|
on Discrete Choice Models |
| By: | Abdullah, Sabah; Mariel, P |
| Abstract: | Modern forms of energy are an important vehicle towards poverty alleviation in rural areas of developing countries. Most developing countries’ households heavily rely on wood fuel which impact their health and social–economic status. To ease such a dependency, other modern forms of energy, namely electricity, need to be provided. However, the quality of the electricity service, namely reliability, is an important factor in reducing this dependency. This paper discusses a choice experiment valuation study conducted among electrified rural households located in Kisumu, Kenya, in which the willingness to pay (WTP) to avoid power outages or blackouts was estimated. A mixed logit estimation was applied to identify the various socio-economic and demographic characteristics which determine preferences to reduce power outages among a household’s users. In conclusion, several of the socio-economic and demographic characteristics outlined in this paper were identified and can assist service differentiation to accommodate the diverse households’ preferences towards the improvement of the electricity service. |
| Keywords: | developing country; rural; power outages; willingness to pay; random parameter logit |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:eid:wpaper:15964&r=dcm |
| By: | Hultkrantz, Lars (Department of Business, Economics, Statistics and Informatics); Shengcong, Xue (Department of Business, Economics, Statistics and Informatics) |
| Abstract: | We present results from a series of willingness to-accept value-of-time choice experiments with students in Sweden and China, using both real and hypothetical purchases of the students´ time. Our results confirm negative hypothetical bias in stated choice elicitation of value-of-time. However, we find no evidence of hypothetical bias in a choice experiment where respondents to hypothetical or real offers have equal reference points (i.e., for purchase of their time “here and now”). Moreover, at least in the Chinese sample, we find that ex-post mitigation of negative hypothetical bias by certainty calibration, through recoding of uncertain “yes” responses into “no”, overshoots, while calibration by restricting estimations to confident “yes” and “no” responses possibly performs better. |
| Keywords: | Stated choice; Certainty calibration; Preference certainty |
| JEL: | C20 C91 D80 |
| Date: | 2009–10–16 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:oruesi:2009_014&r=dcm |