谱分析及其在门诊量统计分析中的应用

Spectral Analysis and Its Application in the Statistical Analysis of the Outpatient Flow

目的 以门诊量资料为例 ,计算功率谱密度函数 ,研究时间序列信号的频率域特征。方法 计算A.Schuster倡导的周期图 ,确定各周期成分的功率值 ,绘制功率谱密度函数图。结果 不同科别门诊量时序对应的频率特征得以直观表达 ,特征峰位置各有特点。经检验 ,时序为白噪声的零假设被拒绝。结论 在频率域中对时间序列进行谱分析 ,是对时间序列数据进行统计特征描述与推断的重要工具。

Objective The power spectral density functions of outpatient flow are calculated in order to study the spectral characteristics of the given time series. Methods The spectral estimation is based on the periodogram initiated by A. Schuster to illustrate the power distribution over through the frequency values. Results The spectral characteristics of the given time series describe the hidden periodicity in a visual way. The null hypothesis to be white noise has been rejected. Conclusion The spectral analysis method is an important approach to study time series.