Thomas Laitila

A Multi-Attribute Extension of Discrete-Choice Contingent Valuation for Valuation of Angling Site Characteristics

Abstract An extended version of the discrete choice contingent valuation method for valuation of angling site attributes is considered in this paper. The respondent is asked to choose among existing angling sites and a described hypothetical site. A new contribution is the approach suggested for modeling this kind of data where hypothetical alternatives are compared with existing ones. A major advantage of this new modeling approach is that it avoids the substantial need for information on existing angling sites. Results from an application of the method and the modeling approach are also presented.

Direct and indirect effects on households¿ intentions to replace the old car

With the purpose of testing the hypothesis that households’ intentions to replace their old car have a direct negative relationship to its perceived quality (‘current level’) and a direct positive relationship to their aspirations for a new car (‘aspiration level’), a rotating panel of car owners were interviewed every fourth month during 2 years. In this data set the hypothesis received support. In addition the results showed that the age of the car, the total number of miles driven, and the number of anticipated repairs affected the current level, whereas marital status, the number of children, consumer confidence, and environmental concern affected the aspiration level.

MODELLING AND PREDICTION OF TRAVEL DISTANCE BY CAR.

A theoretical basis and empirical modelling and prediction results for Swedish travelling distances by car are given. The results form the basis for an assessment of the economic consequences of Swedish petrol price adjustments by region and travel type. Truncated regression models are estimated using a general distribution class specification and a robust estimator based on symmetric trimming. Predictors and prediction variances are given. The study confirms the hypothesis of a positive income effect for work and business travel distances. The effect is negative and significant for recreation distances. Travel distances tend to be shorter in less densely populated regions, i.e. a positive density effect. Males have significantly longer work and shopping trips. The differences between estimators and corresponding predictions are small. The financial support from the Swedish Transport Research Board (Dnr 21/88–82) is gratefully acknowledged.

Estimation of combined site-choice and trip-frequency models of recreational demand using choice-based and on-site samples

Abstract Concentrated log-likelihood functions are derived for combined site-choice and trip-frequency models under choice-based and on-site sampling. Results show that they are equal to log-likelihood functions derived conditional on explanatory variables. A new estimator for estimation of population welfare measures is proposed.

A cost-benefit analysis of restoring the Em River in Sweden: valuation of angling site characteristics and visitation frequency

This article uses Cost-Benefit Analysis (CBA) to evaluate restoration scenarios aimed at improving angling on the Em River in Sweden. We find that none of the proposed projects are socially profitable when considering only values associated with angling. We rely on a Choice Experiment (CE) to derive utilities and estimate the monetary value of angling site characteristics and then also use the utilities derived in a visitation frequency using a two-stage budgeting approach. The visitation frequency is then used to extract values for fishing license sales and business-related income. The case study illustrates how CBA can provide useful insights into the potential economic returns of environmental restoration projects. Our case study also indicates that the results in terms of Willingness-To-Pay (WTP) and visitation frequency are general findings – i.e. they appear similar across angling sites – which is particularly useful from a policy point of view because it supports the use of benefit transfer for more cost-effective river management.

Test of random subject effects in heteroskedastic linear models

A new test of random subject effects in linear regression models is presented. The test is robust against heteroskedasticity and its asymptotic distribution is derived under a sequence of local alternatives. The finite sample properties of the test are studied in a simulation experiment and an empirical example. The results presented show that the new test is to be preferred over earlier test proposed.

Properties of the QME under asymmetrically distributed disturbances

The quadratic mode regression estimator has been suggested for truncated regression models where symmetry characterizes the distribution of disturbances. In this paper the estimator is shown to be consistent and asymptotically normal distributed under asymmetrically distributed disturbances.

Heteroskedasticity in the Tobit model

The paper deals with parameter estimation and the testing of individual parameters in heteroskedastic Tobit models. The statistical properties of semiparametric and maximum likelihood estimators are evaluated. Correspondingt-test statistics are compared. Results from a Monte Carlo experiment indicate that the semiparametric estimator performs relatively better than the maximum likelihood estimator. The associatedt-test statistics appear to perform better than the corresponding maximum likelihood test statistics. *** DIRECT SUPPORT *** A06GP002 00008

Adaptation of honda's one–sided test of random effects to repeated measurements experiments

A test of random subject effects in models for repeated measurements experiments is suggested. The test is suggested for applications where subjects can be divided into groups with respect to subject characteristics. The test is derived as an adaptation of Hondas one–sided test to a general model of experimental repeated measurements. The general model contains models for e.g. continuous and categorical response variables as special cases. In particular, one special case of the model is compound distributions defined by generalized linear models with random subject terms added to the linear predictor. The test is shown to be related to score tests and a t–test of independence in a 2×2 contingency table. Results imply that the test proposed is a potentially valuable tool for analysis of repeated measurement data.

Asymptotic misspecification biases for Heckman's two step estimator

Asymptotic bias formulae are obtained for Heckmans two step estimator under misspecification of the single equation Tobit modelj and the two equation sample selection model. Asymptotic biases are also obtained for the ordinary least squares estimator based on uncensored observations only. Omitted variables, errors in variables, and heteroskedasticity are considered as sources of misspecification. The biases are illustrated by numerical examples, in which the Tobit maximum likelihood estimator is also included. Severe consequences for the two step estimator are indicated.