Графики валидации / конвергенции для упорядоченной переменной с использованием мышей в R - PullRequest
0 голосов
/ 02 апреля 2020

Я начинаю вопрос с указанием данных:

data_s <- structure(list(RC_8 = c(7, 5, 6, 4, NA, 7, 7, 6, 4, 7, 6, 4, 
7, 5, 7, 6, 5, 4, 5, 3, 5, 6, 6, 6, 6, 7, 5, 5, 7, 7, 7, 7, 6, 
7, 5, 7, 5, 6, 7, 1, 6, 7, 5, 6, 5, 5, 6, 5, 7, 2, 6, 6, 5, 6, 
7, 3, 6, 7, 6, 7, 5, 7, 6, 6, 6, 6, 6, 6, 5, 7, 5, 6, 5, 7, 5, 
5, 7, 5, 7, 7, 6, 7, 4, 7, 7, 4, 7, 5, 7, 7, 7, 4, 7, 6, 5, 6, 
3, 4, 6, 7, 3, 6, 7, 6, 7, 7, 7, 5, 6, 7, 7, 5, 5, 7, 6, 6, 3, 
4, 4, 7, 6, 6, 7, 5, 5, 7, 6, 4, 7, NA, 7, 7, 4, 4, 2, 7, 7, 
5, 7, 6, 4, 7, 7, 3, 5, 7, 5, 6, 7, 5, 3, 1, 7, 7, 7, 6, 7, 7, 
5, 5, 7, 4, 4, 6, 6, 7, 6, 7, 7, 6, 5, 5, 6, 4, 4, 7, 6, 1, 7, 
5, 5, 6, 5, 6, 5, 6, 5, 5, 7, 5, 1, 7, 6, 6, 4, 7, 5, 7, 7, 4
), RC_9 = c(7, 5, 6, 3, 7, 7, 7, 6, 4, 7, 6, 5, 7, 7, 7, 6, 7, 
2, 6, 7, 5, 6, 6, 6, 6, 7, 5, 5, 7, 7, 7, 7, 7, 7, 6, 6, 7, 7, 
7, 2, 5, 6, 4, 6, 5, 5, 7, 6, 7, 7, 7, 7, 5, 6, 7, 5, 6, 7, 6, 
7, 6, 7, 6, 6, 6, 6, 6, 6, 6, 7, 5, 6, 5, 7, 6, 5, 7, 5, 7, 7, 
6, 7, 4, 6, 7, 4, 7, 6, 7, 6, 7, 5, 6, 6, 5, 6, 3, 6, 6, 7, 3, 
6, 7, 6, 7, 7, 7, 4, 6, 7, 7, 7, 6, 6, 6, 6, 3, 7, 5, 7, 6, 7, 
3, 5, 7, 7, 6, 4, 7, 6, 7, 7, 4, 5, 2, 6, 7, 7, 7, 6, 3, 7, 7, 
3, 5, 7, 5, 6, 7, 5, 5, 1, 7, 6, 6, 7, 7, 7, 3, 5, 7, 4, 7, 6, 
7, 7, 6, 7, 7, 6, 5, 5, 6, 4, 5, 7, 5, 1, 7, 5, 5, 7, 4, 7, 5, 
6, 5, 5, 7, 6, 1, 7, 6, 5, 4, 7, 5, 7, 7, 6), RC_10 = c(6, 5, 
7, 6, 6, 6, 7, 6, 2, 7, 6, 5, 7, 7, 7, 7, 7, 1, 6, 6, 7, 4, 6, 
6, 6, 7, 5, 5, 7, 7, 7, 7, 7, 6, 6, 7, 7, 6, 7, 7, 5, 6, 4, 6, 
5, 7, 5, 5, 7, 2, 7, 7, 5, 6, 6, 5, 5, 6, 5, 7, 5, 7, 6, 7, 5, 
4, 7, 6, 6, 6, 5, 4, 7, 6, 5, 4, 7, 7, 7, 7, 4, 4, 3, 6, 7, 5, 
7, 6, 7, 6, 6, 7, 7, 6, 6, 5, 4, 3, 5, 7, 7, 7, 7, 6, 5, 7, 7, 
5, 7, 6, 5, 5, 6, 6, 6, 5, 5, 6, 5, 4, 3, 6, 5, 5, 6, 6, 6, 5, 
1, NA, 7, 5, 4, 5, 7, 6, 7, 5, 7, 6, 4, 7, 4, 3, 6, 6, 5, 6, 
7, 6, 6, 1, 4, 2, 6, 7, 7, 7, 2, 5, 7, 4, 4, 6, 7, 7, 6, 6, 7, 
5, 7, 7, 5, 6, 5, 4, 6, 1, 6, 6, 6, 5, 1, 7, 5, 7, 5, 4, 7, 6, 
1, 7, 6, 3, 4, 6, 5, 7, 7, 6), RC_11 = c(7, NA, NA, NA, 5, 7, 
3, 5, NA, 7, 6, 3, NA, 1, 1, 4, 6, NA, NA, NA, 1, 2, 7, NA, 6, 
7, 2, NA, 7, 2, 6, 6, 6, 2, 6, NA, NA, 6, 7, 1, 6, NA, NA, 4, 
4, 4, 3, NA, 4, 7, 4, NA, 4, NA, 7, 2, 5, 6, NA, 7, NA, 7, 4, 
1, 1, 1, 1, 6, NA, 7, NA, NA, NA, 4, 4, NA, 7, 5, 7, NA, 5, NA, 
NA, 5, 4, 4, 7, 7, 5, 5, NA, 2, 7, NA, NA, NA, NA, 5, NA, 5, 
1, 6, 7, 3, 3, NA, 4, NA, NA, 7, 6, NA, NA, NA, 2, NA, 1, 4, 
2, 7, 4, NA, 1, NA, NA, 6, NA, 2, NA, NA, 7, 5, 3, NA, NA, NA, 
3, 1, 7, 1, 3, NA, 7, 1, 3, 2, NA, NA, 6, 2, NA, 1, NA, 2, 5, 
5, NA, 5, 3, 4, 5, NA, NA, NA, 3, 7, 6, 6, 5, 3, NA, 3, NA, 2, 
6, NA, 4, 1, 6, 5, 5, NA, 1, 7, 5, 6, 4, NA, NA, NA, NA, 7, 7, 
NA, 6, 2, 5, 7, 4, 1), RC_12 = c(6, NA, NA, NA, 7, 6, 5, 4, NA, 
6, 6, 5, NA, 7, 1, 6, 7, NA, NA, NA, 5, 6, 7, NA, 6, 7, 2, NA, 
7, 1, 6, 7, 6, 6, 7, NA, NA, 6, 7, 7, 6, NA, NA, 6, 5, 7, 4, 
NA, NA, 2, 6, NA, 4, NA, 7, 3, 5, 7, NA, 7, NA, 7, 6, 3, 1, 1, 
4, 6, NA, 7, NA, NA, NA, 5, 4, NA, 7, 4, 7, NA, 5, NA, NA, 6, 
4, 1, 7, 7, 5, 6, NA, 2, 7, NA, 3, NA, NA, 4, NA, 5, 7, 7, 7, 
6, 6, NA, 5, NA, NA, 7, 6, NA, NA, NA, NA, NA, 1, 1, 2, 7, 4, 
NA, 4, NA, NA, 6, NA, 1, NA, NA, 7, 7, 4, NA, NA, NA, 5, 5, 7, 
5, 2, NA, 4, 7, 3, 6, NA, NA, 4, 4, NA, 1, NA, 1, 6, 4, NA, 2, 
4, 6, 7, NA, NA, NA, 6, 6, 7, 6, 6, 3, NA, 5, NA, 2, 3, NA, 3, 
1, 7, 6, 4, NA, 1, 7, 5, 7, 4, NA, NA, NA, NA, 7, 7, NA, 6, 6, 
5, 7, 4, 1), RC_13 = c(7, NA, NA, NA, 4, 7, 1, 5, NA, 6, 6, 2, 
NA, 6, 1, 7, 7, NA, NA, NA, 1, 1, 5, NA, 6, 7, 2, NA, 7, 1, 6, 
1, 7, 4, 7, NA, NA, 7, 7, 4, 5, NA, NA, 5, 4, 4, 2, NA, NA, 2, 
6, NA, 4, NA, 7, 2, 5, 7, NA, 5, NA, 6, 6, 3, 6, 1, 7, 6, NA, 
6, NA, NA, NA, 4, 3, NA, 7, 5, 7, NA, NA, NA, NA, 5, 7, 1, 7, 
1, 6, 7, NA, 1, 6, NA, 3, NA, NA, 1, NA, 4, 7, 6, 7, 6, 6, NA, 
1, NA, NA, 7, 6, NA, NA, NA, 6, NA, 1, 1, 2, 5, 3, NA, 3, NA, 
NA, 6, NA, 1, NA, NA, 7, 7, 4, NA, NA, NA, 1, 5, 7, 5, 2, NA, 
2, 4, 3, 4, NA, NA, 5, 1, NA, 1, NA, 2, 3, 6, NA, 5, 6, 5, 4, 
NA, NA, NA, 1, 7, 7, 3, 6, 4, NA, 5, NA, 4, 3, NA, 3, 1, 6, 5, 
4, NA, 2, 7, 5, 5, 6, NA, NA, NA, NA, NA, 5, NA, 4, 2, 5, 7, 
4, 1), RC_14 = c(7, 6, 7, 6, 6, 6, 4, 6, 5, 7, 6, 2, 5, 7, 5, 
7, 6, 4, 6, 7, 7, 7, 6, 6, 6, 7, 2, 4, 7, 4, 7, 7, 6, 7, 6, 6, 
7, 6, 7, 4, 7, 5, 6, 4, 5, 7, 2, 5, NA, 4, 6, 5, 4, 5, 6, 4, 
6, 7, 7, 7, 6, 7, 6, 7, 6, 4, 6, 6, 5, 7, 6, 5, 5, 7, NA, 5, 
7, 5, 7, 6, 2, 6, 7, 6, 4, 1, 6, NA, 6, 7, NA, 5, 6, NA, 3, 4, 
4, 4, 6, 7, 7, 6, 7, 6, 6, 7, 6, 6, NA, 7, 7, 6, 5, 7, NA, 4, 
5, 7, 3, 6, 1, 6, 6, NA, 6, 7, 6, 1, 7, 5, 7, 7, 5, 4, 4, 6, 
5, 4, 7, 5, 3, 4, 2, 4, 3, 7, 5, 5, 6, 3, 5, 1, 5, 1, 6, 6, 4, 
2, 2, 6, 4, 6, 6, 5, 7, 6, 6, 6, 7, 4, 6, 5, 5, 3, 5, 6, 6, 1, 
7, 6, 5, 5, 1, 6, 5, 7, 5, 6, 7, 4, NA, 6, 6, 5, 4, 3, 5, 7, 
6, 6), RC_15 = c(7, 7, 5, 5, 7, 7, 5, 6, 4, 5, 6, 2, 6, 7, 7, 
7, 7, 1, 7, 6, 7, 7, 5, 6, 7, 7, 2, 4, 6, 7, 6, 4, 7, 6, 7, 7, 
7, 6, 7, 1, 7, 7, 7, 5, 5, 6, 5, 6, 7, 2, 5, 7, 4, 4, 6, 6, 5, 
7, 6, 7, 7, 7, 4, 7, 7, 7, 4, 7, 6, 7, 7, 5, 6, 1, 6, 6, 5, 6, 
7, 7, 6, 7, 6, 6, 7, 4, 7, 5, 7, 7, 5, 6, 6, 5, 3, 5, 5, 4, 5, 
7, 7, 5, 7, 6, 4, 7, 7, 7, 5, 7, 5, 6, 4, 7, 7, 7, 6, 7, 5, 7, 
1, 7, 6, 7, 6, 5, 7, 6, 7, 7, 7, 5, 5, 5, 7, 5, 2, 3, 7, 5, 2, 
6, 2, 7, 6, 6, 7, 7, 7, 6, 4, 1, 6, 3, 4, 6, 5, 7, 2, 5, 7, 5, 
3, 6, 2, 7, 6, 7, 7, 4, 5, 4, 7, 5, 6, 6, 4, 1, 6, 7, 7, 7, 1, 
6, 5, 7, 4, 7, 7, NA, 1, 7, 5, 7, 3, 2, 5, 7, 4, 5)), row.names = c(NA, 
-200L), class = c("tbl_df", "tbl", "data.frame"))

Я делаю вменение в мои 7-балльные данные Ликерта, полученные из опроса. Проблема в том, что большинство графических c методов не работают для этого типа данных. Например:

data_s <- as.data.frame(data_s)
data_s[] <- lapply(data_s, as.ordered) # I have to do it to mice apply polr method
names(data_s) <- gsub("_", "", names(data_s))
impute_data <- mice(data_s, m = 5, maxit = 4,
                    method = "polr", seed = 1212, printFlag = F)

А затем я могу оценить качество вмененных данных plot, что работает нормально. densityplot не работает, потому что мои данные не являются непрерывными, что является приемлемым.

  1. , почему функция stripplot работает только для числовых данных c? Разве это не будет хорошей возможностью, чтобы добавить его и для ordered данных? Я ожидал панель для каждой переменной, где по оси Y указаны значения, которые может принимать моя переменная, а по оси X - число импутаций.

  2. Более того, как я могу интерпретировать probplot, который показан в этой виньетке :

    источника ("https://gist.githubusercontent.com/NErler/0d00375da460dd33839b98faeee2fdab/raw/c6f537ecf80eddcefd94992ec7926aa57d454536/propplot.R") пропплота (impute_data) enter image description here

  3. Есть ли еще какие-нибудь графики c, которые я могу сделать, чтобы увидеть образец вмененного и реального графика?

Заранее спасибо!

...