协助R错误消息
我试图从障碍回归模型的计数部分绘制拟合负二项式结果。 数据（可重复的子集）：
Age gender familysupport bullying Suicide. SuicideBinary NegBinSuicide
1 -0.771845 0 at risk -0.34840000 1 1 1
2 0.228155 0 at risk 0.05160000 0 0 NA
3 0.228155 0 resilient 0.45160000 1 1 1
4 4.228155 0 resilient 0.25160000 0 0 NA
5 -2.771845 1 resilient -0.44840000 0 0 NA
6 -2.771845 0 at risk -0.64840000 0 0 NA
7 -0.771845 0 resilient -0.04840000 0 0 NA
8 -0.771845 0 resilient -0.14840000 0 0 NA
9 -0.771845 1 at risk -0.64840000 0 0 NA
10 0.228155 0 at risk 0.05160000 0 0 NA
11 0.228155 0 at risk -0.24840000 0 0 NA
12 -2.771845 0 at risk 0.15160000 0 0 NA
13 -0.771845 0 resilient -0.14840000 0 0 NA
14 -1.771845 0 at risk -0.44840000 0 0 NA
15 4.228155 0 at risk -0.24840000 2 1 2
16 0.228155 0 resilient 0.05160000 1 1 1
17 -2.771845 0 resilient 0.05160000 0 0 NA
18 4.228155 0 at risk -0.44840000 0 0 NA
19 -2.771845 1 at risk 0.25160000 0 0 NA
20 -1.771845 1 at risk -0.54840000 0 0 NA
21 -0.771845 0 resilient -0.14840000 0 0 NA
22 -0.771845 0 at risk -0.34840000 0 0 NA
23 -2.771845 0 resilient -0.14840000 0 0 NA
24 0.228155 1 resilient -0.44840000 0 0 NA
25 0.228155 0 at risk -0.14840000 2 1 2
26 -0.771845 0 at risk 1.95160000 0 0 NA
27 -2.771845 1 at risk -0.44840000 1 1 1
28 -1.771845 0 at risk -0.04840000 0 0 NA
29 2.228155 0 resilient -0.44840000 0 0 NA
30 -0.771845 0 at risk -0.34840000 0 0 NA
31 4.228155 0 at risk 0.15160000 4 1 4
32 -0.771845 1 resilient 0.15160000 1 1 1
33 0.228155 0 resilient 0.45160000 0 0 NA
34 -0.771845 0 at risk 0.15160000 0 0 NA
35 -0.771845 0 at risk -0.04840000 0 0 NA
36 4.228155 0 resilient -0.54840000 0 0 NA
37 0.228155 0 resilient 0.05160000 0 0 NA
38 1.228155 0 at risk -0.34840000 1 1 1
39 2.228155 0 at risk 0.25160000 0 0 NA
40 -2.771845 0 at risk -0.34840000 1 1 1
41 0.228155 0 at risk 1.75160000 2 1 2
42 4.228155 0 at risk 0.65160000 0 0 NA
43 0.228155 0 resilient 0.25160000 NA NA NA
44 -1.771845 0 resilient -0.24840000 0 0 NA
45 -2.771845 0 at risk -0.04840000 3 1 3
46 -0.771845 0 resilient 0.25160000 0 0 NA
47 3.228155 0 resilient 0.45160000 0 0 NA
48 -0.771845 0 resilient 0.85160000 0 0 NA
49 -2.771845 1 at risk 0.25160000 2 1 2
50 -0.771845 0 at risk 0.15160000 0 0 NA
51 1.228155 0 resilient -0.44840000 0 0 NA
52 0.228155 0 at risk -0.34840000 0 0 NA
53 -2.771845 0 at risk -0.64840000 NA NA NA
54 -1.771845 0 at risk -0.14840000 6 1 6
55 1.228155 0 at risk -0.64840000 3 1 3
56 0.228155 0 resilient -0.64840000 0 0 NA
57 2.228155 0 resilient -0.64840000 0 0 NA
58 1.228155 0 resilient 1.05160000 0 0 NA
59 0.228155 0 at risk 0.25160000 0 0 NA
60 -0.771845 0 at risk 0.15160000 0 0 NA
61 -1.771845 0 resilient -0.64840000 0 0 NA
62 1.228155 0 at risk -0.44840000 0 0 NA
63 1.228155 0 at risk -0.64840000 0 0 NA
64 -0.771845 0 resilient -0.04840000 0 0 NA
65 -2.771845 0 at risk -0.64840000 0 0 NA
66 1.228155 0 at risk 0.15160000 2 1 2
67 2.228155 NA resilient -0.64840000 0 0 NA
68 0.228155 0 at risk -0.04840000 NA NA NA
69 -0.771845 0 at risk 0.05160000 0 0 NA
70 -0.771845 0 at risk -0.64840000 0 0 NA
71 -0.771845 0 resilient -0.64840000 0 0 NA
72 -0.771845 1 at risk 2.05160000 50 1 50
73 0.228155 0 resilient -0.44840000 0 0 NA
74 1.228155 0 resilient 2.95160000 0 0 NA
75 0.228155 0 resilient 1.25160000 3 1 3
76 1.228155 0 at risk 0.45160000 2 1 2
77 0.228155 0 resilient NA 0 0 NA
78 2.228155 0 at risk -0.04840000 0 0 NA
79 2.228155 0 at risk -0.64840000 2 1 2
80 0.228155 1 resilient 0.35160000 0 0 NA
81 -0.771845 0 resilient 0.25160000 2 1 2
82 -1.771845 1 resilient -0.44840000 0 0 NA
83 0.228155 0 at risk -0.64840000 0 0 NA
84 2.228155 0 resilient 0.01826667 0 0 NA
85 4.228155 0 resilient -0.14840000 0 0 NA
86 -2.771845 0 at risk 0.25160000 0 0 NA
87 0.228155 0 at risk -0.42617778 1 1 1
88 1.228155 0 resilient -0.64840000 0 0 NA
89 0.228155 0 resilient -0.04840000 0 0 NA
90 0.228155 0 resilient 0.15160000 0 0 NA
91 0.228155 0 at risk -0.64840000 1 1 1
92 0.228155 0 at risk -0.64840000 0 0 NA
93 4.228155 0 resilient -0.34840000 0 0 NA
94 4.228155 0 resilient -0.54840000 0 0 NA
95 1.228155 0 resilient 0.75160000 0 0 NA
96 3.228155 0 at risk -0.24840000 0 0 NA
97 -2.771845 0 resilient -0.64840000 0 0 NA
98 -1.771845 0 resilient 0.25160000 0 0 NA
99 -2.771845 0 resilient 0.35160000 2 1 2
100 -1.771845 0 at risk -0.64840000 0 0 NA
但是，当我使用以下代码时：
library(VGAM)
##model
mod <- vglm(NegBinSuicide ~ Age + gender + bullying*familysupport, family=posnegbinomial())
library(visreg)
##plot with INTERACTION TERM
visreg(mod, "bullying", by="familysupport", xlab = "bullying", ylab = "Count model (number of suicide attempts)")
我收到以下错误消息：
Error: $ operator not defined for this S4 class
我不确定这意味着什么。任何人都可以提供有关如何解决这个问题的见解吗？
最终，我正在尝试为两个组件绘制障碍回归输出，因为我的交互项在每个组件中都很重要。 （可能没有给出上面的样本数据）
library(pscl)
##Model
FullModel <- hurdle(Suicide. ~ Age + gender + bullying*familysupport | Age + gender + bullying*familysupport, dist = "negbin", link = "logit")
我想为每个障碍组件创建单独的图。我已经能够使用MASS中glm中的数据（它产生与障碍模型的logit部分相同的逻辑结果）在visreg中的logit部分（单独估计），但是使用glm.nb作为NB部分产生了不同的估计因此我决定从VGAM切换到vglm - 估计与障碍相同，但出现了绘图错误。
任何有关如何解决错误或如何绘制这些数据的见解都将非常感激。
1 个答案:
答案 0 :(得分：1)
我怀疑visreg包不支持VGAM::vglm。 ?visreg的帮助页面显示：
fit：您希望可视化的拟合模型对象。任何对象 使用'predict'和'model.frame'方法， 包括lm，glm，gam，rlm，coxph等等。
知道pscl包具有良好支持的负二项式障碍模型，我试过这个：
library(pscl)
## using the built-in "bioChemists" data set
hh <- hurdle(art~fem+mar,dist="negbin",data=bioChemists)
library(visreg)
visreg(hh)
似乎工作正常，可能适用于您的情况。
相关问题
最新问题
- 我写了这段代码，但我无法理解我的错误
- 我无法从一个代码实例的列表中删除 None 值，但我可以在另一个实例中。为什么它适用于一个细分市场而不适用于另一个细分市场？
- 是否有可能使 loadstring 不可能等于打印？卢阿
- java中的random.expovariate()
- Appscript 通过会议在 Google 日历中发送电子邮件和创建活动
- 为什么我的 Onclick 箭头功能在 React 中不起作用？
- 在此代码中是否有使用“this”的替代方法？
- 在 SQL Server 和 PostgreSQL 上查询，我如何从第一个表获得第二个表的可视化
- 每千个数字得到
- 更新了城市边界 KML 文件的来源？