论文部分内容阅读
目的在相关回归分析的基础上,运用响应面模型分析对影响鼠密度的复合气象因素进行研究。方法连续监测鼠密度与7种气象因子资料,进行相关和线性回归分析,建立气象因子对鼠密度影响的响应面模型。结果线性回归分析表明月平均最低气温、日照时间、降雨量对回归方程的贡献最大,线性回归方程有统计学意义(P<0.030),复相关系数为0.716。响应面分析表明月平均最低气温(P=0.003)、降雨量的二次方(P=0.059)、月平均最低气温与日照的交互作用(P=0.027)是影响鼠密度的气象因素,响应面模型有统计学意义(P<0.013),复相关系数为0.761。结论响应面分析法能够较好地应用于气象因子对鼠密度的影响,建立的响应面模型优于多元线性回归,气象因素对鼠密度的影响是多因素及交互作用的结果。
Objective Based on the correlation analysis, the response surface model was used to analyze the composite meteorological factors that affect the rat density. Methods The data of seven kinds of meteorological factors and the density of rats were continuously monitored. Correlation and linear regression analysis were carried out to establish the response surface model of the influence of meteorological factors on mouse density. Results The linear regression analysis showed that the monthly mean minimum temperature, sunshine duration and rainfall contributed the most to the regression equation. The linear regression equation was statistically significant (P <0.030) and the complex correlation coefficient was 0.716. The response surface analysis showed that the monthly mean minimum temperature (P = 0.003), the quadratic rainfall (P = 0.059) and the interaction between monthly mean minimum temperature and sunshine (P = 0.027) were the meteorological factors affecting the rat density. The response surface The model was statistically significant (P <0.013), the complex correlation coefficient was 0.761. Conclusion The response surface analysis (RSA) method can be applied to the effect of meteorological factors on mouse density. The established response surface model is better than multivariate linear regression. The influence of meteorological factors on mouse density is the result of multiple factors and interactions.