THE INFLUENCE OF SIGNAL VARIATION, BIAS, NOISE AND EFFECT SIZE ON STATISTICAL SIGNIFICANCE IN TREATMENT STUDIES OF THE COMMON COLD

Many groups are working on new and improved methods of common cold tre atment that include antivirals, synthetic viral receptor, compounds wh ich block symptom pathways, and combinations of these approaches. Beca use the common cold syndrome is in large part subjective, symptom meas urement remains an important parameter in evaluating the effectiveness of cold treatments. This review examines the features of the experime ntal and natural cold testing methods that effect recognition of illne ss signal and influence its variance and strength. Also, the importanc e of changes in signal variance and in the magnitude of therapeutic ef fect size as they relate to statistical probability were compared usin g a symptom data set from young adults with experimental rhinovirus co lds.