Levels of demand over time are analyzed for five modes of passenger transportation. The data are for the modes: car driver, car passenger, train, bicycle, and public transit. These data are compiled from week-long travel diaries collected at six-month intervals from a nationwide panel in the Netherlands. Three types of empirical relationships are present in these panel data: (1) autocorrelative relationships, capturing temporal stability in demand for the same mode at different points in time; (2) contemporaneous relationships, capturing complementarity and competition among different modes at the same point in time; and (3) cross-lagged effects, potentially capturing systematic shifts in demand. Simultaneous equation systems are used to test the temporal stability of demand for each mode and the stationarity of the contemporaneous relationships among the modes. The dynamic structure both of trip rates and of travel times are modeled successfully according to several goodness-of-fit indices. The equation systems capture nonstationarity in the contemporaneous relationships, as well as important cross-lagged effects. These results quantify changes in the structure of demand over time in the Netherlands and are shown to be directly related to the event of a public transit fare increase.
Get full access to this article
View all access options for this article.
References
1.
AndersonT WRubinH, 1956, “Statistical inference in factor analysis”Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability (University of California Press, Berkeley, CA) pp 111–150
2.
BaandersASlootmanK C P, 1982, “A panel for longitudinal research into travel behavior” in Recent Advances in Travel Demand Analysis Eds CarpenterSJonesP MGower, Aldershot, Hants) pp 450–461
3.
BentlerP MBonettD G, 1980, “Significance tests and goodness of fit in the analysis of covariance structures”Psychological Bulletin88588–606
4.
BielbyW THauserR M, 1977, “Structural equation models”Annual Review of Sociology3137–161
5.
BoomsmaA, 1982aOn the Robustness of LISREL Against Small Sample Sizes and Non-normality PhD dissertation, University of Groningen, Broerstraat 5, PO Box 72, 9700 AB Groningen, The Netherlands
6.
BoomsmaA, 1982b, “The robustness of LISREL against small sample sizes in factor analysis models”, in Systems Under Indirect Observation: Causality, Structure, Prediction (Part I) Eds JöreskogK GWoldHNorth-Holland, Amsterdam) pp 149–173
7.
BrowneM W, 1974, “Generalized least-squares estimators in the analysis of covariance structures”South African Statistical Journal81–24
8.
CampbellD T, 1963, “From description to experimentation: Interpreting trends as quasi-experiments”, in Problems in Measuring Change Ed. HarrisC WUniversity of Wisconsin Press, Madison, WI) pp 81–105
9.
DuncanO D, 1975Introduction to Structural Equation Models (Academic Press, New York)
10.
GeraciV J, 1976, “Identification of simultaneous equation model with measurement error”Journal of Econometrics4263–283
11.
GlasserM, 1964, “Linear regression models with missing observations among the independent variables”Journal of the American Statistical Association59834–844
12.
GoldbergerA S, 1964Econometric Theory (John Wiley, New York)
GolobJ MSchreursL J MSmitJ G, 1986, “The design and policy applications of a panel for studying changes in mobility over time”, in Behavioral Research for Transport Policy (VNU Science Press, Utrecht) pp 81–96
15.
GolobT FMeursH, 1986, “Biases in response over time in a seven-day travel diary”Transportation13163–181
16.
GolobT FMeursH, 1987, “A structural model of temporal change in multi-mode travel demand”Transportation research21A391–400
17.
GolobT Fvan WissenLGolobJ M, 1985, “A panel-data analysis of the dynamics of transport mode use”, in Proceedings of the PTRC Summer Annual Meeting, University of SussexPTRC Education and Research Services, London WC2R 0AA; pp 15–25
18.
GolobT Fvan WissenLMeursH, 1986, “A dynamic analysis of travel demand”Transportation Research A20401–414
19.
HeiseD R, 1970, “Causal inference from panel data”, in Sociological Methodology Eds BorgattaE FBohrnstedtG WJossey-Bass, San Francisco, CA) pp 3–27
20.
HeiseD R, 1975Causal Analysis (John Wiley, New York)
21.
van der HoornTKitamuraR, 1987, “Evaluation of the predictive accuracy of cross- sectional and dynamic trip generation models using panel data”, paper presented at the Annual Meeting of the Transportation Research Board, Washington, DC, 12–15 January; Transportation Research Record (forthcoming)
22.
JöreskogK G, 1967, “Some contributions to maximum likelihood factor analysis”Psychometrika32443–482
23.
JöreskogK G, 1973, “A general method for estimating a linear structural equation system”, in Structural Equation Models in the Social Sciences Eds GoldbergerA SDuncanO DSeminal Press, New York) pp 85–112
24.
JöreskogK G, 1977, “Structural equations models in the social sciences: Specification, estimation and testing” in Applications of Statistics Ed. KrishnaiahP RNorth-Holland, Amsterdam) pp 265–287
25.
JöreskogK GSörbomD, 1984LISREL VI User's GuideScientific Software, Mooresville, IN 46158–536
26.
KennyD A, 1973, “Cross-lagged and synchronous common factors in panel data”, in Structural Equation Models in the Social Sciences Eds GoldbergerA SDuncanO DSeminar Press, New York) pp 887–903
27.
KennyD AHarackiewiczJ M, 1979, “Cross-lagged panel correlation: Practice and promise”Journal of Applied Psychology64372–379
28.
KitamuraRBovyP H L, 1987, “Attrition and trip reporting errors for the panel data”Transportation Research21A287–302
29.
KitamuraR, 1986, “Linear panel analysis of travel behavior”, report prepared for Dienst Verkeerskunde, Rijkswaterstaat, Ministerie van Verkeer en Waterstaat (Traffic Analysis Division, Department of Public Works, Ministry of Transport and Public Works), The Hague, The Netherlands
30.
LeeS Y, 1977Some Algorithms for Covariance Structure Analysis PhD dissertation, University of California, Los Angeles, CA90024 (University microfilm number 77–17, 230)
31.
MaddalaG S, 1971, “The use of variance components models in pooling cross sectional and time series data”Econometrica39341–358
32.
MariniM MOlsenA RRubinD B, 1980, “Maximum-likelihood estimation in panel studies with missing data”, in Sociological Methodology Ed. LeinhardtSJossey-Bass, San Francisco, CA) pp 314–357
33.
MeursHKlokM, 1985, “Het gebruik van longitudinale paneldata in verkeersen vervoerstudies [Use of longitudinal panel data in traffic and transportation studies]”, in Colloquium Vervoersplanologisch Speurwerk Ed. ClercqF; pp 737–760
34.
PierceD A, 1977, “Relationships—and the lack thereof—between economic time series”Journal of the American Statistical Association7211–22
35.
PierceD AHaughL D, 1977, “Causality in temporal systems: Characterizations and a survey”Journal of Econometrics5265–293
36.
RogosaD, 1980, “A critique of cross-lagged correlation”Psychological Bulletin88245–258
37.
RozelleR MCampbellD T, 1969, “More plausible rival hypotheses in the cross-lagged panel correlation technique”Psychological Bulletin7174–80
38.
RubinD B, 1974, “Characterizing the estimation of parameters in incomplete-data problems”Journal of the American Statistical Association69467–474
39.
SewellW HHauserR M, 1975Education, Occupation and Earnings (Academic Press, New York)
40.
SuchmanE A, 1962, “Analysis of ‘bias’ in survey research”Public Opinion Quarterly26102–111
41.
TaubmanPWalesT, 1974Higher Education and Earnings (McGraw-Hill, New York)
42.
van WissenLZondagE, 1985, “Analyse van veranderingen in gebruik van vervoermiddelen met behulp van panelgegevens [Analysis of change in use of modes using panel data]”, in Colloquium Vervoersplanologisch Speurwerk Ed. ClercqF; pp 717–736
43.
YeeA HGageN L, 1968, “Techniques for estimating the source and direction of causal inference in panel data”Psychological Bulletin70114–126
