This study extends the joint estimation of revealed and stated preference data literature by accounting for truncation in the revealed preference data. The analytical model and estimation procedure are used to estimate the value of recreational red snapper fishing in the Gulf of Mexico. This recreational red snapper valuation is decomposed into its direct and indirect components. As expected, the value of recreational red snapper fishing using the joint revealed-stated preference model proposed in this analysis is bracketed on the upper limit by the value obtained using the contingent valuation method and on the lower limit by the travel cost method. The results also indicate that the joint model improves the precision of estimated recreational red snapper valuation.

Nonparametric techniques are frequently applied in recreation demand studies when researchers are concerned that parametric utility specifications impart bias upon welfare estimates. A goal of this paper is to extend previous work on nonparametric bounds for welfare measures to allow for measurement errors in travel costs. Haab and McConnell (2002) state that issues in travel time valuation continue to be topical in the recreational demand literature. This paper introduces a bootstrap augmented nonparametric procedure to precisely bound welfare when price data contains measurement error. The technique can be extended and becomes more convenient relative to other approaches when more than two site visits are made by a single recreationist. These techniques are demonstrated in a Monte Carlo experiment.

Hedonic prices are estimated for summer and winter rentals for vacation houses located near a lake and ski-golf resort in rural western Maryland. Regressions for weekly rents are conditioned on house size, quality, and recreation features including lakefront proximity and ski-slope access. Percentage effects and marginal implicit prices indicate that access to recreation is reflected importantly in rental offers. Evaluated at the means, lakefront locations command a premium of $1,100–1,200 per week, and the premium for ski-slope access is $500–600 per week. Unit recreation values are about $18 per person per day for a lakefront location with a private dock and $7 per person per day for a ski-slope location. There are small differences in the unit values for three real estate management agencies. Although there is evidence of spatial correlation in ordinary least squares residuals, estimation of spatial-lag and spatial-error models does not yield substantial changes in the empirical results.

Conjoint analysis, widely used in marketing research, offers an alternative resource valuation approach suited to outdoor recreation activities characterized as multiattribute. Design, implementation, and interpretation of conjoint analysis are reviewed in the context of recreation applications. Conjoint analysis is used in an analysis of waterfowl hunting in Louisiana. Using primary data collected from a survey of waterfowl hunters, ordered logit is used to estimate willingness-to-pay for recreation experience attributes.

Treatment of time in travel cost models has been a source of contention among economists. The debate persists because welfare estimates, which are the principal objectives of these studies, are highly sensitive to the treatment of time. The present study examines the dual role of on-site time using evidence from two wilderness areas in Alabama. The empirical results comply with the theoretical expectation that on-site time is both a source of utility and cost. The exclusion of on-site time from demand functions results in biased parameter estimates. In particular, it yields smaller own-price coefficients and higher welfare estimates.

The paper tests two alternative specifications for the opportunity cost of time in travel cost models. The standard travel cost survey design is enriched to include a contingent valuation type question about peoples' willingness to accept compensation to forgo a precisely defined recreational experience. It is hypothesized that individually revealed value of time more appropriately reflects the opportunity costs of time associated with a particular aspect of recreation than the wage rate which measures the trade-off between work and leisure generally. The results seem to indicate a better overall fit for the models with the elicited value of individual consumer's time than for the models with the more traditional hourly earnings (wage rates). The importance of the correct measurement of the opportunity cost time is illustrated by showing that estimated consumer surpluses based on two different value of time measurements differ significantly.