Integration of unobserved effects in generalised transport access costs of cycling to railway stations
La Paix Puello and Geurs, 2016, in European Journal of Transport and Infrastructure Research
doi:nan
Location |
Netherlands |
Population |
Other (specify) |
Sample size |
12000 |
Factor analysis type |
confirmatory factor analysis, none rotation |
Stepwise regression |
nan |
Removal of insignificant variables |
nan |
Reviewed by |
MWC |
Abstract
This paper examines the role of perceptions and attitudes in railway station accessibility. We add unobserved (latent) variables to the Generalised Transport Access Cost (GTAC) of cycling to Dutch railway stations in the metropolitan area of The Hague-Rotterdam. A hybrid discrete choice model was estimated for access mode and two latent variables which were obtained through factor analysis: perception of station environment (including factors such as the users’ judgement of the station, assessment of travel information, presence of high speed trains) and perceived connectivity (including factor such as the evaluation of punctuality and the frequency of the train and quality of bicycle infrastructure). The estimated individual utility was applied to a station access cost index. A comparison between standard logit and hybrid utility functions identifies improvements in the utility-based measures by using discrete choice models. Utilities are computed by station departure, postcode of residence and neighbourhood. The results show, first, that omitting unobserved effect in utility-based measures tends to lead to overestimations of the accessibility levels. Secondly, different variations in accessibility levels are revealed, by size of railway stations and urban areas. Finally, the results highlight stronger effects of network connectivity impedances than station environmental impedances in generalised transport costs. © 2016, Editorial Board EJTIR. All rights reserved.
Factors
Models
Dependent variable |
Bicycle to train station |
Model type |
Binary logit |
Sample size |
12000.0 |
R2 |
nan |
Adjusted R2 |
|
Pseudo R2
(nan)
|
0.157 |
AIC |
nan |
BIC |
nan |
Log-likelihood at zero |
nan |
Log-likelihood at constants |
nan |
Log-likelihood at convergence |
nan |
Variable |
Coefficient |
p-value |
Constant |
-0.457
|
0.153 |
Age |
-0.01
|
0.0 |
Male |
0.04
|
0.772 |
Work trip |
0.48
|
0.0 |
Business trip |
0.63
|
0.0 |
School/study trip |
0.41
|
0.0 |
Discount |
0.26
|
0.0 |
Student card |
-0.16
|
0.011 |
Rush hour |
0.27
|
0.0 |
Car |
-0.08
|
0.063 |
Income level in residence area divided by travel time |
0.07
|
0.121 |
Density of bicycle network |
-0.24
|
0.0 |
Population density |
-0.01
|
0.246 |
Dwelling density |
-0.01
|
0.226 |
Job density |
0.4
|
0.001 |
Employees in health near station |
-0.21
|
0.66 |
Public employees near station |
-3.23
|
0.0 |
Retail employees near station |
1.18
|
0.211 |
Average road quality |
2.4
|
0.0 |
Average traffic nuisance |
-1.04
|
0.795 |
More than 3km from station |
-0.35
|
0.0 |
Bus/tram/metro lines |
-0.03
|
0.0 |
Station type 1 (Very large station in the centre of a large city) |
-0.27
|
0.0 |
Bicycle parking spaces |
0.002
|
0.0 |
Dependent variable |
Bicycle to train station |
Model type |
Integrated choice and latent variable |
Sample size |
12000.0 |
R2 |
nan |
Adjusted R2 |
|
Pseudo R2
(nan)
|
0.215 |
AIC |
nan |
BIC |
nan |
Log-likelihood at zero |
nan |
Log-likelihood at constants |
nan |
Log-likelihood at convergence |
nan |
Station perception |
Variable |
Coefficient |
p-value |
Constant |
6.15
|
0.0 |
Station type 1 (Very large station in the centre of a large city) |
-0.24
|
0.067 |
Easy to find travel information |
0.03
|
0.711 |
Bicycle parking |
0.06
|
0.0 |
Lighting quality at station |
-0.003
|
0.968 |
Number of high-speed trains |
-0.15
|
0.0 |
Std. dev. |
0.06
|
0.003 |
Utility |
Variable |
Coefficient |
p-value |
Constant |
-1.06
|
0.003 |
Station perception |
0.1
|
0.0 |
Age |
-0.01
|
0.0 |
Male |
0.04
|
0.332 |
Work trip |
0.51
|
0.0 |
Business trip |
0.63
|
0.0 |
School/study trip |
0.27
|
0.0 |
Discount |
0.36
|
0.0 |
Student card |
-0.21
|
0.001 |
Rush hour |
0.28
|
0.0 |
Car |
-0.08
|
0.105 |
Income level in residence area divided by travel time |
0.08
|
0.121 |
Density of bicycle network |
-0.24
|
0.0 |
Population density |
-0.01
|
0.234 |
Dwelling density |
-0.52
|
0.234 |
Job density |
0.38
|
0.002 |
Employees in health near station |
-0.238
|
0.624 |
Public employees near station |
-3.32
|
0.0 |
Retail employees near station |
1.05
|
0.263 |
Average road quality |
2.4
|
0.0 |
Average traffic nuisance |
-1.04
|
0.0 |
More than 3km from station |
-0.35
|
0.0 |
Bus/tram/metro lines |
-0.03
|
0.0 |
Station type 1 (Very large station in the centre of a large city) |
-0.37
|
0.0 |
Bicycle parking spaces |
0.002
|
0.038 |
Dependent variable |
Bicycle to train station |
Model type |
Integrated choice and latent variable |
Sample size |
12000.0 |
R2 |
nan |
Adjusted R2 |
|
Pseudo R2
(nan)
|
nan |
AIC |
nan |
BIC |
nan |
Log-likelihood at zero |
nan |
Log-likelihood at constants |
nan |
Log-likelihood at convergence |
nan |
Connectivity |
Variable |
Coefficient |
p-value |
Constant |
5.87
|
0.0 |
Quality of bicycle access roads |
-0.02
|
0.208 |
Quality of guarded bicycle parking |
0.003
|
0.43 |
Quality of unguarded bicycle parking |
0.08
|
0.0 |
Number of InterCity trains |
-0.01
|
0.036 |
Number of Sprinter trains |
0.05
|
0.003 |
Std. dev. |
0.23
|
0.0 |
Utility |
Variable |
Coefficient |
p-value |
Constant |
-3.67
|
0.0 |
Connectivity |
0.25
|
0.0 |
Age |
-0.01
|
0.0 |
Male |
0.02
|
0.596 |
Work trip |
0.55
|
0.0 |
Business trip |
0.61
|
0.0 |
School/study trip |
0.27
|
0.0 |
Discount |
0.44
|
0.0 |
Student card |
-0.22
|
0.001 |
Rush hour |
0.27
|
0.0 |
Car |
-0.1
|
0.026 |
Income level in residence area divided by travel time |
0.0
|
0.497 |
Density of bicycle network |
-0.2
|
0.0 |
Population density |
-0.03
|
0.0 |
Dwelling density |
0.002
|
0.569 |
Job density |
0.2
|
0.012 |
Employees in health near station |
-0.185
|
0.704 |
Public employees near station |
-2.95
|
0.0 |
Retail employees near station |
0.605
|
0.509 |
Average road quality |
2.75
|
0.0 |
Average traffic nuisance |
-1.0
|
0.0 |
More than 3km from station |
-0.33
|
0.0 |
Bus/tram/metro lines |
-0.03
|
0.0 |
Station type 1 (Very large station in the centre of a large city) |
-0.11
|
0.007 |
Bicycle parking spaces |
0.002
|
0.0 |