Monte Carlo simulation methods are used to confirm the identifiability of discrete choice models in which unobserved heterogeneity is specified as a random effect and modelled using the nonparametric mass-points approach. This simulation analysis is also used to examine alternative strategies for the estimation of such models by using a quasi-Newton maximum-likelihood estimation procedure, given the apparent sensitivity of model identification to choice of starting values. A mass-point model approach is then applied to a dataset of repeated choice involving household shopping trips between three types of retail centre, and the results from this approach are compared with those obtained from a conventional cross-sectional multinomial logit choice model as well as to results from a model in which a parametric distribution (the Dirichlet) is used to model the unobserved heterogeneity.
Get full access to this article
View all access options for this article.
References
1.
AllisonP D, 1984Event History Analysis: Regression for Longitudinal Event Data (Sage, Beverly Hills, CA)
2.
AndersenE B, 1970, “Asymptotic properties of conditional maximum likelihood estimators”Journal of the Royal Statistical Society B32283–301
3.
BanerjeeA KBhattacharyyaG K, 1976, “A purchase incidence model with inverse gaussian interpurchase times”Journal of the American Statistical Association71823–829
4.
ChamberlainG, 1980, “Analysis of covariance with qualitative data”Review of Economic Studies47225–238
5.
ChatfieldCGoodhardtG J, 1973, “A consumer purchasing model with erlang interpurchase times”Journal of the American Statistical Association68828–835
6.
ClarkW A V, 1992, “Comparing cross-sectional and longitudinal analysis of residential mobility and migration”Environment and Planning A24 1291–1302
7.
CongdonP, 1987, “Heterogeneity and timing effects in occupational mobility in the Irish Republic”, in London Papers in Regional Science 18. Longitudinal Data Analysis: Methods and Applications Ed. UnclesM D (Pion, London) pp 29–44
8.
CrouchleyR, 1987Longitudinal Data Analysis (Gower, Aldershot, Hants)
9.
DaviesR B, 1984, “A generalized beta-logistic model for longitudinal data with an application to residential mobility”Environment and Planning A16 1375–1386
10.
DaviesR B, 1987, “Mass point methods for dealing with nuisance parameters in longitudinal studies”, in Longitudinal Data Analysis Ed. CrouchleyR (Gower, Aldershot, Hants) pp 88–109
11.
DaviesR BCrouchleyR, 1984, “Calibrating longitudinal models of residential mobility and migration”Regional Science and Urban Economics14231–247
12.
DaviesR BCrouchleyR, 1985, “Control for omitted variables in the analysis of panel and other longitudinal data”Geographical Analysis171–15
13.
DaviesR BEzzetF, 1988, “Software for the statistical modelling of recurrent behaviour”, in London Papers in Regional Science 18. Longitudinal Data Analysis: Methods and Applications Ed. UnclesM D (Pion, London) pp 124–138
14.
DaviesR BPicklesA R, 1985, “Longitudinal versus cross-sectional methods for behavioural research: A first-round knockout”Environment and Planning A17 1315–1329
15.
DaviesR BPicklesA R, 1987, “A joint trip timing store-type choice model for grocery shopping, including inventory effects and nonparametric control for omitted variables”Transportation Research A21345–361
16.
DempsterA PLairdN MRubinD B, 1977, “Maximum likelihood from incomplete data via the EM algorithm”Journal of the Royal Statistical Society B391–38
17.
DunnRReaderSWrigleyN, 1987, “A nonparametric approach to the incorporation of heterogeneity into repeated polytomous choice models of urban shopping behaviour”Transportation Research A21327–343
18.
ElbersCRidderG, 1982, “True and spurious duration dependence: The identifiability of the proportional hazards model”Review of Economic Studies49403–410
FischerM MNijkampP, 1987, “From static towards dynamic discrete choice modelling: A state of the art review”Regional Science and Urban Economics17(1) 3–27
21.
GuyC MWrigleyNO'BrienL GHiscocksG, 1983, “The Cardiff Consumer Panel: A report on the methodology”, Papers in Planning Research, Department of Town Planning, University of Wales, Cardiff
22.
HeckmanJ J, 1981, “Statistical models for discrete panel data”, in Structural Analysis of Discrete Data with Econometric Applications Eds ManskiCMcFaddenD (MIT Press, Cambridge, MA) pp 114–178
23.
HeckmanJ JBorjasG, 1980, “Does unemployment cause future unemployment? Definitions, questions and answers from a continuous time model of heterogeneity and state dependence”Econometrica52271–320
24.
HeckmanJ JSingerB, 1982, “The identification problem in econometric models for duration data”, in Advances in Econometrics Ed. HilderbrandW (Cambridge University Press, Cambridge) pp 39–77
25.
HeckmanJ JSingerB, 1984a, “A method for minimising the impact of distributional assumptions in econometric models for duration data”Econometrica52271–320
26.
HeckmanJ JSingerB, 1984b, “The identifiability of the proportional hazards model”Review of Economic Studies60231–243
27.
HeckmanJ JWillisR J, 1977, “A beta-logistic model for the analysis of sequential labor force participation by married women”Journal of Political Economy8527–58
28.
HerniterJ D, 1971, “A probabilistic model of purchase timing and brand selection”Management Science18102–113
29.
HougaardP, 1984, “Life table methods for heterogeneous populations: Distributions describing the heterogeneity”Biometrika7175–82
30.
HsiaoC, 1986Analysis of Panel Data (Cambridge University Press, Cambridge)
31.
JeulandA BBassF MWrightG P, 1980, “A multibrand stochastic model compounding heterogenous erlang timing and multinomial choice processes”Operations Research28255–277
32.
KieferNWolfowitzJ, 1956, “Consistency of the maximum likelihood estimates in the presence of infinitely many incidental parameters”Annals of Mathematical Statistics27887–906
33.
LairdN, 1978, “Nonparametric maximum likelihood estimation of a mixing distribution”Journal of the American Statistical Association73805–811
34.
LancasterT, 1979, “Econometric methods for the duration of unemployment”Econometrica47939–956
35.
ManskiC, 1981, “Structural models of discrete data”Sociological Methodology 1981 Ed. LeinhardtS (Jossey-Bass, San Francisco, CA) pp 58–109
36.
MatthewsS, 1987, “Computer packages for longitudinal data analysis”, Papers in Planning Research, Department of Town Planning, University of Wales, Cardiff
37.
MeghirC, 1988, “Attrition in company panels and the estimation of investment equations”, paper presented at the Second European Conference on Panel Data, June, Paris; copy available from this author (Reader)
38.
MundlakY, 1978, “On the pooling of time series and cross section data”Econometrica4669–85
39.
NeymanJScottE L, 1948, “Consistent estimates based on partially consistent observations”Econometrica161–32
40.
ParksR W, 1980, “On the estimation of multinomial logit models from relative frequency data”Journal of Economics13293–303
41.
PicklesA R, 1983, “The analysis of residence histories and other longitudinal panel data: A continuous time mixed Markov renewal model incorporating exogenous variables”Regional Science and Urban Economics13271–285
42.
ReaderS, 1988Incorporating Unobserved Heterogeneity into Longitudinal Models of Repeated Choice: Optimization, Estimation and Simulation Issues PhD thesis, Department of Geography, University of Bristol, Bristol
43.
ReaderSUnclesM D, 1988, “The collection and analysis of consumer data”, in London Papers in Regional Science 18. Longitudinal Data Analysis: Methods and Applications Ed. UnclesM D (Pion, London) pp 45–57
44.
TardiffT J, 1980, “Definition of alternatives and representation of dynamic behaviour in spatial choice models”Transportation Research Record72325–30
45.
TrussellJRichardsT, 1985, “Correcting for unmeasured heterogeneity in hazard models using the Heckman — Singer procedure”, in Sociological Methodology 1985 Ed. TumaN B (Jossey-Bass, San Francisco, CA) pp 242–276
46.
UnclesM D (Ed.), 1988London Papers in Regional Science 18. Longitudinal Data Analysis: Methods and Applications (Pion, London)
47.
VaupelJ WMantonK GStallardC, 1979, “The impact of heterogeneity in individual frailty on the dynamics of mortality”Demography16439–454
48.
WoodAHindeJ, 1987, “Binomial variance component models with a nonparametric assumption concerning random effects”, in Longitudinal Data Analysis Ed. CrouchleyR (Gower, Aldershot, Hants) pp 110–128
49.
WrigleyN, 1986, “Quantitative methods: The era of longitudinal data analysis”Progress in Human Geography10 84–102
50.
WrigleyNDunnR, 1984a, “Stochastic panel-data models of urban shopping behaviour: 1. Purchasing at individual stores in a single city”Environment and Planning A16629–650
51.
WrigleyNDunnR, 1984b, “Stochastic panel-data models of urban shopping behaviour: 2. Multistore purchasing patterns and the Dirichlet model”Environment and Planning A16759–778
52.
WrigleyNDunnR, 1984c, “Stochastic panel-data models of urban shopping behaviour: 3. The interaction of store choice and brand choice”Environment and Planning A16 1221–1236
53.
WrigleyNDunnR, 1985, “Stochastic panel-data models of urban shopping behaviour: 4. Incorporating independent variables into the NBD and Dirichlet models”Environment and Planning A17319–331
54.
YamaguchiK, 1986, “Alternative approaches to unobserved heterogeneity in the analysis of repeatable events”, in Sociological Methodology 1986 Ed. TumaN B (Jossey-Bass, San Francisco, CA) pp 213–249
