1 / 15

M8 Choice Modelling

M8 Choice Modelling. Valuation of Non-Market Goods. Revealed Preference Methods. Stated Preference Methods. Travel Cost Method. Hedonic Pricing. Choice Modelling. Contingent Valuation Method. Choice Experiments Pair Comparisons Contingent Ranking

laszlo
Download Presentation

M8 Choice Modelling

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. M8Choice Modelling

  2. Valuation of Non-Market Goods Revealed Preference Methods Stated Preference Methods Travel Cost Method Hedonic Pricing Choice Modelling Contingent Valuation Method Choice Experiments Pair Comparisons Contingent Ranking Contingent Rating Choice Modelling Source: Bateman et al., 2002

  3. Choice Modelling • Introduction • The term ‘choice modelling’ encompasses a range of SP techniques includes: • Choice experiments • Contingent ranking • Contingent rating • Paired comparison • CM originates in the market research and transportation (Henscher, 1994) • Food market; quality, taste, price • Transport; timing, comfort, cost

  4. Choice Modelling CM approaches are based around the idea that any good can be described in terms of attributes, or characteristics and the levels

  5. Choice Modelling Source: Bateman et al., 2002

  6. Choice Modelling: Choice Experiments • Introduction • The first study to apply choice experiments to non-market valuation was Adamowicz et al., (1994) • In Malaysia; 3 studies available • Jamal et al., (2000) – Forest Management Options • Jamal et al., (2002) – Contingent Ranking on Waste Management • Mohd Rusli (2006) – Choice Experiment – Recreation and ecotourism resources • There are several reasons for increased interest in CE to used in valuation exercises such as:- • Reduction of some of the potential biases of CVM • More information is elicited from each respondent compared to CVM and, • The possibility of testing for internal consistency

  7. Choice Experiment • The theoretical foundations: • Theory of value by Lancaster (1966) • Random utility theory by Manski (1977). • Lancaster’s theory specifies the value of a good as a function of the attributes that characterize the good rather that the good per se. • The random utility theory (RUT) helps to derive the best estimator of the unknown true utility function. • RUT relates utility directly to the probability of choosing an alternative from a set of alternatives.

  8. Choice Experiments • The probability; Pin = f ( Xin, Xjn ; j ≠ i, β) Where; Pin = probability of respondent n choosing alternative i Xin = a vector of observable characteristics of alternative i accessible to respondent n Xjn = a vector of observable characteristics of alternatives j accessible to respondent n

  9. Choice experiment Welfare measure: • The ratio of an attribute’s coefficient and the price coefficient represents the marginal implicit price of the attributes. • This ratio represents the implied change in the implicit price of the attributes relative to a current situation or status quo as in the formula below: ρi,k = ∂V / ∂Xi, k = -1 βi,k ∂V / ∂P i, k βi,k=p

  10. Choice Experiment • A CE study involves five important stages: • selecting attributes • determining levels, • choosing experimental design, • constructing choice sets • measuring preferences

  11. Choice Experiment Choice of Attributes • The attributes used to describe the alternatives in each choice set should be relevant to the policy making process. • The attributes used must have meaning to the people who will answer the questionnaire. • If the attributes used are irrelevant to respondents, the likelihood of valid responses being received is reduced, and response rates could be diminished.

  12. Choice Experiment Marine Park and Areas (MPA)

  13. Choice Experiment Choice Options • Discrete choice • Multiple choices • Example Each choice set had three alternatives or management options for ecotourism development in RIMP. Management options one and two are the alternatives; management option three is always the same as the ‘status quo’ option. The status quo option was provided for respondents who do not want a change for the management options described.

  14. Choice Experiment Factorial Design • All choice modelling studies require an experimental design. • The design is formulated from number of attributes (or factors) or the number of levels for each attribute. • Attributes must have at least two levels. • The attributes included in an experimental design should be the attributes that influence a visitor’s or respondent’s choices. • A complete factorial design (CFD) or full factorial design is simply all possible combinations of levels from all attributes. • Example, CFD was 3341= 108,impossible to implement. • Fractional FD, only a subset of all possible combinations of attributes levels is selected. • This design reduces the number of alternatives the respondent evaluates and still allows the estimation of the unknown parameters the researcher seeks.

  15. Choice Experiment Table 5.5 Example of CE question

More Related