THE PROBLEM OF MISSING CLINICAL-DATA FOR RESEARCH IN PSYCHOPATHOLOGY - SOME SOLUTION GUIDELINES

There are no guidelines to help psychiatric researchers statistically adjust for missing data. We discuss the problems resulting from missin g values, and illustrate some of them with examples from our work. Usi ng structured instruments, we obtained clinical information from 241 p atients. Some instrument items were not rated, and these did not occur randomly: hallucinations and delusions were most frequently unrated, especially in chronic schizophrenics, and patients with high scores fo r other psychopathology. Systematically assigning an intermediate valu e between present and absent to nonrated items was a satisfactory solu tion, unaffected by nonrandom missing values. This simple solution was equivalent to a complicated one (vectoring) in discriminating patient s. When relationships between variables are linear, we recommend the i ntermediate value method as a practical solution to missing values. We stress that missing values do not mean missing information, and the m ost common response to missing values (dropping subjects) is least inf ormative.