Familial and sporadic schizophrenia. A simulation study of statistical power

The importance of genetic factors in schizophrenia is clear but the mechanism involved remains obscure. Etiological heterogeneity may be responsible. Recently there has been interest in a putative distinction between genetic and environmental forms of the illness based on a positive or negative family history of the disorder. Those with a positive family history are classified as 'familial' and are considered to be more likely to have the genetic form of the illness. Those with a negative family history are classified as 'sporadic' and considered more likely to have an environmental form of the illness. This paper reports the results of a Monte Carlo simulation study with varying rates of misclassification to determine the statistical power of comparisons between familial and sporadic groups. For a large sample (n = 175) statistical power was moderate to good for effect sizes greater than or equal to 1.0 standard deviation unit and positive predictive value of 0.3 or greater.