#### DMCA

## Recent methodological advances relevant to activity and travel behavior analysis, paper presented at (1997)

Venue: | International Association of Travel Behavior Research Conference |

Citations: | 22 - 5 self |

### Citations

2385 |
Conditional logit analysis of qualitative choice behavior. In: Zarembka P (ed.) Frontiers in Econometrics.
- McFadden
- 1974
(Show Context)
Citation Context ...random components of the utilities of thesdifferent alternatives in the MNL model are assumed to be independent and identicallysdistributed (IID) with a type I extreme-value (or Gumbel) distribution (=-=McFadden, 1973-=-). ThesMNL model also maintains an assumption of homogeneity in responsiveness to attributes ofsalternatives across individuals (i.e., an assumption of response homogeneity). For example, in asmode ch... |

2037 |
Limited–dependent and qualitative variables in econometrics,
- Maddala
- 1983
(Show Context)
Citation Context ...smodels (this situation is analogous to the difference between a general endogenous switchingsregression equation system and the more restrictive disequilibrium market model of demand andssupply; see =-=Maddala, 1983-=-, page 308).sBhat (1996c) considers a generalization of the Han and Hausman competing risksspecification where the exit state is modeled explicitly and jointly with duration models for eachspotential ... |

1148 |
Discrete Choice Analysis: Theory and Application to Travel Demand.
- Ben-Akiva, Lerman
- 1985
(Show Context)
Citation Context ...t closed-form mathematical structure of the MNL. However, thesesassumptions also leave the MNL model saddled with the “independence of irrelevantsalternatives” (IIA) property at the individual level (=-=Ben-Akiva and Lerman, 1985-=-).1 In the nextsthree sections, we will discuss generalizations of the MNL structure along each of the threesdimensions mentioned above: a) Relaxation of the IID (across alternatives) error structure,... |

1067 |
Advanced Econometrics
- Amemiya
- 1985
(Show Context)
Citation Context ...far, most of the attention to date has focused on thesdichotomous case (see Heckman, 1976 and Lee, 1981 for estimation methods and Willis andsRosen, 1980 and Sakamoto and Chen, 1991 for applications; =-=Amemiya, 1985-=- and Maddala, 1983sprovide a review of economic applications, while Winship and Mare, 1992 provide a review ofssociological applications). In contrast to the dichotomous case, the polychotomous case h... |

931 |
The Common Structure of Statistical Models of Truncation, Sample Selection, and Limited Dependent Variables and a Simple Estimator for Such Models.”
- Heckman
- 1976
(Show Context)
Citation Context ...e decision. The first category is the dichotomous alternative case and the second is thespolychotomous alternative case. By far, most of the attention to date has focused on thesdichotomous case (see =-=Heckman, 1976-=- and Lee, 1981 for estimation methods and Willis andsRosen, 1980 and Sakamoto and Chen, 1991 for applications; Amemiya, 1985 and Maddala, 1983sprovide a review of economic applications, while Winship ... |

810 | Analysis of Survival Data, - Cox, OAKEs - 1984 |

587 |
Analysis of Covariance with Qualitative Data.”
- Chamberlain
- 1980
(Show Context)
Citation Context ...eity) across individuals. In particular, if the assumption ofshomogeneity is imposed when there is heterogeneity, the result is biased and inconsistentsparameter and choice probability estimates (see =-=Chamberlain, 1980-=-).sResponse homogeneity may be relaxed in one of two ways. In the first approach (whichswe will refer to as the varying coefficients approach), the coefficients on alternative attributes aresallowed t... |

547 |
Economic Duration Data and Hazard Functions.
- KIEFER
- 1988
(Show Context)
Citation Context ...deally suited to modeling duration data. Such models focusson an end-of-duration occurrence (such as end of shopping activity participation) given that thesduration has lasted to some specified time (=-=Kiefer, 1988-=-; Hensher and Mannering, 1994). Thissconcept of conditional probability of “failure” or termination of activity duration recognizes thesdynamics of duration; that is, it recognizes that the likelihood... |

344 | An econometric analysis of residential electric appliance holdings and consumption. - Dubin, McFadden - 1984 |

276 |
Regression analysis of grouped survival data with application to the breast cancer data.
- Prentice, Gloeckler
- 1978
(Show Context)
Citation Context ...zard parameters (also sometimes referred to as the incidental or nuisancesparameters) simultaneously (the Han and Hausman approach is an alternative formulation of thesapproach originally proposed by =-=Prentice and Gloeckler, 1978-=- and extended by Meyer, 1987).sBetween the Cox and Han and Hausman (HH) approaches, the HH approach has manysadvantages. First, in many studies, the dynamics of duration is itself of direct interest; ... |

272 |
Unemployment insurance and unemployment spells.
- Meyer
- 1990
(Show Context)
Citation Context ...s have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametric heterogeneity specifications(see Gupta, 1991, Manston et al., 1986, =-=Meyer, 1990-=-, Han and Hausman, 1990, all of whom usesa gamma distribution). Very few studies have adopted a nonparametric heterogeneity distributions(see Jain and Vilcassim, 1991 and Vilcassim and Jain, 1991).sAm... |

270 | Generalized econometric models with selectivity.
- Lee
- 1983
(Show Context)
Citation Context ...de a review ofssociological applications). In contrast to the dichotomous case, the polychotomous case hassreceived much lesser attention (see Hay 1980, Dubin and McFadden 1983, Hanemann 1984, ands32s=-=Lee 1983-=- for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and Mannering and Winston 1985 for applications;sMannering and Hensher, 1987 provide a r... |

234 | Forecasting New Product Penetration with Flexible Substitution Patterns.
- Brownstone, Train
- 1996
(Show Context)
Citation Context ... a normal distribution for the randomscomponents and the latter is appropriate for various extensions of the multinomial logit structures(see Chib and Greenberg, 1996, Hajivassiliou et al., 1996, and =-=Brownstone and Train, 1996-=- forsreviews of such simulation techniques). The underlying concept in such methods is tosapproximate the integration by computing the integrand at various values drawn from thesappropriate multi-vari... |

178 | New Methods for Analyzing Structural Models of Labor Force Dynamics,”
- Flinn, Heckman
- 1982
(Show Context)
Citation Context ...sestimates of the covariate effects (Heckman and Singer, 1984; Lancaster, 1985; Sharma, 1987).sThe standard procedure used to control for unobserved heterogeneity is the randomseffects estimator (see =-=Flinn and Heckman, 1982-=-). This involves specification of a distribution forsthe unobserved heterogeneity (across individuals) in the population. Two general approachessmay be used to specify the distribution of unobserved h... |

160 |
Discrete/continuous models of consumer demand.
- Hanemann
- 1984
(Show Context)
Citation Context ...p and Mare, 1992 provide a review ofssociological applications). In contrast to the dichotomous case, the polychotomous case hassreceived much lesser attention (see Hay 1980, Dubin and McFadden 1983, =-=Hanemann 1984-=-, ands32sLee 1983 for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and Mannering and Winston 1985 for applications;sMannering and Hensher,... |

153 | Markov chain Monte Carlo simulation methods in econometrics.
- Chib, Greenberg
- 1996
(Show Context)
Citation Context ...formersis suitable for discrete-choice structures that use a normal distribution for the randomscomponents and the latter is appropriate for various extensions of the multinomial logit structures(see =-=Chib and Greenberg, 1996-=-, Hajivassiliou et al., 1996, and Brownstone and Train, 1996 forsreviews of such simulation techniques). The underlying concept in such methods is tosapproximate the integration by computing the integ... |

144 |
Simulation of Multivariate Normal Rectangle Probabilities and their Derivatives: Theoretical and Computational Results”,
- HAJIVASSILIOU, McFADDEN, et al.
- 1996
(Show Context)
Citation Context ...crete-choice structures that use a normal distribution for the randomscomponents and the latter is appropriate for various extensions of the multinomial logit structures(see Chib and Greenberg, 1996, =-=Hajivassiliou et al., 1996-=-, and Brownstone and Train, 1996 forsreviews of such simulation techniques). The underlying concept in such methods is tosapproximate the integration by computing the integrand at various values drawn... |

98 |
A dynamic empirical analysis of household vehicle ownership and utilization.
- Mannering, Winston
- 1985
(Show Context)
Citation Context ...ser attention (see Hay 1980, Dubin and McFadden 1983, Hanemann 1984, ands32sLee 1983 for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and =-=Mannering and Winston 1985-=- for applications;sMannering and Hensher, 1987 provide a review of transportation-related applications). Almostsall applications of the dichotomous case have used either a logit or probit approach to ... |

86 |
Stated preference analysis of travel choices: the state of practice,
- Hensher
- 1994
(Show Context)
Citation Context ...ince it does not impose a prior probability distribution.sApplication of duration models in the transportation field have, for the most part, ignoredsunobserved heterogeneity (but see Bhat, 1996b and =-=Hensher, 1994-=-b). Researchers in thesmarketing and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametric heterogeneity sp... |

82 |
Accommodating Variations in Responsiveness to Level-of-Service Variables in Travel Mode Choice Modeling,
- Bhat
- 1998
(Show Context)
Citation Context ...ent estimation since it does not impose a prior probability distribution.sApplication of duration models in the transportation field have, for the most part, ignoredsunobserved heterogeneity (but see =-=Bhat, 1996-=-b and Hensher, 1994b). Researchers in thesmarketing and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametr... |

74 |
Multinomial Probit: The Theory and its Application to Demand Forecasting,
- Daganzo
- 1979
(Show Context)
Citation Context ...istributed random componentssThe concept that heteroscedasticity in alternative error terms (i.e., independent, but notsidentically distributed error terms) relaxes the IIA assumption is not new (see =-=Daganzo, 1979-=-),sbut has received little (if any) attention in travel demand modeling and other fields. In fact, thesIIA property has become virtually synonymous with the assumption of lack of similarity (orsindepe... |

72 |
Investigating Household Purchase Timing Decisions: A Conditional Hazard Function Approach,”
- ain, Vilcassim
- 1991
(Show Context)
Citation Context ...cations(see Gupta, 1991, Manston et al., 1986, Meyer, 1990, Han and Hausman, 1990, all of whom usesa gamma distribution). Very few studies have adopted a nonparametric heterogeneity distributions(see =-=Jain and Vilcassim, 1991-=- and Vilcassim and Jain, 1991).sAmong the duration studies mentioned above, Bhat (1996b) uses a nonparametricsbaseline hazard (based on the Han and Hausman approach) and a nonparametric unobservedshet... |

70 |
A method for minimizing the distributional assumptions in econometric models for duration data
- Heckman, Singer
- 1984
(Show Context)
Citation Context ...nce durations. It is well established now that failure to control forsunobserved heterogeneity can produce severe bias in the nature of duration dependence and thesestimates of the covariate effects (=-=Heckman and Singer, 1984-=-; Lancaster, 1985; Sharma, 1987).sThe standard procedure used to control for unobserved heterogeneity is the randomseffects estimator (see Flinn and Heckman, 1982). This involves specification of a di... |

65 | On using demographic variables to determine segment membership in logit mixture models. - Gupta, PK - 1994 |

65 | What do we really know about wages? The importance of nonreporting and Census imputation. - Lillard, Smith, et al. - 1986 |

64 | Concomitant-Variable Latent-Class Models," - Dayton, MacReady - 1988 |

61 |
A discrete choice model for ordered alternatives,”
- Small
- 1987
(Show Context)
Citation Context ... just discussed can be formulated by using the multinomial logit (MNL)sformulation for the higher-level mode choice decision and the standard ordered generalizedsextreme-value (OGEV) formulation (see =-=Small, 1987-=-) for the lower-level departure time choicesdecision (i.e., the MNL-OGEV model). The MNL-OGEV structure, in the context of the modedeparture time example, has two dissimilarity parameters: one is asso... |

59 |
Multinomial probit with a logit kernel and a general parametric speci®cation of the covariance structure, MIT Working Paper
- Ben-Akiva, Bolduc
- 1996
(Show Context)
Citation Context ... to be positive. Thus, the normalization ofswhich pair to select as the base is not innocuous; the base pair should be the one with leastscovariance, which of course we do not know a priori (see also =-=Ben-Akiva and Bolduc, 1996-=- forsa related discussion). Thus, in general, we have to impose a restrictive structure for thescovariance patterns based on a priori theoretical considerations.s13sThe general multinomial probit (MNP... |

56 | The retirement and Unemployment Behavior of older men” - Diamond, Housman - 1984 |

51 |
Modeling travelers’ postwork activity involvement: toward a new methodology,”
- Hamed, Mannering
- 1993
(Show Context)
Citation Context ...ous case hassreceived much lesser attention (see Hay 1980, Dubin and McFadden 1983, Hanemann 1984, ands32sLee 1983 for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, =-=Hamed and Mannering 1993-=-, and Mannering and Winston 1985 for applications;sMannering and Hensher, 1987 provide a review of transportation-related applications). Almostsall applications of the dichotomous case have used eithe... |

49 |
Improved Multiple Choice Models,”
- Daly, Zachary
- 1978
(Show Context)
Citation Context ...s (each alternative can be assigned to one and only one nest). Alternativessin a nest exhibit an identical degree of increased sensitivity relative to alternatives not in the nests(Williams, 1977 and =-=Daly and Zachary, 1978-=-). Each nest in the NL structure has associated withsit a dissimilarity (or logsum) parameter that determines the correlation in unobservedscomponents among alternatives in that nest (see Daganzo and ... |

43 | A hazard-based duration model of shopping activity with nonparametric baseline specification and nonparametric control for unobserved heterogeneity,”
- Bhat
- 1996
(Show Context)
Citation Context ...ent estimation since it does not impose a prior probability distribution.sApplication of duration models in the transportation field have, for the most part, ignoredsunobserved heterogeneity (but see =-=Bhat, 1996-=-b and Hensher, 1994b). Researchers in thesmarketing and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametr... |

42 |
A Random-Coefficients Logit Brand-Choice Model Appli.
- Jain, Vilcassim, et al.
- 1994
(Show Context)
Citation Context ...on).s7 In concept, the endogenous segmentation approach is equivalent to a random-coefficientssapproach with non-parametric discrete probability distributions for the heterogeneitysspecification (see =-=Jain et al., 1994-=- and Chintagunta and Honore, 1996).s20s2.3.1.sVariance relaxationsSwait and Adamowicz (1996) formulate a heteroscedastic multinomial logit (HMNL) model thatsallows the variance of alternatives to vary... |

39 | Accommodating Flexible Substitution Patterns in Multidimensional Choice Modeling: Formulation and Application to Travel Mode and Departure Time Choice
- Bhat
- 1998
(Show Context)
Citation Context ...es. This structure is less restrictive than the nested logit structure in thatsan alternative can belong to more than one group. Also, by structure, the variance of thesalternatives is different (see =-=Bhat, 1997-=-b for application of this structure to a multi-dimensionalschoice context).6 More general structures for izµ′sin equation (1) are presented by Ben-Akivasand Bolduc (1996) and Brownstone and Train (199... |

36 |
Modeling multiple sources of heterogeneity in multinomial logit models: methodological and managerial issues. Mark Sci (Summer)
- Gonul, Srinivasan
- 1993
(Show Context)
Citation Context ...rm and log-normally distributed if one uses the secondsform. Applications of random response heterogeneity include Fisher and Nagin, 1985, Reveltsand Train, 1996, Train, 1996, Ben-Akiva et al., 1993, =-=Gonül and Srinivasan, 1993-=-, andsMehndiratta, 1996. The qkvsterms in the random response heterogeneity specification representsthe random tastes of person q and are common to the utility of all alternatives i. Therefore,svarian... |

35 | Imputing a continuous income variable from grouped and missing income observations - Bhat - 1994 |

35 | GIS and spatial analytical problems. - Fotheringham, Rogerson - 1993 |

34 | Analysis of travel mode and departure time choice for urban shopping trips,”
- Bhat
- 1998
(Show Context)
Citation Context ...es. This structure is less restrictive than the nested logit structure in thatsan alternative can belong to more than one group. Also, by structure, the variance of thesalternatives is different (see =-=Bhat, 1997-=-b for application of this structure to a multi-dimensionalschoice context).6 More general structures for izµ′sin equation (1) are presented by Ben-Akivasand Bolduc (1996) and Brownstone and Train (199... |

34 | An Endogenous Segmentation Mode Choice Model with an Application to Intercity Travel.
- Bhat
- 1997
(Show Context)
Citation Context ...es. This structure is less restrictive than the nested logit structure in thatsan alternative can belong to more than one group. Also, by structure, the variance of thesalternatives is different (see =-=Bhat, 1997-=-b for application of this structure to a multi-dimensionalschoice context).6 More general structures for izµ′sin equation (1) are presented by Ben-Akivasand Bolduc (1996) and Brownstone and Train (199... |

33 |
Estimation of travel choice models with randomly distributed values of time’,
- Ben-Akiva, Bolduc, et al.
- 1993
(Show Context)
Citation Context ...if one uses the first form and log-normally distributed if one uses the secondsform. Applications of random response heterogeneity include Fisher and Nagin, 1985, Reveltsand Train, 1996, Train, 1996, =-=Ben-Akiva et al., 1993-=-, Gonül and Srinivasan, 1993, andsMehndiratta, 1996. The qkvsterms in the random response heterogeneity specification representsthe random tastes of person q and are common to the utility of all alter... |

33 |
Two Computational Process Models of Activity-Travel Behavior.
- Kitamura, Fujii
- 1998
(Show Context)
Citation Context ... models havesbeen conducted not very long ago by pioneers of the approach who are more knowledgeables2sregarding the approach than the current author (see Gärling et al., 1994; Golledge et al., 1994;s=-=Kitamura and Fujii, 1996-=-; and Kurani and Kitamura, 1996). An additional reason for notsfocusing on computation process models (CPMs) here is that while there has been considerablesadvancement in these methods, some basic iss... |

31 |
Generalised residuals and heterogeneous duration models: with applications to the Weibull model
- Lancaster
- 1985
(Show Context)
Citation Context ...established now that failure to control forsunobserved heterogeneity can produce severe bias in the nature of duration dependence and thesestimates of the covariate effects (Heckman and Singer, 1984; =-=Lancaster, 1985-=-; Sharma, 1987).sThe standard procedure used to control for unobserved heterogeneity is the randomseffects estimator (see Flinn and Heckman, 1982). This involves specification of a distribution forsth... |

30 | A generalized multiple durations proportional hazard model with an application to activity behavior during the evening work-to-home commute,”
- Bhat
- 1996
(Show Context)
Citation Context ...ent estimation since it does not impose a prior probability distribution.sApplication of duration models in the transportation field have, for the most part, ignoredsunobserved heterogeneity (but see =-=Bhat, 1996-=-b and Hensher, 1994b). Researchers in thesmarketing and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametr... |

29 | The Paired Combinatorial Logit Model: Properties, Estimation, - Koppelman, Wen - 2000 |

28 | e effects of in-store displays and feature advertising on consideration sets.International - Allenby, Ginter - 1995 |

28 |
Work travel mode choice and number of nonwork commute stops.
- Bhat
- 1997
(Show Context)
Citation Context |

28 | A Paired Combinatorial Logit Model for Travel Demand Analysis,” - Chu - 1989 |

28 |
Hazard-based duration models and their application to transport analysis,”
- Hensher, Mannering
- 1994
(Show Context)
Citation Context ...to modeling duration data. Such models focusson an end-of-duration occurrence (such as end of shopping activity participation) given that thesduration has lasted to some specified time (Kiefer, 1988; =-=Hensher and Mannering, 1994-=-). Thissconcept of conditional probability of “failure” or termination of activity duration recognizes thesdynamics of duration; that is, it recognizes that the likelihood of ending a shopping activit... |

26 | Competing risk hazard model of activity choice, timing, sequencing, and duration. In: Transportation Research Record
- Ettema, Borgers, et al.
- 1995
(Show Context)
Citation Context ...ity). The secondscategory accommodates the interdependence between a discrete choice variable and anothersrelated continuous or grouped or ordinal variable (such as the interdependence between modes9 =-=Ettema et al., 1995-=- also formulate a competing risk model to model activity duration with thestermination states being any one of several activity types such as in-home leisure,swork/education, shopping, etc. They use a... |

25 |
Alternative models for the heterogeneity of mortality risks among the aged. J Am Stat Assoc.
- KG, Stallard, et al.
- 1986
(Show Context)
Citation Context ...ng and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametric heterogeneity specifications(see Gupta, 1991, =-=Manston et al., 1986-=-, Meyer, 1990, Han and Hausman, 1990, all of whom usesa gamma distribution). Very few studies have adopted a nonparametric heterogeneity distributions(see Jain and Vilcassim, 1991 and Vilcassim and Ja... |

24 |
The Dynamics of Household Travel Time Expenditures and Car Ownership Decisions
- Golob
- 1990
(Show Context)
Citation Context ...thescontinuous measure of income that frequently appears as an explanatory variable in labor supplysmodels, market research models and travel demand models (Killingsworth 1983, Koppelman etsal. 1993, =-=Golob 1989-=-). Second, there might be systematic differences in unobservedscharacteristics affecting income between respondent and non-respondent households (orsindividuals). For example, it seems at least possib... |

22 | Establishing a fare elasticity regime for urban passenger transport: Nonconcession commuters. - Hensher - 1997 |

20 |
Dimensions of automobile demand; a longitudinal study of automobile ownership and use.
- Hensher, Barnard, et al.
- 1992
(Show Context)
Citation Context ...ions). In contrast to the dichotomous case, the polychotomous case hassreceived much lesser attention (see Hay 1980, Dubin and McFadden 1983, Hanemann 1984, ands32sLee 1983 for estimation methods and =-=Hensher et al. 1992-=-, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and Mannering and Winston 1985 for applications;sMannering and Hensher, 1987 provide a review of transportation-related applications). ... |

19 |
Covariance heterogeneity in nested logit models: Econometric structure and application to intercity travel Transportation Research Part B: Methodological
- Bhat
- 1997
(Show Context)
Citation Context |

19 |
Reconsidering the multinomial probit model
- Horowitz
- 1991
(Show Context)
Citation Context ...nterpretation, highly non-intuitive model behavior, low precision of covariancesparameter estimates, and increased difficulty in transferring models from one space-timessampling frame to another (see =-=Horowitz, 1991-=- and Currim, 1982). Further, the errorcomponents models can be estimated using simulators which are conceptually simple and easy tosprogram. These simulators involve simultaneous draws from the approp... |

19 | Modeling preference and structural heterogeneity in consumer choice. - Kamakura, Kim, et al. - 1996 |

18 | Interdependencies in activity behavior - Damm - 1980 |

17 | An Endogenous Switching Simultaneous Equation System of Employment - Bhat, Koppelman - 1993 |

17 | Random versus Fixed Coefficient Quantal Choice Models,” in Structural Analysis of Discrete Data with Econometric Applications - FISCHER, NAGIN - 1981 |

17 | Recent advances in activity-based travel demand modeling - Pas - 1996 |

16 |
Recent developments and the prospects for modeling household activity schedules. Report prepared for the Los
- Kurani, Kitamura
- 1996
(Show Context)
Citation Context ...t very long ago by pioneers of the approach who are more knowledgeables2sregarding the approach than the current author (see Gärling et al., 1994; Golledge et al., 1994;sKitamura and Fujii, 1996; and =-=Kurani and Kitamura, 1996-=-). An additional reason for notsfocusing on computation process models (CPMs) here is that while there has been considerablesadvancement in these methods, some basic issues related to statistical esti... |

15 |
A duration model of automobile ownership.
- Gilbert
- 1992
(Show Context)
Citation Context ...g risks) hassextended the univariate proportional hazard model to the case of two competing risks in one ofsthree ways. The first method assumes independence between the two risks (see Katz, 1986 ands=-=Gilbert, 1992-=-). Under such an assumption, estimation proceeds by estimating a separatesunivariate hazard model for each risk. Unfortunately, the assumption of independence issuntenable in most situations and, at t... |

15 |
Discrete-continuous econometric models and their application to transport analysis
- Mannering, Hensher
- 1987
(Show Context)
Citation Context ...en 1983, Hanemann 1984, ands32sLee 1983 for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and Mannering and Winston 1985 for applications;s=-=Mannering and Hensher, 1987-=- provide a review of transportation-related applications). Almostsall applications of the dichotomous case have used either a logit or probit approach to model thesdiscrete choice in the discrete/cont... |

15 | Testing the Proportional Hazards Assumption in the Presence of Unmeasured Heterogeneity - McCall - 1994 |

15 | Spatial Effects in Probit Models: A Monte Carlo Investigation - McMillen - 1995 |

14 |
Predictive Testing of Consumer Choice Models Not Subject to Independence of Irrelevant Alternatives
- Currim
- 1982
(Show Context)
Citation Context ...ly non-intuitive model behavior, low precision of covariancesparameter estimates, and increased difficulty in transferring models from one space-timessampling frame to another (see Horowitz, 1991 and =-=Currim, 1982-=-). Further, the errorcomponents models can be estimated using simulators which are conceptually simple and easy tosprogram. These simulators involve simultaneous draws from the appropriate density fun... |

14 |
Computational process modelling of household travel decisions using a geographical information system
- Golledge, Kwan, et al.
- 1994
(Show Context)
Citation Context ...s models since comprehensive reviews of these models havesbeen conducted not very long ago by pioneers of the approach who are more knowledgeables2sregarding the approach than the current author (see =-=Gärling et al., 1994-=-; Golledge et al., 1994;sKitamura and Fujii, 1996; and Kurani and Kitamura, 1996). An additional reason for notsfocusing on computation process models (CPMs) here is that while there has been consider... |

14 |
Time-of-day effects in inter-city business travel
- Mehndiratta
- 1996
(Show Context)
Citation Context ...if one uses the secondsform. Applications of random response heterogeneity include Fisher and Nagin, 1985, Reveltsand Train, 1996, Train, 1996, Ben-Akiva et al., 1993, Gonül and Srinivasan, 1993, ands=-=Mehndiratta, 1996-=-. The qkvsterms in the random response heterogeneity specification representsthe random tastes of person q and are common to the utility of all alternatives i. Therefore,svariance in the qkvsterms acr... |

13 |
Investigating the effects of marketing variables and unobserved heterogeneity in a multinomial probit model
- Chintagunta, Honore
- 1996
(Show Context)
Citation Context ...identification considerations) the variance-covariance matrix of thesoverall random components among the different alternatives (see Bunch and Kitamura, 1990;sLam, 1991; Lam and Mahmassani, 1991; and =-=Chintagunta and Honore, 1996-=-). The advantage ofsthe MNP model is that the structure is more general than the error-components models (the errorscomponents structure essentially parameterizes the variance-covariance matrix in an ... |

12 | Efficient Estimation of Nested Logit Models - Brownstone, Small - 1989 |

12 |
The Timing of Change for Automobile Transactions: A Competing Risk Multispell Specification.
- Hensher
- 1994
(Show Context)
Citation Context ...ince it does not impose a prior probability distribution.sApplication of duration models in the transportation field have, for the most part, ignoredsunobserved heterogeneity (but see Bhat, 1996b and =-=Hensher, 1994-=-b). Researchers in thesmarketing and economics fields have paid more attention to unobserved heterogeneity. However,seven in these fields, most applications have employed a parametric heterogeneity sp... |

12 | Extending Valuation to Controlled Value Functions and Non-uniform Scaling with Generalised Unobserved Variances - Hensher - 1999 |

12 | Market research evaluation of actions to reduce traffic congestion: Commuter travel behavior and response to demand reduction actions - Koppelman, Bhat, et al. - 1993 |

11 |
Identification and diagnosis of specification errors in the multinomial logit model
- Horowitz
- 1981
(Show Context)
Citation Context ...mode (based on, say, thesdegree of crowding on different train routes) but little for the automobile mode, then the randomscomponents for the automobile and train modes will have different variances (=-=Horowitz, 1981-=-).sThe HEV model does not have a closed-form solution for the choice probabilities, but involvessonly a one-dimensional integration regardless of the number of alternatives in the choice set.sBhat dev... |

11 | Duration of trip-making activities by men and women. - Niemeier, Morita - 1996 |

11 | Inequality and Attainment in a Dual Labor Market." - Sakamoto, Chen - 1991 |

10 |
Mixed MNL models for discrete response, working paper
- McFadden, Train
- 1996
(Show Context)
Citation Context ... tastes of person q and are common to the utility of all alternatives i. Therefore,svariance in the qkvsterms across individuals induces a correlation among the utility of differentsalternatives (see =-=McFadden and Train, 1996-=-). As a result, the random response specification doessnot exhibit the restrictive independence from irrelevant alternatives (IIA) property even if the IIDserror assumption across alternatives of the ... |

9 |
A Model of Post-Home Arrival Activity Participation Behavior
- Bhat
- 1998
(Show Context)
Citation Context |

9 |
Multinomial Probit Model Estimation Revisited: Testing Estimable Model Specifications, Maximum Likelihood Algorithms, and Probit Integral Approximations for Trinomial Models of Household Car Ownership, University of California Transportation Centre Workin
- Bunch, Kitamura
- 1991
(Show Context)
Citation Context ...s not partition the error terms, andsestimates (subject to certain identification considerations) the variance-covariance matrix of thesoverall random components among the different alternatives (see =-=Bunch and Kitamura, 1990-=-;sLam, 1991; Lam and Mahmassani, 1991; and Chintagunta and Honore, 1996). The advantage ofsthe MNP model is that the structure is more general than the error-components models (the errorscomponents st... |

9 |
Two properties of the nested logit model
- Daganzo, Kusnic
- 1993
(Show Context)
Citation Context ...achary, 1978). Each nest in the NL structure has associated withsit a dissimilarity (or logsum) parameter that determines the correlation in unobservedscomponents among alternatives in that nest (see =-=Daganzo and Kusnic, 1993-=-). The range of thissdissimilarity parameter should be between 0 and 1 for all nests if the NL model is to remainsglobally consistent with the random utility maximizing principle. A problem with the N... |

9 | Bounded Rationality in Commuter Decision Dynamics: Incorporating Trip Chaining - Mahmassani, Jou - 1998 |

7 |
Semiparametric estimation of duration models
- Meyer
- 1987
(Show Context)
Citation Context ...lar parametric form is appropriate, the resultingsestimates are consistent and the loss of efficiency (resulting from disregarding information aboutsthe hazard’s distribution) may not be substantial (=-=Meyer, 1987-=-).sWithin the nonparametric approach, one may use the partial likelihood frameworkssuggested by Cox (1972) which estimates the covariate effects but not the baseline hazard, or thes24sapproach suggest... |

7 | Discrete choice with an oddball alternative - Recker - 1995 |

6 |
Multistop-based measurements of accessibility in a GIS environment
- Arentze, Borgers, et al.
- 1994
(Show Context)
Citation Context ...nology. A specific application of GIS technology to activitytravel analysis is the development of a measure of spatial accessibility for use in the modeling ofsmultistop and multi-purpose travel (see =-=Arentze et al., 1994-=-a,b,c; Lee, 1996). Golledge et al.s(1994) and Kwan (1994) have used GIS to calibrate a production system model of activitysscheduling behavior. Caliper Corporation's TransCAD GIS software represents a... |

6 | The spatial distribution of retail expenditures - Barnard, Hensher - 1992 |

6 | A heteroscedastic extreme-value model of intercity mode choice. - Bhat - 1995 |

6 | Incentives for appliance efficiency: random-parameters logit models of households’ choices. Deptartment of Economics working paper, - Revelt, Train - 1996 |

5 |
Multinomial probit model estimation: computational procedures and applications
- Lam, Mahmassani
- 1991
(Show Context)
Citation Context ...estimates (subject to certain identification considerations) the variance-covariance matrix of thesoverall random components among the different alternatives (see Bunch and Kitamura, 1990;sLam, 1991; =-=Lam and Mahmassani, 1991-=-; and Chintagunta and Honore, 1996). The advantage ofsthe MNP model is that the structure is more general than the error-components models (the errorscomponents structure essentially parameterizes the... |

5 |
Analysis of Accessibility and Travel Behavior Using GIS. Master of Science Thesis.
- Lee
- 1996
(Show Context)
Citation Context ...ion of GIS technology to activitytravel analysis is the development of a measure of spatial accessibility for use in the modeling ofsmultistop and multi-purpose travel (see Arentze et al., 1994a,b,c; =-=Lee, 1996-=-). Golledge et al.s(1994) and Kwan (1994) have used GIS to calibrate a production system model of activitysscheduling behavior. Caliper Corporation's TransCAD GIS software represents an importantsbrid... |

5 |
Dynamics of commuter behavior: recent research and continuing challanges
- Mahmassani
- 1996
(Show Context)
Citation Context ...sscolleagues who have used the multinomial probit structure to examine the day-to-day dynamicssin departure time and route choice of commuters (see Lam and Mahmassani, 1991; Mahmassanisand Jou, 1996; =-=Mahmassani, 1997-=-). Logit-based simulators have been used in the travel demandsfield by Brownstone and Train (1996), Bhat (1996a, 1997b), and Ben-Akiva and Bolduc (1996).sThe formulation and estimation of behaviorally... |

5 |
Models of travelers' activity choice and home-stay duration: analysis of functional form and temporal stability
- Mannering, Murakami, et al.
- 1994
(Show Context)
Citation Context ...ngle event.sFor example, the length of unemployment ends when an individual gains employment (seesMeyer, 1990) or home stay duration ends when an individual leaves home to participate in ansactivity (=-=Mannering et al. 1992-=-). A limited number of studies have been directed towardsmodeling the more interesting and realistic situation of multiple duration-ending outcomes. Forsexample, failure in the context of unemployment... |

4 |
The residential location and workplace choice: a nested multinomial logit model
- Evers
- 1990
(Show Context)
Citation Context ...nnot be accurately represented bys5spartitioning the alternatives into mutually exclusive subsets. The NL model has been applied tosmultidimensional choice contexts (for example, see Waddell 1993 and =-=Evers, 1990-=-) andsunidimensional contexts where subsets of the available alternatives share common unobservedscomponents of utility (for example, see Forinash and Koppelman, 1993 and Brownstone andsSmall, 1989).s... |

3 |
Computational process modeling of travel decisions using geographical information systems
- Golledge, Kwan, et al.
- 1994
(Show Context)
Citation Context ...ensive reviews of these models havesbeen conducted not very long ago by pioneers of the approach who are more knowledgeables2sregarding the approach than the current author (see Gärling et al., 1994; =-=Golledge et al., 1994-=-;sKitamura and Fujii, 1996; and Kurani and Kitamura, 1996). An additional reason for notsfocusing on computation process models (CPMs) here is that while there has been considerablesadvancement in the... |

2 |
Geographical information systems and the measurement of accessibility in the context of multipurpose travel: a new approach
- Arentze, Borgers, et al.
- 1994
(Show Context)
Citation Context ...nology. A specific application of GIS technology to activitytravel analysis is the development of a measure of spatial accessibility for use in the modeling ofsmultistop and multi-purpose travel (see =-=Arentze et al., 1994-=-a,b,c; Lee, 1996). Golledge et al.s(1994) and Kwan (1994) have used GIS to calibrate a production system model of activitysscheduling behavior. Caliper Corporation's TransCAD GIS software represents a... |

2 |
Geographic information systems, spatial opportunities, and multi-stop travel: a new measurement approach
- Arentze, Borgers, et al.
- 1994
(Show Context)
Citation Context ...nology. A specific application of GIS technology to activitytravel analysis is the development of a measure of spatial accessibility for use in the modeling ofsmultistop and multi-purpose travel (see =-=Arentze et al., 1994-=-a,b,c; Lee, 1996). Golledge et al.s(1994) and Kwan (1994) have used GIS to calibrate a production system model of activitysscheduling behavior. Caliper Corporation's TransCAD GIS software represents a... |

2 | Estimation of randomly distributed value of time, working paper - Gopinath, Ben-Akiva - 1995 |

2 | A GIS-based computational process model of activity scheduling for intelligent vehicle highway systems (IVHS). Unpublished - Kwan - 1994 |

2 | Microsimulation and activity-based forecasting, paper prepared for publication - Miller - 1996 |

1 |
Selectivity bias in a simultaneous logit-OLS model
- Hay
- 1980
(Show Context)
Citation Context ...economic applications, while Winship and Mare, 1992 provide a review ofssociological applications). In contrast to the dichotomous case, the polychotomous case hassreceived much lesser attention (see =-=Hay 1980-=-, Dubin and McFadden 1983, Hanemann 1984, ands32sLee 1983 for estimation methods and Hensher et al. 1992, Bhat 1996, Barnard and Henshers1992, Hamed and Mannering 1993, and Mannering and Winston 1985 ... |

1 | Combining sources of preference data: the case of the lurking scale parameters, working paper - Hensher, Louviere, et al. - 1996 |