TL;DR: In this article, the authors present the results of a choice experiment carried out from August to October 2000 on the visitors of the Galleria Borghese Museum, a worldwide known heritage site located in Rome.
Abstract: This paper presents the results of a choice experiment carried out from August to October 2000 on the visitors of the Galleria Borghese Museum, a worldwide known heritage site located in Rome. The main objective of this work is to study the relevancy of choice experiment techniques as a tool aimed at measuring economic values and assessing user preferences concerning the multi‐attribute and multi‐value services as supplied by cultural institutions. A set of alternative incremental changes in service attributes showing improvements in supply are designed and presented to visitors. Alternative conditional logit specifications are used for analysing stated choices over the hypothetical incremental changes in museum attributes. Willingness to pay for incremental variations concerning site attributes is positive and statistically significant for most changes. Conditional logit specifications, which incorporate heterogeneity by adding interaction socio‐economic terms, are generally robust and do not violate the IIA assumption. In addition, in the present case study, non‐IIA models do not outperform conditional logit models. Choice experiments confirm as being a practical and effective tool for non‐market valuation, and they should be used to provide information to decision makers for justifying demand led policies.
TL;DR: In this article, the logit model is used to estimate nonmarket commodity demand in recreational boating data collected using the contingent valuation method (CVM), and the expected negative slope of the demand curve for the theoretically preferred functional form is shown.
TL;DR: In this paper, the authors studied the association between a firm's stock returns and subsequent top management changes and found that there is an inverse relation between the probability of a management change and the firm's share performance.
Abstract: This paper studies the association between a firm's stock returns and subsequent top management changes. Consistent with internal monitoring of management, there is an inverse relation between the probability of a management change and a firm's share performance. This relation can result from monitoring by the board, other top managers, or blockholders. However, unless share performance is extremely good or bad, logit models have no predictive ability. No average stock reaction is detected at announcement of a top management change.
TL;DR: In this paper, the authors argue that the traditional logit model does not have a natural interpretation when the true response function is not logit and propose a weighted maximum likelihood estimator for binary response.
Abstract: It is well-known that, under the logit model for binary response, the random sampling and response-based sampling maximum likelihood estimators coincide for all parameters except the intercept. Citing this coincidence, many researchers have assumed the logit model and analyzed data from response-based samples as if those data were obtained by random sampling. We argue that this practice should be avoided unless the researcher really believes the logit specification. One preferable alternative is the weighted maximum likelihood estimator of Manski and Lerman (1977). Random sampling maximum likelihood analysis does not have a natural interpretation when the true response function is not logit. Weighted maximum likelihood analysis estimates a constrained best predictor of the binary response and so remains interpretable.
TL;DR: A general expression of the variance-covariance matrix of the cross-nested logit model presenting interesting empirical evidences is proposed and it will be demonstrated as it would be generally possible to specify the model so that this general expression reproduces any given hypothetical homoschedastic variance- covariances matrix.
Abstract: In this paper the cross-nested logit model is reformulated as a generalization of the single level Hierarchical logit model. The proposed analytical formulation is derived from the GEV model. Moreover a general expression of the variance-covariance matrix of the cross-nested logit model presenting interesting empirical evidences is proposed. It will be also demonstrated as it would be generally possible to specify the model so that this general expression reproduces any given hypothetical homoschedastic variance-covariance matrix. In other words, assuming this general variance-covariance matrix expression, a particular cross-nested logit model specification could be generally individuated in correspondence of any assumed homoschedastic variance-covariance matrix and thus, from the latter, it would be possible to derive not just probit choice probabilities but also cross-nested logit choice probabilities (with a closed analytical form). (a) For the covering entry of this conference, please see ITRD abstract no. E213535.