Purpose The purpose of this paper is to investigate the accuracy and volatility of different methods for estimating and updating hedonic valuation models. Design/methodology/approach The authors apply six estimation methods (linear least squares, robust regression, mixed-effects regression, random forests, gradient boosting and neural networks) and two updating methods (moving and extending windows). They use a large and rich data set consisting of over 123,000 single-family houses sold in Switzerland between 2005 and 2017. Findings The gradient boosting method yields the greatest accuracy, while the robust method provides the least volatile predictions. There is a clear trade-off across methods depending on whether the goal is to improve accuracy or avoid volatility. The choice between moving and extending windows has only a modest effect on the results. Originality/value This paper compares a range of linear and machine learning techniques in the context of moving or extending window scenarios that are used in practice but which have not been considered in prior research. The techniques include robust regression, which has not previously been used in this context. The data updating allows for analysis of the volatility in addition to the accuracy of predictions. The results should prove useful in improving hedonic models used by property tax assessors, mortgage underwriters, valuation firms and regulatory authorities.

No abstract

No abstract

No abstract

Extreme value data with a high clump-at-zero occur in many domains.Moreover, it might happen that the observed data are either truncated below a given threshold and/or might not be reliable enough below that threshold because of the recording devices. This situations occurs in particular with radio audience data measured using personal meters that record environmental noise every minute, that is then matched to one of the several radio programs. There are therefore genuine zeroes for respondents not listening to the radio, but also zeroes corresponding to real listeners for whom the match between the recorded noise and the radio program could not be achieved. Since radio audiences are important for radio broadcasters in order for example to determine advertisement price policies, possibly according to the type of audience at different time points, it is essential to be able to explain not only the probability of listening a radio but also the average time spent listening the radio by means of the characteristics of the listeners. In this paper, we propose a generalized linear model for zeroinflated truncated Pareto distribution (ZITPo) that we use to fit audience radio data. Because it is based on the generalized Pareto distribution, the ZITPo model has nice properties such as model invariance to the choice of the threshold and from which a natural residual measure can be derived to assess the model fit to the data. From a general formulation of the most popular models for zero-inflated data, we derive our model by considering successively the truncated case, the generalized Pareto distribution and then the inclusion of covariates to explain the non-zero proportion of listeners and their mean listening time. By means of simulations, we study the performance of the maximum likelihood estimator (and derived inference) and use the model to fully analyze the audience data of a radio station in an area of Switzerland.