机器算法验证 - R 中 ivreg() 诊断的解释 - 吾爱随笔录

我正试图ivreg()从 {AER} 包中解释 R 中命令的诊断。运行帮助页面中提供的示例代码：

## data
data("CigarettesSW", package = "AER")
CigarettesSW$rprice <- with(CigarettesSW, price/cpi)
CigarettesSW$rincome <- with(CigarettesSW, income/population/cpi)
CigarettesSW$tdiff <- with(CigarettesSW, (taxs - tax)/cpi)

## model 
fm <- ivreg(log(packs) ~ log(rprice) + log(rincome) | log(rincome) + tdiff + I(tax/cpi), data = CigarettesSW, subset = year == "1995")
summary(fm, vcov = sandwich, df = Inf, diagnostics = TRUE)

您会得到以下输出：

Call:
ivreg(formula = log(packs) ~ log(rprice) + log(rincome) | log(rincome) + 
tdiff + I(tax/cpi), data = CigarettesSW, subset = year == 
"1995")

Residuals:
   Min         1Q     Median         3Q        Max 
-0.6006931 -0.0862222 -0.0009999  0.1164699  0.3734227 

Coefficients:
         Estimate Std. Error z value Pr(>|z|)    
(Intercept)    9.8950     0.9288  10.654  < 2e-16 ***
log(rprice)   -1.2774     0.2417  -5.286 1.25e-07 ***
log(rincome)   0.2804     0.2458   1.141    0.254    

Diagnostic tests:
             df1 df2 statistic p-value    
Weak instruments   2  44   228.738  <2e-16 ***
Wu-Hausman         1  44     3.823  0.0569 .  
Sargan             1  NA     0.333  0.5641

我对诊断测试的解释很感兴趣。这是否意味着这些工具很弱或没有？考虑到它在 10% 的水平上显着，Wu-Hausman 是什么意思？Sargan 不重要意味着什么？