Question

我正在运行从UCLA下载的数据集

read.dta("https://stats.idre.ucla.edu/stat/data/ologit.dta")

，并在自变量中随机分配一些缺失值：pared，public和gpa。然后，我使用鼠标生成估算值，并对具有估算值的5个完整数据集进行有序逻辑回归。

DAT.imp=mice(DAT,print=FALSE)
DAT.fit.mice.plr = with(DAT.imp, polr(apply ~ pared + public + gpa))
summary(DAT.fit.mice.plr)

但是错误消息显示如下：

Error in as.data.frame.default(x) : 
 cannot coerce class ""polr"" to a data.frame

这是一个问题，因为pool（）函数无法运行不属于lm的模型吗？我是否应该通过polr（）分别为5个估算数据集运行模型并手动合并它们？预先感谢您的任何答复。

Answer 1

这应该做到：

data_noimp <- read.dta("https://stats.idre.ucla.edu/stat/data/ologit.dta")

data_noimp[c(1, 15, 20, 200), 2] <- NA
data_noimp[c(1, 30, 50, 150), 3] <- NA
data_noimp[c(1, 50, 70, 250), 4] <- NA

data_imp = mice(data_noimp, print=FALSE, m = 5)

mod <-  with(data_imp, polr(apply ~ pared + public + gpa, Hess = TRUE))
summary(pool(mod))

> summary(pool(mod))
                                     est        se           t       df
pared                        1.107674490 0.2713236  4.08248505 344.4757
public                      -0.006703536 0.3009678 -0.02227326 370.4461
gpa                          0.641763808 0.2623608  2.44611162 380.4930
unlikely|somewhat likely     2.295188221 0.7848823  2.92424510 382.4064
somewhat likely|very likely  4.402820363 0.8108302  5.43001523 382.6683
                                Pr(>|t|)      lo 95     hi 95 nmis
pared                       5.543550e-05  0.5740151 1.6413339    4
public                      9.822420e-01 -0.5985232 0.5851162    4
gpa                         1.489271e-02  0.1259052 1.1576224    4
unlikely|somewhat likely    3.658528e-03  0.7519630 3.8384135   NA
somewhat likely|very likely 1.003383e-07  2.8085801 5.9970606   NA
                                   fmi     lambda
pared                       0.03853733 0.03297131
public                      0.02549015 0.02024303
gpa                         0.01899782 0.01385485
unlikely|somewhat likely    0.01754762 0.01242275
somewhat likely|very likely 0.01734109 0.01221865

Answer 2

我尝试安装具有依赖关系的软件包的最新版本：

install.packages(c("mice", "MASS"), dep = TRUE)

取得了结果
> summary(pool(mod)) estimate std.error statistic df p.value pared 1.088364240 0.2675445 4.0679748 388.8699 5.744000e-05 public -0.007057661 0.3020328 -0.0233672 376.9368 9.813694e-01 gpa 0.628030991 0.2610602 2.4056945 387.3003 1.660783e-02 unlikely|somewhat likely 2.250628213 0.7816727 2.8792461 386.0658 4.206607e-03 somewhat likely|very likely 4.353582378 0.8076085 5.3907086 385.6545 1.219831e-07 和

> pool(mod) Class: mipo m = 5 estimate ubar b t dfcom df pared 1.088364240 0.07111586 0.0003868321 0.07158006 395 388.8699 public -0.007057661 0.08973729 0.0012387621 0.09122381 395 376.9368 gpa 0.628030991 0.06759665 0.0004631305 0.06815241 395 387.3003 unlikely|somewhat likely 2.250628213 0.60530521 0.0047558921 0.61101228 395 386.0658 somewhat likely|very likely 4.353582378 0.64589464 0.0052807731 0.65223157 395 385.6545

riv lambda fmi pared 0.006527356 0.006485026 0.01155566 public 0.016565181 0.016295247 0.02147350 gpa 0.008221658 0.008154614 0.01323709 unlikely|somewhat likely 0.009428418 0.009340353 0.01443286 somewhat likely|very likely 0.009811086 0.009715764 0.01481172

略有不同。报告的统计信息也略有不同。我不确定它是正确的（仅由于插补）。但是代码运行良好，没有错误。

MICE是否可以通过函数polr（）运行序数逻辑回归的结果？

2 个答案: