r - 我对 regsubsets 做错了什么？

Question

我的任务是:

使用leaps包中的regsubsets函数进行穷举搜索

对于最佳子集回归模型。然后比较每个选择的调整后的r^2

子集大小。根据这个标准，哪个模型最好？你将不得不

查看 summary.regsubsets 的组件。在那里你可以找到相关的。

在每个尺寸下选择的最佳模型的不同最优性标准的值。

我有一个数据集 cigs，我调用它

q=regsubsets(Sales~Age+HS+Income+Black+Female+Price, data=cigs, method="exhaustive")

所有这些都是正确的变量

summary(q)

返回

Subset selection object
Call: regsubsets.formula(Sales ~ Age + HS + Income + Black + Female + 
    Price, data = cigs, method = "exhaustive")
6 Variables  (and intercept)
       Forced in Forced out
Age        FALSE      FALSE
HS         FALSE      FALSE
Income     FALSE      FALSE
Black      FALSE      FALSE
Female     FALSE      FALSE
Price      FALSE      FALSE
1 subsets of each size up to 6
Selection Algorithm: exhaustive
         Age HS  Income Black Female Price
1  ( 1 ) " " " " "*"    " "   " "    " "  
2  ( 1 ) " " " " "*"    " "   " "    "*"  
3  ( 1 ) "*" " " "*"    " "   " "    "*"  
4  ( 1 ) "*" " " "*"    "*"   " "    "*"  
5  ( 1 ) "*" " " "*"    "*"   "*"    "*"  
6  ( 1 ) "*" "*" "*"    "*"   "*"    "*"

知道为什么这没有给我关于 r^2 的任何信息吗？

Answer 1

您看到的只是您的 regsubsets 对象的打印摘要。如果您输入 ?regsubsets，您会看到 summary.regsubsets 返回的组件比打印的组件多。例如，要访问 r^2 只需键入:

summary_of_q <- summary(q)
summary_of_q$rsq