PREDICTING TELEVISION EXTREME VIEWERS AND NONVIEWERS - A NEURAL NETWORK ANALYSIS

In an attempt to better understand the attributes of the ''average'' v iewer, an analysis of the data characterizing television nonviewers an d extreme viewers was performed, The data were taken from the 1988, 19 89, and 1990 General Social Surveys, conducted by the National Opinion Research Center The authors performed a neural network analysis and d iscuss the significance of the findings. For comparison, a discriminan t analysis was also performed and is shown to be outperformed by the n eural network, Furthermore, the set of demographic variables were iden tified as the strongest predictor of nonviewers, and the combination o f family-related and lifestyle/social-activity-related variables were the strongest attribute of extreme viewers.