杭州市GDP数据的统计诊断分析  

Statistical Diagnosis Analysis of Hangzhou’s GDP Data

作　　者：陆丹妮 宋红凤[1] 徐登可[1] 

机构地区：[1]浙江农林大学统计系,浙江 杭州

出　　处：《统计学与应用》2020年第2期296-303,共8页Statistical and Application

基　　金：浙江省高校重大人文社科攻关计划项目(2018QN037)。

摘　　要：国内生产总值(GDP)常被公认为是衡量国家经济状况的最佳指标,可以反映一个国家或地区的经济实力和市场规模。为探索影响杭州市GDP的主要因素,本文选择杭州市2000~2018年若干国民经济指标,基于多元线性回归建立回归模型。然后利用逐步回归法进行变量筛选,并对回归模型进行统计诊断,在一定标准下筛选模型中的强影响点,基于删除强影响点后的数据删除模型再次进行逐步回归分析,得到杭州市GDP与年末常住人口、固定资产投资额、居民消费指数以及财政总收入密切相关。Gross domestic product (GDP) is often recognized as the best indicator to measure the economic situation of a country, which can reflect the economic strength and market size of a country or region. In order to explore the main factors affecting Hangzhou’s GDP, this paper selects several national economic indicators of Hangzhou from 2000 to 2018, and establishes a regression model based on multiple linear regression. Then the stepwise regression method is used to screen variables, and statistical diagnosis is carried out for the regression model. The strong influence points in the model are screened under certain standards. Based on the data deletion model after deleting the strong influence points, the stepwise regression analysis is carried out again, and the conclusion is that the GDP of Hangzhou is closely related to the year-end resident population, fixed asset investment, resident consumption index and total fiscal revenue.

关 键 词：GDP 多元线性回归 多重共线性 统计诊断 COOK距离 W-K统计量 

分 类 号：F12[经济管理—世界经济]