Sas 简明教程
SAS - Hypothesis Testing
假设检验是用统计数据确定给定假设为真的概率。假设检验的通常过程由以下四步组成。
Step-4
将 p 值与可接受的显著性值 alpha(有时称为 alpha 值)比较。如果 p ⇐alpha,即观测效应具有统计显着性,则排除原假设,而备择假设有效。
SAS 编程语言具有执行各种类型假设检验的功能,如下所示。
Test |
Description |
SAS PROC |
T-Test |
A t-tests is used to test whether the mean of one variable is significantly different than a hypothesized value.We also determine whether means for two independent groups are significantly different and whether means for dependent or paired groups are significantly different. |
PROC TTEST |
ANOVA |
It is also used to compare means when there is one independent categorical variable. We want to use one-way ANOVA when testing to see if the means of the interval dependent variable are different according to the independent categorical variable. |
PROC ANOVA |
Chi-Square |
We use chi square goodness of fit to assess if frequencies of a categorical variable were likely to happen due to chance. Use of a chi square test is necessary whether proportions of a categorical variable are a hypothesized value. |
PROC FREQ |
Linear Regression |
Simple linear regression is used when one wants to test how well a variable predicts another variable. Multiple linearregression allows one to test how well multiple variables predict a variable of interest. When using multiple linear regression, we additionally assume the predictor variables are independent. |
PROC REG |