Eliminating Bias Due to the Repeated Measurements Problem in Stated Preference Data

Cirillo, Cinzia; Daly, Andrew; Lindveld, Karel

doi:10.1007/978-3-662-03514-6_13

Cited by 26 publications

(24 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to allow for what is termed the repeat observations problem, whereby correlations amongst the errors within individuals' multiple answers lead to the standard errors associated with the coefficients being too low, we have used a jack-knife procedure. This is a repeat sampling method (Cirillo et al, 2000) which provides revised standard errors of coefficient estimates but rarely has any appreciable impact on the coefficient estimates themselves. In all cases, the jack-knife procedure was specified to take 30 samples from the SP data set 1 .…”

Section: Stated Preference Resultsmentioning

confidence: 99%

Traffic related noise and air quality valuations: evidence from stated preference residential choice models

Wardman

Bristow

2004

Transportation Research Part D: Transport and Environment

View full text Add to dashboard Cite

This paper reports on research which has estimated valuations of changes in traffic related noise levels and air quality and which contributes to the body of knowledge and to methodology in this area. There are several novel aspects of this research. Firstly, there have been relatively few stated preference studies of the monetary valuations of traffic related noise and air quality. A feature of this analysis is the examination of variations in values according to the size and sign of the environmental change, the currently experienced level of the attribute and various socio-economic factors. Secondly, the important issue of presentation is addressed, with two different methods used in the valuation of air quality and links made between valuations and physical measures. Thirdly, the results from stated preference and the contingent valuation method are compared. Finally, we bring together evidence from other studies and compare them with the findings obtained here.

show abstract

Section: Stated Preference Resultsmentioning

confidence: 99%

Traffic related noise and air quality valuations: evidence from stated preference residential choice models

Wardman

Bristow

2004

Transportation Research Part D: Transport and Environment

View full text Add to dashboard Cite

show abstract

“…It should be noted that the models presented in this paper do not include any treatment of the 'repeated measures' property of SP data (e.g., there are no individual level error components). Experience suggests that this is likely to lead to an overstatement (sometime substantially) of the significance of certain parameters, but not to major bias in the central estimates of the parameters themselves; see, for example, Cirillo et al (2000). This should be borne in mind in interpreting the results presented below.…”

Section: Generic Choice Model Specificationmentioning

confidence: 92%

Flexible substitution patterns in models of mode and time of day choice: new evidence from the UK and the Netherlands

et al. 2006

Self Cite

View full text Add to dashboard Cite

Modelling the temporal response of travellers to transport policy interventions has rapidly emerged as a major issue in many practical transport planning studies and is recognised to hold particular challenges. The importance of congestion and its variation over the day, together with the emergence of time-dependent road user charging as a policy tool, emphasise the need to understand whether and how travellers will change the timing of their journeys. For practical planning studies, analysts face a major issue of relating temporal changes to other behavioural changes that are likely to result from policy or exogenous changes. In particular, the relative sensitivity of time and mode switching has been difficult to resolve. This paper describes a study undertaken to determine the relative sensitivity of mode and time of day choice to changes in travel times and costs and to investigate whether evidence exists of varying magnitudes of unobservable influences in time of day switching. The study draws on data from three related stated preference studies undertaken over the past decade in the United Kingdom and the Netherlands and uses error components logit models to investigate the patterns of substitution between mode and time of day alternatives. It is concluded that the magnitude of unobserved influences on time switching depends significantly on the magnitudes of the time switches considered. With time periods of the magnitude generally represented in practical modelling, i.e. peak periods of 2-3 hours, time switching is generally more sensitive in this data than mode switching. However, the context of the modelling and the extent to which relevant variables can be measured will strongly influence these results.

show abstract

“…388 Results are presented for models with Jack-knife 2 and without (called Ôoriginal modelÕ) Jack-knife 389 estimation. The Jack-knife (see Cirillo et al, 2000) was used here to correct for the repeated 390 measurements bias, which leads to overstated t-ratios and may correct for other specification 391 errors as well. Future work may include using error components for this as well and comparing 392 the outcomes with those of the Jack-knife.…”

mentioning

confidence: 99%

A model for time of day and mode choice using error components logit

Jong¹,

Daly²,

Pieters³

et al. 2003

Transportation Research Part E: Logistics and Transportation Re

Self Cite

106

View full text Add to dashboard Cite

11 The severity of road congestion not only depends on the relation between traffic volumes and network 12 capacity, but also on the distribution of car traffic among different time periods during the day. A new error 13 components logit model for the joint choice of time of day and mode is presented, estimated on stated 14 preference data for car and train travellers in The Netherlands. The results indicate that time of day choice 15 in The Netherlands is sensitive to changes in peak travel time and cost and that policies that increase these 16 peak attributes will lead to peak spreading. In the Netherlands, the Dutch National Model System for traffic and transport (LMS) has been 21 used since 1990 to predict the responses of travellers to a wide range of developments, such as 22 changing travel times (e.g. from congestion) or the imposition of time-dependent road user 23 charging. One of the results of these simulations has been that the choice of when to travel (time of 24 day choice) greatly affects the amount of congestion on the road network and that policies aiming 25 at spreading out peak travel can be effective instruments to relieve congestion. U N C O R R E C T E D P R O O F 26However, these results rely to a large extent on a time of day choice sub-model within the 27 Dutch National Model System, which is more than 10 years old. Moreover, this sub-model uses a 28 rather simple and restrictive specification: only three time periods are distinguished within a 29 working day, there are no links between the outward and inward leg of the same tour, and the 30 model is multinomial logit (MNL). Since then, congestion has increased considerably, casting 31 doubt about whether the old specifications will still hold, while modelling capabilities also im-32 proved. 33In this paper, a new model for the joint choice of mode and time of day is presented and es-34 timated on new stated preference data. The model is not restricted to shifts between large time 35 periods and follows the error components logit (EClogit; also called mixed MNL) specification. 36 Using this type of model, one can take account of the different degrees of substitution between 37 time periods (e.g. greater substitution between nearby periods than between periods further away 38 from each other) and between time of day alternatives and alternative modes. It is a tour-based 39 model, in which outbound time of travel, duration of the activity at the destination and mode 40 choice are determined simultaneously. 41This new model was developed to become the basis of a new time of day choice sub-module of 42 the Dutch National Model System. It also covers public transport users, whereas the old module 43 only referred to the time of day choice of car drivers. Most empirical studies into the choice of time of day have considered only the demand of 52 travellers for travel at different points of time or periods in time (mostly using discrete time pe-53 riods) for given travel time and/or travel cost. Impacts on congestion and feedback to ...

show abstract

Eliminating Bias Due to the Repeated Measurements Problem in Stated Preference Data

Cited by 26 publications

References 3 publications

Traffic related noise and air quality valuations: evidence from stated preference residential choice models

Traffic related noise and air quality valuations: evidence from stated preference residential choice models

Flexible substitution patterns in models of mode and time of day choice: new evidence from the UK and the Netherlands

A model for time of day and mode choice using error components logit

Contact Info

Product

Resources

About