Khaki A.m., Moayedfar R.,
Volume 2, Issue 2 (June 2004)
Abstract
The purpose of the present study, is proposing a more flexible model comparing with linear regression model, to estimate the rate of household trip production and its prediction in the�project horizon. For this purpose, a combined model composed of poission distribution and the possible distribution of A. in the form of negative binominal distribution are used. Then the proposed model was conducted on a real case (Karaj City). Then the result of model processinghas been compared to .the real observation in the peak hours in Karaj city.
A. Mansour Khaki, Sh. Afandizadeh, R. Moayedfar,
Volume 7, Issue 3 (Sept. 2009)
Abstract
Household trip production is not a constant parameter and vary based on socio-economic characteristics.
Even households in each category (households with constant socio-economic characteristics) produce several numbers
of trips. Purpose of present study is to model the variation of household trip production rate in urban societies. In order
to do this, concept of the Bayesian Inference has been used. The city of Isfahan was selected as case study. First,
likelihood distribution function was determined for number of household trips, separating odd and even trips. In order
to increase precision of the function, the composed likelihood distribution function was utilized. To insert households’
socio-economic variables in the process, disaggregate 2 calibrated model were used at the likelihood distribution
function. Statistical indices and 2 test show that likelihood distribution function of numbers of household trip
production follows the Poisson distribution. The final composed likelihood distribution was determined based on
Bayesian inference. Related function was created with compilation of mean parameter distribution function (Gamma
distribution) and numbers of household trip production (Poisson distribution). Finally, disaggregate model was put at
final composed probability function instead of mean parameter. Results show that with Bayesian inference method, it
would be possible to model the variation of household trip production rate in urban societies. Also it would be possible
to put socio-economic characteristics in the model to predict likelihood of real produced trips (not average produced
trips) for each household's category.
