Abstract
Recently car trip generation and attraction data have been accumulated for some periods and we have more chance to develop new trip estimating methods using time series data. This paper examines the temporal stability of parameteres estimated in regression equations of trip generation and attraction with use of 4 time periods and 52 zone data in Kinki region.
New forecating equations which introduce temporal variables and have parameters estimated by pooling data analysis are proposed. It is shown that the volume of error between forecasted and actual car trips in the case of the new equations is much less than that in the case of the former equations where parameters are estimated using only one time data.
