Hello, I am running a model with four categories and want predicted
probabilities in each category. Now for this example I wont give a
counterfactual just the training data is fine but is there anyway to get a
confidence interval around the predicted probabilities in each group? I have
tried but it gives me probabilities and I have used
interval="confidence",
level=.095 and then interval = "prediction". Below is a sample of my
data
and my code I am trying to run (its from an open access public data set; I
tried to make the size as small as possible, sorry for its length).
polr.result<-polr(ordered(tvwatch)~ses+testscores,method="probit",Hess
T,data=testdata)
polr.predict<-predict(polr.result,type="probs",interval="confidence",level=.
95)
structure(list(tvwatch = c(2L, 2L, 1L, 4L, 2L, 4L, 3L, 2L, 3L,
2L, 3L, 4L, 4L, 3L, 4L, 3L, 2L, 1L, 3L, 1L, 2L, 3L, 4L, 4L, 1L,
1L, 2L, 2L, 4L, 4L, 2L, 1L, 3L, 3L, 3L, 2L, 4L, 2L, 1L, 1L, 1L,
1L, 2L, 3L, 4L, 4L, 2L, 1L, 2L, 2L), ses = c(-0.529, -0.377,
-0.859, -0.191, -0.319, -0.292, -0.601, -0.07, 0.198, 0.096,
0.136, -0.101, 0.11, -0.182, -0.323, 0.205, 0.21, 0.749, -0.273,
0.66, 0.009, -0.374, -0.094, -0.427, 1.369, -1.306, 0.611, 0.392,
-0.371, 1.059, 1.308, -0.89, -1.741, -0.169, 0.13, -0.698, 0.385,
-0.067, -0.386, 0.813, 0.997, 1.46, 1.196, -0.723, -0.612, 0.119,
1.421, -1.02, -0.807, 1.33), testscores = c(53.38, 57.91, 54.64,
45.67, 58.74, 57.55, 63.78, 59.97, 51.41, 49.54, 65.82, 44.04,
45.8, 56.67, 35.6, 50.41, 45.18, 61.22, 61.24, 66.58, 64.91,
40.79, 41.77, 46.51, 59.83, 49.95, 58.1, 54.53, 58.31, 69.92,
66.4, 50.94, 51.23, 47.45, 37.93, 59.66, 60.59, 55.11, 40.65,
67.89, 52.54, 61.76, 69.71, 44.37, 43.53, 45.89, 75.81, 53.18,
51.85, 58.03)), .Names = c("tvwatch", "ses",
"testscores"), row.names c(1L,
2L, 3L, 4L, 5L, 6L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 18L,
19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 28L, 29L, 30L, 31L, 32L,
34L, 35L, 38L, 39L, 40L, 41L, 42L, 44L, 45L, 46L, 47L, 48L, 49L,
50L, 54L, 55L, 56L, 57L, 58L, 59L, 60L, 61L), class = "data.frame")
-------------------------------------------
Joe King, M.A.
Ph.D. Student
University of Washington - Seattle
206-913-2912
<mailto:jp@joepking.com> jp@joepking.com
-------------------------------------------
Ad astra per aspera - "Through hardships to the stars"
[[alternative HTML version deleted]]
