论文标题
多重膨胀的负二项式障碍回归模型：对大衰退期间意大利人的旅游行为的分析
A multiple inflated negative binomial hurdle regression model: analysis of the Italians' tourism behaviour during the Great Recession
论文作者
论文摘要
我们分析了涵盖2008年大萧条时期意大利居民的旅游行为。使用意大利国家统计研究所进行的意大利居民和国外季度调查的意大利居民旅行，我们调查了经济衰退是否以及如何影响过夜的总数。响应变量是两个阶段决策过程的结果：首先，我们选择度假，然后花多长时间。此外，由于隔夜停留的数量通常集中在特定的长度上（周末，周，每两周），我们在其分布中观察到了多个特殊的尖峰。要考虑到这两个独特的特征，我们通过指定阳性响应的多个膨胀的截短负二项式分布来概括通常的障碍回归模型。结果表明，经济衰退对决策过程的两个组成部分产生了负面影响，并且，通过控制响应变量分布的膨胀性质，拟议的配方与非充气栏模模型相比，可以更好地表示意大利人的旅游行为。鉴于此，我们认为我们的模型可以成为试图预测新目标政策以支持旅游经济影响的政策制定者的有用工具。
We analyse tourism behaviour of Italian residents in the period covering the 2008 Great Recession. Using the Trips of Italian Residents in Italy and Abroad quarterly survey, carried out by the Italian National Institute of Statistics, we investigate whether and how the economic recession has affected the total number of overnight stays. The response variable is the result of a two-stage decision process: first we choose to take a holiday, then for how long. Moreover, since the number of overnight stays is typically concentrated on specific lengths (week-end, week, fortnight) we observe multiple peculiar spikes in its distribution. To take into account these two distinctive characteristics, we generalise the usual hurdle regression model by specifying a multiple inflated truncated negative binomial distribution for the positive responses. Results show that the economic recession impacted negatively on both components of the decision process and that, by controlling for the inflated nature of the response variable's distribution, the proposed formulation provides a better representation of the Italians' tourism behaviour in comparison with non-inflated hurdle models. Given this, we believe that our model can be a useful tool for policy makers who are trying to forecast the effects of new targeted policies to support tourism economy.
