to control for many threats to internal validity.