数据

总体与样本

概念 定义
总体 (Population) 全部研究对象,规模 N(可无限)
样本 (Sample) 总体的子集,规模 n

参数与统计量

名称 来源 记号
Parameter 总体 (Population) μ,σ2\mu,\sigma^2
Statistics 样本 (Samples) xˉ,s2\bar x, s^2

目标:用样本统计量推断总体参数。

抽样方法

  • Random Sampling

  • Systematic Sampling: j[1,n],j+n,j+2n,j+3n,j\in[1,n], j+n, j+2n, j+3n,\dots

  • Descriptive statistics focus on graphical and numerical procedures that are used to summarize and the process data.

  • Inferential statistics focus on using the data to make predictions, forecasts, and estimates to make better decisions.

The target of statistics is to make decisions on a population parameter based on a sample statistic.

Sampling Error: n<Nn\lt N

Non-Sampling Error:

  • 受访对象错误
  • 受访者不诚实
  • 无回应

变量类型

按 Type and Amount of Information

可以分为 Categorical, Numerical

按 Level of Measurement

类型 特征
Nominal 无序分类
Ordinal 有序但无距离
Interval 有距离,无自然零点
Ratio 有自然零点