1. Reporting stanbeen well conceived and well conducted2-estimates of the magnitude of selective whatever their results-represent positive publication biases if the exciting new possibilidards and research strategies for controlled trials: agenda for the editor. Controlled Clinical Trials 1980; 1: 37-58. contributions to knowledge. I suspect that the concept of a negative trial ties presented by "meta-analyses" of data pooled from independently mounted;Mosteller, F.; Gilbert, J.P.; McPeek, B.
2. A proposal for a new editorial policy in the Social Sciences;Walster, W.; Clearly, T.A.;The American, Statistician,1970