ingrid janssen co-authors: aloys borgers & harry timmermans june 2010
DESCRIPTION
Measuring Adaptive Behaviour in a Retail Planning Context; A Multi-Stakeholder Conjoint Measurement Experiment. Ingrid Janssen Co-authors: Aloys Borgers & Harry Timmermans June 2010. Agenda. Introduction Retail planning in the Netherlands Multi-actor decision making Approach - PowerPoint PPT PresentationTRANSCRIPT
Measuring Adaptive Behaviour in a Retail Planning Context;A Multi-Stakeholder Conjoint Measurement Experiment
Ingrid JanssenCo-authors: Aloys Borgers & Harry Timmermans
June 2010
2
Agenda
Introduction Retail planning in the Netherlands Multi-actor decision making
Approach Online conjoint experiment Multiple stakeholders Choice modelling
Model specification Results Conclusion
3
Introduction
Retail planning: Multi-Stakeholder decision making Planning philosophy: From plan-driven to market-driven Introduction “Nota Ruimte”:
Development planning No strict rules for new out-of-town retail locations Responsibility planning decisions delegated to local
governments Regional governments have a steering role
Dominant retail development industry
4
Introduction
5
Introduction
Retail planning in the Netherlands: Retail planning nowadays is a result of negotiations
between multiple actors
1. Developers
2. Retailers
3. Local governments To understand the behavioral aspects underlying
(retail) planning decisions there is a need for multi-actor approaches.
Focus: adaptive behavior
6
Approach
Suitable approach: A conjoint experiment in combination with choice modelling
Experiment: deciding on the expansion of retail supply in an imaginary city.
Three stakeholders involved: developers, local governments, retailers.
How: conjoint analysis. Alternatives are pre-specified
References: Borgers & Timmermans (1993) -> household
decisions Hensher et. al. (2007) -> freight distribution decisions
7
Research objectives
The aim of the experiment is…
…to understand the preferences of different stakeholder groups regarding the planning of out-of-town retail facilities.
…to measure adaptive behaviour between agents involved in retail planning, as one of the behavioural aspects.
8
Design choice task: Decision problem: How to
expand retail supply in the imaginary city “Shop City”?
Possible expansions: Toys and Sporting Goods Home Electronics and Media Fashion Restaurant
Characteristics “Shop City”: Middle sized Dutch city Market position non-daily retail
supply “Shop City” is weak compared to other cities in region.
Accessibility of both peripheral is equal.
Extended conjoined experiment
9
Attributes Levels
1 Toys and sporting goods (2.500 m2)
- Peripheral location sport stadium- Peripheral location furniture strip- Inner city
2 Home electronics and media (5.000 m2)
- Peripheral location sport stadium - Peripheral location furniture strip- Inner city
3 Fashion (7.500 m2) - Peripheral location sport stadium - Peripheral location furniture strip- Inner city
4 Restaurant (1.000 m2) - Peripheral location sport stadium - Peripheral location furniture strip- No restaurant
Extended conjoined experiment
10
Research approach (part II)
11
Data collection
Invitation by personal letter
Invitation by personal e-mail
Invitation by letter to organization
Invitation by e-mail to organization
Visited
website
Completed questionnaire
Developers 163 147 0 0 unknown 67
Retailers 88 68 185 160 unknown 36
Planners 132 216 62 0 unknown 67
Total 383 431 247 160 266 170
Response
12
Model specification
Random utility theory Each alternative i, has a utility (Ui). This utility consists of a
structural (Vi) and a random (εi) component:
iii VU (1)
(2)
where Xik represents characteristic k of alternative i and βk is the parameter for characteristic k. β0 is the utility of the “both retail plans are not acceptable”-option.
βk represent the main effects. However, interaction effects and adaptation effects have to be introduced.
k ikki XV 0
13
Model specification
The formula for the structural utility can be extended:
(3)
where β0 represents the utility of the “both alternatives are not acceptable” option
βk parameters measure the main effects
Өk parameters measure the interaction effects
αk parameters measure the adaptation effects
8,0
2,1
8,0
2,122
8,0
11
12,18,10 k ikk kikkk ikkl illk ikki AAAIXV
14
Model estimation
Multinimial Logit models were estimated using maximum likelihood procedures. Only parameters at the 5% significance level were included. For each stakeholder group (developer, retailer, planner) separate models were
estimated.
15
Estimated parameters MNL-modelvariabele attribute level β P(|Z|>z) β P(|Z|>z) β P(|Z|>z)X0 Both alternatives not acceptable -0.658 0.000 -0.630 0.000 -1.007 0.000X2 Toys&Sports Furniture strip - - - - -0.570 0.000X3 Elect&Media Sport stadium -0.783 0.000 -1.213 0.000 -1.091 0.000X4 Elect&Media Furniture strip 0.333 0.002 - - - -X5 Fashion Sport stadium -2.793 0.000 -1.724 0.000 -2.950 0.000X6 Fashion Furniture strip -2.369 0.000 -1.569 0.000 -2.491 0.000X8 Restaurant Furniture strip 0.293 0.003 - - - -X1xX3 0.640 0.000 0.893 0.000 - -X2xX3 - - - - 0.570 0.009X1xX7 0.595 0.000 - - - -X1xX8 - - 0.585 0.000 0.739 0.000X2xX7 - - 0.364 0.044 - -X3xX7 0.385 0.031 0.580 0.011 - -A3DEVELOPER XXX XXX - - 0.333 0.023
A8DEVELOPER XXX XXX 0.575 0,000 - -
A0RETAILER 0.335 0.000 XXX XXX - -
A2RETAILER 0.286 0.044 XXX XXX - -
A3RETAILER 0.322 0.017 XXX XXX - -
A4RETAILER 0.382 0.004 XXX XXX - -
A5RETAILER - - XXX XXX 0.596 0.003
A6RETAILER 0.459 0.002 XXX XXX - -
A8RETAILER - - XXX XXX 0.551 0.000
A0PLANNER 0.305 0.000 - - XXX XXX
A3PLANNER 0.292 0.027 0.442 0.016 XXX XXX
A4PLANNER 0.301 0.016 - - XXX XXX
A0DEV.xRETAILER XXX XXX - - 0.459 0.001
A2DEV.xRETAILER XXX XXX - - 0.851 0.002LL(B)LL(0)Rho2
Rho2 Adjusted0.30 0.16 0.340.29 0.340.16
-996.0 -1453.0-2208.4 -1186.6 -2208.4
pref
eren
ce
varia
ble
sin
tera
ctio
n va
riabl
es
adap
tatio
n va
riabl
es
-1554.6
developers retailers local governments
16
Findings
All stakeholders do not prefer to locate fashion on a peripheral retail location.
Since X0 is significant but negative for all stakeholders, respondents are really willing to make a choice.
Different type of interaction variables are of significant importance.
Developer is most willing to adapt his preference to the opinion of other stakeholders.
The retailer is the least sensitive for the opinion of other stakeholders
Planners’ utility of the location of toys&sport on a furniture strip turns positive when both other stakeholders are in favour.
Goodness-of-fit (Rho2) is satisfying for developers and planners.
17
Conclusions
The experiment showed that adaptive behaviour in retail planning decision plays an important role.
By extending the traditional random utility model with parameters that measure adaptive behaviour, this behavioural aspect can be incorporated.
Applying Mixed Logit models will lead to even more valid models (the Rho2 will increase).
Further research: estimating for heterogeneity within each group of stakeholders based on respondent characteristics.