修复 eval(m$data， parent.frame()) 中的错误：在 R 中找不到对象 'dzclass'

Question

我有这个数据帧(可复制(：

structure(list(age = c(62.84998, 60.33899, 52.74698, 42.38498
), death = c(0, 1, 1, 1), sex = c("male", "female", "female", 
"female"), hospdead = c(0, 1, 0, 0), slos = c(5, 4, 17, 3), d.time = c(2029, 
4, 47, 133), dzgroup = c("Lung Cancer", "Cirrhosis", "Cirrhosis", 
"Lung Cancer"), dzclass = c("Cancer", "COPD/CHF/Cirrhosis", "COPD/CHF/Cirrhosis", 
"Cancer"), num.co = c(0, 2, 2, 2), edu = c(11, 12, 12, 11), income = c("$11-$25k", 
"$11-$25k", "under $11k", "under $11k"), scoma = c(0, 44, 0, 
0), charges = c(9715, 34496, 41094, 3075), totcst = c(NA_real_, 
NA_real_, NA_real_, NA_real_), totmcst = c(NA_real_, NA_real_, 
NA_real_, NA_real_), avtisst = c(7, 29, 13, 7), race = c("other", 
"white", "white", "white"), sps = c(33.8984375, 52.6953125, 20.5, 
20.0976562), aps = c(20, 74, 45, 19), surv2m = c(0.262939453, 
0.0009999275, 0.790893555, 0.698974609), surv6m = c(0.0369949341, 
0, 0.664916992, 0.411987305), hday = c(1, 3, 4, 1), diabetes = c(0, 
0, 0, 0), dementia = c(0, 0, 0, 0), ca = c("metastatic", "no", 
"no", "metastatic"), prg2m = c(0.5, 0, 0.75, 0.899999619), prg6m = c(0.25, 
0, 0.5, 0.5), dnr = c("no dnr", NA, "no dnr", "no dnr"), dnrday = c(5, 
NA, 17, 3), meanbp = c(97, 43, 70, 75), wblc = c(6, 17.0976562, 
8.5, 9.09960938), hrt = c(69, 112, 88, 88), resp = c(22, 34, 
28, 32), temp = c(36, 34.59375, 37.39844, 35), pafi = c(388, 
98, 231.65625, NA), alb = c(1.7998047, NA, NA, NA), bili = c(0.19998169, 
NA, 2.19970703, NA), crea = c(1.19995117, 5.5, 2, 0.79992676), 
sod = c(141, 132, 134, 139), ph = c(7.459961, 7.25, 7.459961, 
NA), glucose = c(NA_real_, NA_real_, NA_real_, NA_real_), 
bun = c(NA_real_, NA_real_, NA_real_, NA_real_), urine = c(NA_real_, 
NA_real_, NA_real_, NA_real_), adlp = c(7, NA, 1, 0), adls = c(7, 
1, 0, 0), sfdm2 = c(NA, "<2 mo. follow-up", "<2 mo. follow-up", 
"no(M2 and SIP pres)"), adlsc = c(7, 1, 0, 0)), row.names = c(NA, 
4L), class = "data.frame")

我还制作了一张SUPPORT第3天生理学评分(sps(的图表，该评分按原发疾病类别(dzclass(分组，数据帧名称为SB_xlsx。

SB_xlsx = SB_xlsx[!is.na(SB_xlsx$sps), ]
ggplot(SB_xlsx, aes(x=dzclass, y=sps)) + geom_boxplot() + ggtitle("Box Plot - sps by Primary Disease Class") + xlab("Disease Class") + ylab("sps")

现在，我想测试人群的平均支持第3天生理学分数在原发疾病类别之间是否存在差异。我认为运行成对的t.tests是一个不错的选择，但我的代码有问题。

mu.diff = 0
alpha = 0.05
combs = combn(unique(SB_xlsx$dzclass), 2)
for (s in 1:ncol(combs)) {
i = combs[1, s]
j = combs[2, s]
tt = t.test(sps ~ dzclass, mu=mu.diff, var_equal=FALSE, 
conf_level=1-alpha, alternative='two.sided', 
data=SB_xlsx[dzclass == i | dzclass == j, ])
print(tt)
}

这是我目前掌握的代码。理论上应该是可行的，但由于某种原因，我犯了一个错误"eval(m$data，parent.frame(((中出错：找不到对象"dzclass"；。我对此感到困惑，因为dzclass显然在我的数据集中，所以我不确定它是怎么找不到的。

Answer 1

dzclass不是已知对象，但如果在子集参数中使用，则是已知对象。请注意，双面是默认设置，因此不必指定。

tt = t.test(sps ~ dzclass, data = SB_xlsx, subset = dzclass == i | dzclass == j,
mu = mu.diff, var_equal = FALSE, conf_level = 1 - alpha)

更进一步，我们可以这样缩短代码：

for(s in as.data.frame(combs)) {
tt = t.test(sps ~ dzclass, data = SB_xlsx, subset = dzclass %in% s, 
mu = mu.diff, var_equal = FALSE, conf_level = 1 - alpha)
print(tt)
}