美国户外休闲产业发展特征及预测模型构建研究——基于PLS和PLS-DA方法的分析-《体育科学研究》

文章信息/Info

Title:: Research on the Development Characteristics and Prediction Models of American Outdoor Leisure Industry——Analysis Based on PLS and PLS-DA Methods

Author(s):: LEI Wen1; WEI Deyang2; 1.Department of Physical Education, Minjiang University, Fuzhou 350108,China;2.School of Physical Education and Sport Science,Fujian Normal University,Fuzhou 350117,China

Keywords:: outdoor recreation; partial least squares method; partial least squares discriminant analysis; United States

摘要:: 户外休闲产业是美国经济的支柱性产业，分析其发展特征和构建预测模型对于我国健身休闲产业健康、可持续发展有重要借鉴价值。研究收集了美国50个州2021年户外休闲产业相关数据，选取27个影响指标，运用PLS和PLS-DA方法，对美国户外休闲产业发展特征进行分析并构建预测模型。研究表明：（1）美国州域户外休闲产业可分为4种发展模式，即总量大占比小型、总量小占比大型、总量较大占比较小型、总量较小占比较大型，4种发展模式在空间上呈现一定集聚分布特征。（2）构建的预测模型有效且精度较高，并筛选出12个VIP指标，经济、人口和社会因素似乎更多地影响美国户外休闲产业发展，而自然环境因素的影响相对较弱。

Abstract:: Outdoor recreation is a pillar industry of the American economy. Analyzing its development characteristics and constructing prediction models will have important reference value for the healthy and sustainable development of China’s fitness and leisure industry. We collected data on the outdoor leisure industry in the 50 states of the United States in 2021, selected 27 impact indicators, and used the PLS and PLS-DA methods to analyze the development characteristics of the outdoor recreation in the United States and build predictive models. Studies show that: (1) The U.S. state outdoor recreation can be divided into 4 development modes, namely, high total amount, low proportion; low total amount, high proportion; total amount relatively high, proportion relatively low; total amount relatively low, proportion relatively high. The four development models present certain spatial distribution characteristics. (2) The prediction model is effective and highly accurate, and 12 VIP indicators are screened out; economic, demographic, and social factors seem to affect the development of outdoor recreation in the United States more, but the impact of natural environmental factors is relatively weak.