This report is the third in series in which data sets gathered by others are revisited. The first dealt with conversion from two-way to four-way stop control in San Francisco (Hauer, Lovell and Persuad, 1984); the second uses data from Philadelphia (Persaud, 1984). By now, a certain routine has been established in content, style and method. The only new element here has been the need to come to grips with "before" and "after" periods of unequal length which may also vary from site to site. In consequence, equation 2 is a generalization of its previous versions. We have one more data set to examine - from the City of Toronto. When the analysis of this remaining data set is complete, the stage will be set for the final step - the aggregation of several likelihood functions into one coherent estimate. (Author/publisher)
Abstract