Modeling Growth Trend and Forecasting Techniques for Vehicular Population in India

Abstract

Forecasting and estimation of growth in vehicular population is a sine qua non of any major transportation engineering development, requires capturing the past trend and using it to predict the future trend based on qualified assumptions, simulations and models created using explanatory variables. This work attempts to review the in vogue approaches and investigate a more contemporary approach, the Time Series (TS) Analysis. Three fundamentally different methods were explored and results from each of these analyses were collated to check for respective levels of accuracy in predicting vehicular population for the same target year. Within the scope of this study and estimation, results obtained from TS Analysis were found to be considerably more accurate than those from Trend Line Analysis and observably better than those from Econometric Analysis. To reinforce these observations and inferences drawn, a second set of analysis was done on more recent input by using AADT data from PeMS, California. Inter alia this was carried out to contrast any statistical improvement observed when doing TS analysis with rich and accurate data. With all the data sets used and locations analyzed for forecasting, the Time Series analysis technique was invariably found to be a potent tool for forecasting.

Estimating the adoption of electric vehicles: A case study of four Indian states

“…Many studies have estimated vehicular growth using various techniques, such as the econometric model, time series analysis using auto-regressive moving average, and growth factor using the Gompertz function. (Jha et al, 2013) used time series analysis and econometric model methods to forecast India's vehicular growth in the short term. (S & Raj, 2019) used the time-series econometric analysis to analyse the influence of GDP on vehicular growth in India.…”

Analysis of Forecasting Techniques for the Growth of Vehicular Population in Nepal

“…The research paper concluded that econometric and time series analyses are more accurate than trend line analyses. The study sug-gested that trend line analysis may be suitable for long-term forecasting [6]. The econometric model has vital significance in the transportation sector.…”

Basic Characteristics of Traffic on Primary Rural Roads in Serbia

“…In the period analyzed (1988 -2009) vehicle population in Serbia suffered minor changes with motorization rate more or less constant with minimal increase so major impact on road traffic occurred in drastic reduction of yearly vehicle kilometers and substantial increase of vehicle average age. Therefore, forecasting vehicle population in Serbia would be of little value (Jha et al, 2013) in analyzing traffic trends and, due to major presence of transit trips, is not applied in the analyses.…”