Summarise proportions of treatment response by two subgroups - r

I generated the following random data which has the same structure as my real data:
data <- structure(list(gender = structure(c(1L, 2L, 1L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L), .Label = c("Female",
"Male"), class = "factor"), treatment_response = structure(c(2L,
2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L,
1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L,
1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L,
1L, 2L, 1L), .Label = c("Non-responder", "Responder"), class = "factor"),
country = structure(c(1L, 3L, 9L, 7L, 2L, 2L, 6L, 6L, 4L,
9L, 5L, 7L, 3L, 2L, 8L, 8L, 10L, 3L, 1L, 1L, 9L, 2L, 5L,
5L, 2L, 7L, 5L, 1L, 6L, 10L, 7L, 10L, 2L, 10L, 1L, 4L, 6L,
8L, 9L, 4L, 3L, 6L, 1L, 8L, 7L, 3L, 2L, 10L, 7L, 6L, 1L,
9L, 8L, 4L, 8L, 7L, 3L, 5L, 3L, 4L, 7L, 4L, 8L, 4L, 5L, 6L,
8L, 1L, 7L, 5L, 8L, 1L, 7L, 10L, 8L, 1L, 9L, 8L, 6L, 6L,
10L, 7L, 3L, 6L, 5L, 10L, 2L, 1L, 9L, 5L, 5L, 10L, 2L, 6L,
10L, 4L, 8L, 7L, 9L, 8L), .Label = c("Switzerland", "Czech Republic",
"Denmark", "Iceland", "Netherlands", "Norway", "Portugal",
"Romania", "Sweden", "Finland"), class = "factor")), class = "data.frame", row.names = c(NA,
-100L))
This is how it looks like
'data.frame': 100 obs. of 3 variables:
$ gender : Factor w/ 2 levels "Female","Male": 1 2 1 2 2 1 1 1 2 1 ...
$ treatment_response: Factor w/ 2 levels "Non-responder",..: 2 2 1 2 1 1 2 2 2 1 ...
$ country : Factor w/ 10 levels "Switzerland",..: 1 3 9 7 2 2 6 6 4 9 ...
I wish to create a data.frame where the treatment_response is summarised by gender and country in percentages or proportions. For example, 60% (or 0.6) of males in Switzerland are responders and 40% are non-responder, similarly for females, etc.
I am familiar with the existence of dplyr and have managed to find a method to do this for mean but not for proportion or percentages.

Related

How to reshape conjoint data from wide to long?

users,
I have received a data from a conjoint survey experiment. What I want to do is to reshape from wide to long format. However, this seems to be slightly complicated. I am pretty sure it is possible to do with cj_tidy (package cregg) but can't solve it myself.
In the survey, the respondents were asked to compare two organizations that vary across 7 profiles (Efficiency Opennes Inclusion Leader Gain & System). In total, respondents were presented with four comparisons. So 2 organizations and 4 comparisons (4x2). They had to choose one of the presented organization and rate them separately after choosing one.
At the moment, the profile variables are structured in this way: org1_Efficiency_conj_1, org1_Opennes_conj1 ..etc. The first part "org" indicates whether it is the first or second organization. The last part "conj", indicated the order of the conjoint/comparison, where the "conj4" is the last comparison. The CHOICE variables also follow the order of conjoint – for example,"CHOICE_conj1", "CHOICE_conj2", where =1 means the respondent chose "org1". If =2, then org2 was chosen. The RATING> variable indicates a value from 0 to 10 for each organization: RATING_conj1_org1; RATING_conj1_org2 etc..
The current wide format of the data is not suitable for conjoint analysis - what I need is to create 8 observations for each respondent (4x2=8) where the variable CHOICE would indicate which of the organizations were chosen (where =1 if yes; and =0 if no). In a similar way, the variable RATING should indicate the rating given by respondents for both of the organizations (0 to 10).
This is how I would like the data to look like:
Note please that there are also covariates such as Q1 and Q2 in the picture, they are not a part of the experiment and should remain constant for each individual observation.
Below I share 50 observations from my real data.
> dput(cjdata_wide) structure(list(ID = 1:50, org1_Effeciency_conj_1 =
> c(3L, 2L, 1L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 2L, 1L, 1L, 1L, 1L, 1L, 3L,
> 2L, 3L, 3L, 3L, 2L, 3L, 1L, 2L, 1L, 3L, 3L, 1L, 1L, 3L, 1L, 1L, 3L,
> 3L, 2L, 3L, 2L, 3L, 2L, 1L, 1L, 3L, 2L, 1L, 1L, 1L, 2L, 2L, 1L ),
> org1_Oppenes_conj_1 = c(3L, 3L, 1L, 3L, 1L, 3L, 2L, 3L, 2L, 3L, 1L,
> 1L, 1L, 2L, 3L, 2L, 2L, 1L, 3L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 1L, 3L,
> 1L, 2L, 2L, 3L, 2L, 2L, 1L, 3L, 1L, 3L, 2L, 2L, 1L, 2L, 3L, 3L, 3L,
> 3L, 3L, 2L, 3L, 1L), org1_Inclusion_conj_1 = c(2L, 1L, 1L, 2L, 2L,
> 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L,
> 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
> 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L), org1_Leader_conj_1 =
> c(5L, 6L, 3L, 6L, 1L, 4L, 2L, 6L, 1L, 6L, 1L, 2L, 2L, 6L, 3L, 2L, 6L,
> 3L, 5L, 6L, 3L, 1L, 4L, 3L, 5L, 5L, 2L, 1L, 4L, 1L, 3L, 4L, 2L, 3L,
> 5L, 2L, 1L, 3L, 3L, 2L, 1L, 4L, 1L, 5L, 2L, 6L, 1L, 4L, 2L, 3L),
> org1_Gain_conj_1 = c(4L, 4L, 1L, 3L, 3L, 8L, 3L, 2L, 6L, 5L, 1L, 6L,
> 3L, 8L, 1L, 3L, 6L, 2L, 2L, 5L, 5L, 3L, 4L, 8L, 6L, 4L, 5L, 6L, 6L,
> 8L, 4L, 4L, 5L, 7L, 6L, 7L, 3L, 7L, 8L, 2L, 6L, 4L, 6L, 4L, 8L, 4L,
> 6L, 4L, 3L, 6L), org1_System_conj_1 = c(5L, 4L, 5L, 1L, 4L, 4L, 5L,
> 1L, 2L, 2L, 4L, 3L, 1L, 4L, 4L, 2L, 3L, 3L, 2L, 4L, 3L, 1L, 4L, 3L,
> 1L, 1L, 5L, 3L, 1L, 3L, 5L, 4L, 5L, 3L, 2L, 4L, 1L, 2L, 3L, 4L, 1L,
> 1L, 3L, 5L, 5L, 5L, 1L, 1L, 5L, 3L), org2_Effeciency_conj_1 = c(2L,
> 1L, 3L, 2L, 1L, 3L, 1L, 2L, 2L, 2L, 3L, 2L, 3L, 3L, 3L, 2L, 2L, 1L,
> 2L, 2L, 2L, 3L, 1L, 3L, 1L, 3L, 2L, 1L, 2L, 2L, 1L, 2L, 3L, 1L, 2L,
> 1L, 1L, 3L, 2L, 1L, 3L, 3L, 2L, 3L, 3L, 2L, 2L, 3L, 3L, 3L),
> org2_Oppenes_conj_1 = c(1L, 1L, 3L, 1L, 3L, 1L, 1L, 2L, 3L, 2L, 3L,
> 3L, 2L, 1L, 1L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 3L, 1L,
> 2L, 3L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 3L, 1L, 2L, 3L, 1L, 1L, 1L,
> 2L, 1L, 1L, 1L, 3L), org2_Inclusion_conj_1 = c(1L, 2L, 2L, 1L, 1L,
> 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
> 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L), org2_Leader_conj_1 =
> c(4L, 5L, 6L, 3L, 2L, 5L, 1L, 3L, 6L, 2L, 4L, 6L, 6L, 5L, 6L, 4L, 1L,
> 2L, 4L, 2L, 4L, 6L, 5L, 6L, 4L, 1L, 3L, 5L, 3L, 5L, 6L, 1L, 6L, 4L,
> 1L, 3L, 4L, 2L, 1L, 3L, 4L, 3L, 5L, 2L, 4L, 4L, 3L, 3L, 4L, 2L),
> org2_Gain_conj_1 = c(5L, 1L, 6L, 5L, 8L, 6L, 4L, 3L, 8L, 8L, 7L, 7L,
> 7L, 5L, 7L, 7L, 2L, 6L, 7L, 7L, 6L, 8L, 3L, 1L, 8L, 2L, 6L, 2L, 5L,
> 6L, 7L, 1L, 7L, 2L, 2L, 5L, 8L, 6L, 2L, 7L, 8L, 7L, 1L, 8L, 4L, 3L,
> 4L, 7L, 7L, 7L), org2_System_conj_1 = c(3L, 3L, 3L, 4L, 3L, 3L, 3L,
> 5L, 4L, 4L, 1L, 4L, 3L, 1L, 5L, 5L, 5L, 4L, 3L, 3L, 4L, 4L, 1L, 5L,
> 5L, 3L, 4L, 2L, 5L, 2L, 2L, 5L, 3L, 4L, 3L, 5L, 5L, 5L, 5L, 2L, 3L,
> 4L, 2L, 1L, 3L, 3L, 2L, 4L, 4L, 2L), org1_Effeciency_conj_2 = c(2L,
> 1L, 2L, 3L, 3L, 2L, 1L, 2L, 1L, 3L, 1L, 1L, 1L, 2L, 3L, 3L, 2L, 3L,
> 3L, 1L, 2L, 1L, 2L, 3L, 2L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 2L, 1L, 2L,
> 1L, 1L, 3L, 1L, 3L, 1L, 2L, 3L, 3L, 1L, 2L, 1L, 2L, 3L, 3L),
> org1_Oppenes_conj_2 = c(1L, 3L, 2L, 1L, 2L, 3L, 3L, 2L, 1L, 3L, 3L,
> 2L, 1L, 2L, 3L, 3L, 1L, 1L, 1L, 2L, 1L, 3L, 1L, 3L, 2L, 1L, 3L, 2L,
> 3L, 3L, 3L, 3L, 2L, 2L, 1L, 2L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 1L,
> 1L, 3L, 3L, 2L, 3L), org1_Inclusion_conj_2 = c(2L, 1L, 1L, 2L, 1L,
> 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L,
> 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L,
> 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L), org1_Leader_conj_2 =
> c(3L, 3L, 2L, 2L, 5L, 5L, 6L, 2L, 2L, 1L, 6L, 5L, 2L, 1L, 2L, 4L, 5L,
> 4L, 3L, 6L, 4L, 1L, 5L, 3L, 1L, 5L, 5L, 4L, 6L, 6L, 5L, 6L, 5L, 4L,
> 4L, 6L, 3L, 4L, 6L, 2L, 4L, 4L, 1L, 4L, 4L, 3L, 3L, 1L, 4L, 4L),
> org1_Gain_conj_2 = c(3L, 1L, 7L, 7L, 2L, 1L, 8L, 1L, 2L, 7L, 5L, 4L,
> 4L, 3L, 6L, 3L, 1L, 1L, 8L, 3L, 4L, 3L, 3L, 5L, 4L, 3L, 4L, 8L, 6L,
> 8L, 3L, 1L, 8L, 5L, 6L, 3L, 3L, 6L, 7L, 1L, 3L, 6L, 5L, 7L, 6L, 6L,
> 3L, 4L, 2L, 6L), org1_System_conj_2 = c(5L, 1L, 5L, 1L, 4L, 3L, 3L,
> 4L, 2L, 1L, 5L, 3L, 5L, 3L, 4L, 2L, 2L, 3L, 4L, 1L, 1L, 4L, 3L, 4L,
> 3L, 2L, 1L, 1L, 4L, 5L, 2L, 3L, 5L, 3L, 5L, 2L, 4L, 2L, 1L, 5L, 5L,
> 1L, 2L, 2L, 5L, 2L, 4L, 3L, 2L, 3L), org2_Effeciency_conj_2 = c(3L,
> 3L, 1L, 2L, 2L, 1L, 3L, 1L, 3L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 3L, 1L,
> 2L, 3L, 3L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 2L, 3L, 3L, 3L,
> 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L),
> org2_Oppenes_conj_2 = c(2L, 2L, 1L, 3L, 1L, 1L, 1L, 1L, 3L, 2L, 2L,
> 3L, 3L, 1L, 2L, 1L, 2L, 3L, 3L, 3L, 3L, 2L, 3L, 1L, 1L, 3L, 1L, 3L,
> 2L, 2L, 2L, 2L, 3L, 3L, 2L, 3L, 3L, 3L, 2L, 3L, 2L, 2L, 2L, 2L, 2L,
> 2L, 2L, 1L, 1L, 2L), org2_Inclusion_conj_2 = c(1L, 2L, 2L, 1L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L,
> 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
> 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L), org2_Leader_conj_2 =
> c(6L, 6L, 1L, 4L, 1L, 4L, 4L, 1L, 4L, 4L, 1L, 3L, 5L, 2L, 1L, 5L, 4L,
> 6L, 4L, 2L, 3L, 3L, 1L, 4L, 2L, 2L, 6L, 6L, 1L, 5L, 4L, 4L, 1L, 3L,
> 3L, 4L, 5L, 5L, 3L, 3L, 6L, 3L, 2L, 5L, 2L, 6L, 4L, 2L, 5L, 1L),
> org2_Gain_conj_2 = c(8L, 5L, 3L, 6L, 8L, 2L, 2L, 2L, 7L, 6L, 4L, 1L,
> 6L, 7L, 2L, 1L, 2L, 2L, 3L, 2L, 5L, 5L, 4L, 2L, 7L, 2L, 7L, 4L, 7L,
> 1L, 2L, 5L, 1L, 2L, 7L, 1L, 6L, 2L, 8L, 7L, 7L, 1L, 6L, 3L, 3L, 2L,
> 5L, 3L, 4L, 2L), org2_System_conj_2 = c(1L, 5L, 3L, 4L, 5L, 1L, 4L,
> 3L, 4L, 4L, 4L, 5L, 2L, 2L, 1L, 3L, 4L, 4L, 5L, 2L, 5L, 1L, 2L, 1L,
> 2L, 3L, 3L, 4L, 1L, 3L, 3L, 5L, 4L, 5L, 1L, 5L, 5L, 5L, 4L, 3L, 2L,
> 4L, 4L, 3L, 3L, 4L, 3L, 1L, 1L, 2L), org1_Effeciency_conj_3 = c(1L,
> 3L, 3L, 1L, 2L, 3L, 3L, 1L, 2L, 3L, 1L, 3L, 3L, 3L, 2L, 3L, 2L, 1L,
> 1L, 2L, 2L, 3L, 2L, 1L, 3L, 3L, 2L, 3L, 2L, 1L, 2L, 3L, 3L, 1L, 3L,
> 3L, 2L, 1L, 1L, 1L, 3L, 2L, 3L, 1L, 3L, 3L, 2L, 3L, 3L, 1L),
> org1_Oppenes_conj_3 = c(2L, 3L, 3L, 3L, 1L, 2L, 1L, 2L, 1L, 2L, 3L,
> 2L, 3L, 3L, 1L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 1L, 3L, 1L, 3L, 3L, 1L,
> 3L, 1L, 2L, 3L, 2L, 1L, 3L, 1L, 3L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 3L,
> 3L, 2L, 3L, 3L, 3L), org1_Inclusion_conj_3 = c(1L, 1L, 1L, 2L, 1L,
> 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L,
> 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L,
> 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L), org1_Leader_conj_3 =
> c(3L, 1L, 5L, 6L, 3L, 2L, 2L, 6L, 4L, 3L, 3L, 2L, 2L, 1L, 2L, 3L, 5L,
> 6L, 4L, 1L, 2L, 4L, 5L, 1L, 2L, 2L, 2L, 6L, 4L, 6L, 4L, 6L, 1L, 1L,
> 3L, 5L, 4L, 1L, 3L, 6L, 2L, 6L, 6L, 1L, 2L, 2L, 6L, 2L, 6L, 5L),
> org1_Gain_conj_3 = c(2L, 7L, 2L, 4L, 6L, 7L, 2L, 4L, 1L, 5L, 5L, 7L,
> 5L, 7L, 7L, 3L, 2L, 6L, 2L, 5L, 6L, 6L, 7L, 3L, 5L, 6L, 3L, 8L, 1L,
> 2L, 8L, 5L, 2L, 8L, 5L, 6L, 5L, 2L, 5L, 3L, 3L, 2L, 4L, 2L, 4L, 5L,
> 7L, 6L, 2L, 7L), org1_System_conj_3 = c(5L, 5L, 1L, 1L, 4L, 3L, 1L,
> 1L, 2L, 5L, 1L, 5L, 2L, 1L, 5L, 4L, 1L, 1L, 3L, 4L, 5L, 1L, 5L, 3L,
> 3L, 5L, 1L, 3L, 2L, 5L, 2L, 1L, 5L, 1L, 3L, 2L, 5L, 5L, 2L, 1L, 3L,
> 2L, 2L, 4L, 4L, 4L, 2L, 3L, 5L, 4L), org2_Effeciency_conj_3 = c(2L,
> 1L, 2L, 2L, 1L, 2L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 2L, 1L, 1L, 1L, 3L,
> 3L, 1L, 3L, 1L, 1L, 2L, 2L, 1L, 3L, 2L, 1L, 3L, 1L, 1L, 1L, 3L, 1L,
> 2L, 1L, 2L, 3L, 3L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L),
> org2_Oppenes_conj_3 = c(1L, 1L, 1L, 2L, 3L, 3L, 2L, 1L, 3L, 3L, 1L,
> 3L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 3L, 2L, 3L, 1L, 2L, 3L,
> 1L, 2L, 1L, 1L, 3L, 3L, 1L, 3L, 1L, 2L, 3L, 3L, 3L, 3L, 3L, 1L, 2L,
> 2L, 1L, 1L, 2L, 1L), org2_Inclusion_conj_3 = c(2L, 2L, 2L, 1L, 2L,
> 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
> 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L,
> 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L), org2_Leader_conj_3 =
> c(1L, 5L, 2L, 1L, 2L, 4L, 4L, 1L, 2L, 4L, 5L, 5L, 5L, 4L, 3L, 4L, 6L,
> 3L, 2L, 2L, 5L, 2L, 2L, 5L, 5L, 3L, 5L, 3L, 3L, 1L, 5L, 5L, 2L, 2L,
> 2L, 2L, 1L, 6L, 1L, 5L, 1L, 5L, 1L, 2L, 6L, 6L, 4L, 3L, 2L, 6L),
> org2_Gain_conj_3 = c(1L, 8L, 3L, 5L, 2L, 6L, 3L, 2L, 7L, 1L, 2L, 2L,
> 8L, 1L, 2L, 6L, 1L, 8L, 6L, 3L, 7L, 4L, 5L, 2L, 6L, 8L, 2L, 7L, 6L,
> 8L, 5L, 7L, 3L, 6L, 1L, 8L, 4L, 3L, 7L, 5L, 8L, 8L, 3L, 6L, 3L, 4L,
> 5L, 4L, 4L, 5L), org2_System_conj_3 = c(4L, 1L, 4L, 3L, 3L, 5L, 3L,
> 3L, 4L, 2L, 3L, 1L, 1L, 5L, 2L, 3L, 3L, 2L, 5L, 3L, 1L, 2L, 3L, 5L,
> 1L, 4L, 5L, 2L, 3L, 2L, 3L, 2L, 4L, 3L, 5L, 3L, 1L, 1L, 3L, 2L, 4L,
> 5L, 5L, 3L, 1L, 1L, 4L, 1L, 4L, 5L), org1_Effeciency_conj_4 = c(1L,
> 1L, 2L, 2L, 3L, 2L, 2L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 2L, 3L,
> 3L, 1L, 1L, 3L, 1L, 3L, 2L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 1L, 3L, 2L,
> 3L, 3L, 2L, 3L, 1L, 2L, 2L, 3L, 2L, 1L, 1L, 3L, 3L, 1L, 3L),
> org1_Oppenes_conj_4 = c(2L, 1L, 2L, 2L, 2L, 3L, 2L, 3L, 2L, 1L, 1L,
> 1L, 3L, 1L, 3L, 2L, 2L, 3L, 2L, 3L, 1L, 3L, 3L, 1L, 1L, 1L, 3L, 1L,
> 1L, 1L, 2L, 3L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 3L, 1L, 3L, 3L, 1L, 3L,
> 3L, 3L, 2L, 3L, 2L), org1_Inclusion_conj_4 = c(2L, 2L, 1L, 2L, 2L,
> 2L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
> 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L,
> 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L), org1_Leader_conj_4 =
> c(4L, 6L, 5L, 1L, 2L, 1L, 1L, 3L, 3L, 6L, 2L, 5L, 6L, 6L, 6L, 2L, 3L,
> 3L, 4L, 4L, 4L, 1L, 5L, 5L, 2L, 6L, 2L, 5L, 4L, 4L, 2L, 5L, 6L, 5L,
> 1L, 4L, 4L, 3L, 4L, 2L, 3L, 2L, 5L, 1L, 3L, 6L, 2L, 6L, 4L, 1L),
> org1_Gain_conj_4 = c(3L, 1L, 2L, 3L, 4L, 7L, 2L, 7L, 4L, 1L, 6L, 3L,
> 5L, 8L, 3L, 7L, 8L, 1L, 3L, 6L, 7L, 1L, 1L, 1L, 1L, 3L, 4L, 3L, 1L,
> 8L, 3L, 2L, 1L, 7L, 2L, 4L, 4L, 1L, 6L, 8L, 6L, 3L, 7L, 3L, 8L, 7L,
> 3L, 1L, 3L, 3L), org1_System_conj_4 = c(5L, 1L, 2L, 3L, 2L, 5L, 5L,
> 2L, 3L, 5L, 3L, 4L, 5L, 2L, 4L, 2L, 3L, 2L, 4L, 4L, 1L, 1L, 4L, 3L,
> 2L, 4L, 3L, 1L, 5L, 5L, 2L, 4L, 5L, 4L, 3L, 3L, 1L, 5L, 4L, 1L, 2L,
> 3L, 5L, 5L, 3L, 2L, 5L, 2L, 3L, 3L), org2_Effeciency_conj_4 = c(3L,
> 3L, 3L, 1L, 1L, 3L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 3L, 2L, 1L, 1L,
> 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 3L, 2L, 2L, 1L, 3L, 1L, 3L,
> 2L, 2L, 3L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 3L, 2L, 2L, 3L, 1L),
> org2_Oppenes_conj_4 = c(1L, 3L, 1L, 3L, 3L, 2L, 3L, 2L, 3L, 2L, 2L,
> 3L, 2L, 2L, 2L, 1L, 3L, 1L, 3L, 2L, 2L, 1L, 1L, 3L, 3L, 2L, 1L, 3L,
> 3L, 2L, 3L, 1L, 3L, 3L, 2L, 1L, 3L, 1L, 3L, 1L, 2L, 2L, 1L, 2L, 1L,
> 1L, 2L, 3L, 1L, 1L), org2_Inclusion_conj_4 = c(1L, 1L, 2L, 1L, 1L,
> 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
> 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L,
> 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L), org2_Leader_conj_4 =
> c(1L, 5L, 2L, 6L, 6L, 6L, 2L, 1L, 2L, 4L, 5L, 3L, 4L, 4L, 2L, 1L, 6L,
> 1L, 1L, 2L, 6L, 3L, 1L, 4L, 4L, 3L, 3L, 4L, 6L, 5L, 3L, 2L, 3L, 6L,
> 6L, 5L, 2L, 6L, 3L, 5L, 5L, 1L, 6L, 5L, 4L, 5L, 1L, 2L, 2L, 6L),
> org2_Gain_conj_4 = c(5L, 8L, 1L, 2L, 7L, 2L, 7L, 8L, 2L, 6L, 7L, 7L,
> 7L, 5L, 8L, 4L, 6L, 6L, 6L, 4L, 6L, 6L, 7L, 2L, 5L, 6L, 6L, 1L, 8L,
> 5L, 2L, 5L, 6L, 3L, 3L, 7L, 7L, 8L, 4L, 7L, 5L, 2L, 2L, 7L, 6L, 4L,
> 7L, 4L, 4L, 1L), org2_System_conj_4 = c(2L, 3L, 3L, 2L, 4L, 4L, 4L,
> 4L, 1L, 4L, 1L, 2L, 4L, 5L, 2L, 3L, 5L, 1L, 1L, 1L, 5L, 4L, 2L, 2L,
> 3L, 2L, 1L, 4L, 3L, 4L, 5L, 3L, 1L, 3L, 2L, 4L, 4L, 1L, 3L, 3L, 4L,
> 5L, 4L, 4L, 1L, 1L, 3L, 5L, 5L, 1L), CHOICE_conj1 = c(2L, 2L, 1L, 2L,
> 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
> 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L,
> 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L ), RATING_conj1_org1 =
> c(1L, 3L, 6L, 5L, 3L, 1L, 5L, 2L, 0L, 7L, 6L, 8L, 5L, 10L, 8L, 10L,
> 1L, 6L, 5L, 8L, 2L, 7L, 0L, 6L, 8L, 0L, 4L, 2L, 8L, 6L, 7L, 7L, 7L,
> 2L, 3L, 8L, 6L, 7L, 2L, 7L, 3L, 8L, 5L, 7L, 8L, 6L, 6L, 10L, 3L, 9L),
> RATING_conj1_org2 = c(7L, 6L, 4L, 7L, 7L, 1L, 6L, 6L, 0L, 3L, 2L, 0L,
> 0L, 9L, 5L, 3L, 1L, 6L, 8L, 5L, 2L, 2L, 0L, 4L, 5L, 0L, 6L, 8L, 3L,
> 5L, 6L, 6L, 5L, 8L, 3L, 8L, 3L, 1L, 5L, 9L, 7L, 3L, 7L, 6L, 6L, 4L,
> 4L, 0L, 6L, 7L), CHOICE_conj2 = c(1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
> 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
> 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L,
> 2L, 1L, 1L, 2L, 1L, 1L, 2L), RATING_conj2_org1 = c(5L, 4L, 4L, 4L,
> 5L, 1L, 5L, 7L, 0L, 3L, 5L, 6L, 5L, 9L, 5L, 3L, 1L, 4L, 4L, 8L, 3L,
> 7L, 0L, 9L, 9L, 1L, 3L, 2L, 3L, 5L, 6L, 4L, 5L, 8L, 3L, 7L, 6L, 1L,
> 7L, 0L, 7L, 6L, 6L, 8L, 9L, 7L, 5L, 10L, 7L, 7L), RATING_conj2_org2 =
> c(0L, 2L, 7L, 4L, 8L, 1L, 7L, 8L, 0L, 3L, 6L, 0L, 0L, 7L, 8L, 10L,
> 0L, 3L, 6L, 8L, 2L, 5L, 0L, 4L, 5L, 2L, 5L, 5L, 7L, 5L, 5L, 7L, 1L,
> 2L, 3L, 8L, 3L, 7L, 3L, 6L, 2L, 8L, 8L, 8L, 7L, 6L, 6L, 5L, 5L, 9L),
> CHOICE_conj3 = c(2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L,
> 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L,
> 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
> 2L, 1L, 1L), RATING_conj3_org1 = c(4L, 6L, 4L, 6L, 7L, 1L, 6L, 3L,
> 0L, 6L, 2L, 7L, 0L, 9L, 5L, 3L, 1L, 3L, 4L, 7L, 1L, 8L, 0L, 5L, 5L,
> 1L, 5L, 2L, 8L, 5L, 5L, 5L, 3L, 8L, 2L, 4L, 5L, 7L, 8L, 6L, 7L, 6L,
> 4L, 9L, 7L, 5L, 4L, 2L, 8L, 9L), RATING_conj3_org2 = c(7L, 4L, 6L,
> 5L, 6L, 1L, 3L, 7L, 0L, 3L, 2L, 3L, 3L, 6L, 5L, 10L, 0L, 3L, 4L, 10L,
> 0L, 4L, 0L, 7L, 5L, 2L, 3L, 2L, 3L, 5L, 8L, 2L, 7L, 2L, 7L, 5L, 3L,
> 3L, 0L, 0L, 2L, 6L, 7L, 8L, 5L, 2L, 8L, 10L, 6L, 8L), CHOICE_conj4 =
> c(2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L,
> 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L,
> 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L),
> RATING_conj4_org1 = c(4L, 5L, 8L, 6L, 4L, 1L, 8L, 3L, 0L, 7L, 5L, 5L,
> 2L, 8L, 7L, 10L, 1L, 5L, 5L, 10L, 1L, 3L, 0L, 6L, 7L, 1L, 2L, 5L, 7L,
> 8L, 7L, 3L, 6L, 2L, 2L, 8L, 5L, 5L, 4L, 5L, 3L, 7L, 3L, 8L, 8L, 6L,
> 2L, 10L, 7L, 7L), RATING_conj4_org2 = c(6L, 4L, 4L, 4L, 5L, 1L, 6L,
> 7L, 0L, 3L, 6L, 2L, 0L, 5L, 5L, 3L, 0L, 3L, 4L, 9L, 4L, 8L, 0L, 5L,
> 6L, 2L, 8L, 3L, 2L, 5L, 5L, 7L, 2L, 6L, 7L, 8L, 3L, 3L, 1L, 5L, 7L,
> 10L, 7L, 10L, 5L, 5L, 7L, 5L, 5L, 8L), Q7 = c(0L, 0L, 8L, 9L, 6L,
> 10L, 2L, 2L, 6L, 8L, 0L, 0L, 5L, 2L, 7L, 7L, 3L, 0L, 0L, 5L, 6L, 4L,
> 7L, 2L, 977L, 0L, 6L, 3L, 2L, 4L, 7L, 8L, 2L, 1L, 9L, 8L, 10L, 6L,
> 0L, 9L, 5L, 0L, 3L, 0L, 0L, 0L, 2L, 5L, 977L, 2L), Q8 = c(1L, 1L, 2L,
> 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 977L, 1L, 2L, 2L, 1L, 3L, 1L, 1L,
> 3L, 1L, 3L, 1L, 2L, 1L, 977L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L,
> 3L, 3L, 2L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 977L, 1L), Q9 = c(4L, 8L,
> 1L, 0L, 4L, 0L, 8L, 7L, 0L, 0L, 10L, 10L, 0L, 4L, 0L, 10L, 4L, 5L,
> 10L, 8L, 2L, 9L, 0L, 5L, 2L, 0L, 5L, 4L, 4L, 8L, 0L, 0L, 5L, 6L, 2L,
> 0L, 0L, 0L, 7L, 4L, 5L, 5L, 6L, 10L, 7L, 4L, 6L, 0L, 977L, 7L), Q10 =
> c(8L, 10L, 7L, 5L, 7L, 2L, 7L, 8L, 0L, 2L, 10L, 10L, 0L, 10L, 2L,
> 10L, 8L, 8L, 10L, 8L, 7L, 10L, 5L, 7L, 4L, 0L, 7L, 7L, 10L, 10L, 4L,
> 2L, 5L, 9L, 5L, 6L, 2L, 4L, 10L, 3L, 5L, 7L, 9L, 10L, 10L, 10L, 8L,
> 977L, 977L, 10L), Q11 = c(10L, 9L, 1L, 4L, 5L, 0L, 5L, 6L, 1L, 3L,
> 9L, 10L, 0L, 10L, 7L, 7L, 5L, 7L, 10L, 10L, 9L, 7L, 0L, 8L, 7L, 0L,
> 7L, 7L, 8L, 10L, 5L, 2L, 2L, 10L, 5L, 1L, 2L, 4L, 6L, 4L, 7L, 10L,
> 6L, 8L, 8L, 6L, 8L, 6L, 977L, 10L), Q12 = c(0L, 0L, 0L, 5L, 1L, 10L,
> 2L, 0L, 0L, 2L, 0L, 0L, 5L, 0L, 6L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
> 0L, 0L, 10L, 3L, 0L, 0L, 977L, 10L, 7L, 0L, 0L, 5L, 8L, 2L, 0L, 966L,
> 7L, 977L, 0L, 0L, 0L, 0L, 0L, 0L, 977L, 977L, 0L), Q13 = c(2L, 2L,
> 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 977L, 2L), Q14 =
> c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), Q1 =
> c(2L, 2L, 8L, 6L, 5L, 1L, 7L, 3L, 7L, 4L, 1L, 6L, 4L, 1L, 5L, 10L,
> 5L, 4L, 3L, 7L, 2L, 5L, 3L, 5L, 977L, 0L, 5L, 4L, 4L, 7L, 5L, 3L, 8L,
> 3L, 3L, 0L, 5L, 6L, 3L, 4L, 0L, 3L, 3L, 2L, 7L, 4L, 2L, 7L, 4L, 7L),
> Q2 = c(1L, 1L, 1L, 977L, 1L, 3L, 3L, 1L, 2L, 2L, 3L, 1L, 2L, 1L, 3L,
> 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 977L, 2L, 3L, 3L, 1L, 1L, 3L, 2L,
> 1L, 1L, 3L, 3L, 2L, 3L, 3L, 2L, 1L, 3L, 3L, 3L, 977L, 1L, 3L, 977L,
> 977L, 1L), gender = c(1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
> 1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L,
> 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
> 1L, 2L, 2L, 1L), profile_age = c(5L, 2L, 5L, 5L, 3L, 5L, 2L, 5L, 3L,
> 5L, 3L, 3L, 5L, 5L, 5L, 5L, 5L, 5L, 2L, 5L, 5L, 5L, 5L, 2L, 5L, 5L,
> 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 1L, 5L, 5L, 1L, 1L, 1L, 1L, 1L,
> 1L, 1L, 1L, 1L, 1L, 1L, 1L ), educ = c(6L, 5L, 2L, 5L, 6L, 6L, 4L, 6L,
> 3L, 5L, 4L, 5L, 6L, 4L, 4L, 6L, 6L, 6L, 3L, 6L, 5L, 6L, 5L, 5L, 3L,
> 4L, 6L, 6L, 5L, 3L, 3L, 4L, 3L, 6L, 3L, 5L, 5L, 6L, 3L, 5L, 3L, 3L,
> 3L, 3L, 4L, 5L, 5L, 4L, 2L, 3L)), class = "data.frame", row.names =
> c(NA,
> -50L))
What I have done so far is this:
library(cregg)
str(long <- cj_tidy(cjdata_wide,
profile_variables = c("All the profile variables"),
task_variables = c("CHOICE AND RATING VARIABLES HERE"),
id = ~ id))
stopifnot(nrow(long) == nrow(data)*4*2
But I'm keep getting errors. I have tried to follow the example given by the cregg package - but with no success. Any help is much appreciated! I am open to all possible ways, be it so through cregg package or tidyr for instance.

Your data not being in a standard form mades this a difficult problem. Here is a solution using the tidyr package.
The solutions involves 3 parts, dealing with the profiles, the rating and finally the rating choice.
The key to the profiles part was to pivot long and breaking up the profile names into component parts and then pivot wider for the column headings.
The rating and binary choice involved pivoting longer and then aligning the rows.
library(tidyr)
library(dplyr)
#Get the categories part correct
answer <-cjdata_wide %>% pivot_longer(cols=starts_with("org"), names_to=c("org", "Cat", "conj", "order"), values_to= "values", names_sep="_") %>% select(-c("conj"))
answer <-answer %>% select(!starts_with("RATING") & !starts_with("CHOICE"))
answer <-pivot_wider(answer, names_from = "Cat", values_from = "values")
#get the ratings column corretn
rating <-cjdata_wide %>% select(starts_with("RATING") )
rating <- rating%>% pivot_longer(cols=everything(), names_to=c("Rating", "conj", "order"), values_to= "Choice_Rating", names_sep="_") %>% select(-c("conj"))
answer$Choice_Rating <- rating$Choice_Rating
#Get the choice correct
choice <-cjdata_wide %>% select(starts_with("CHOICE") )
choiceRate <- choice%>% pivot_longer(cols=everything(), names_to=c("Choice", "conj"), values_to= "Choice_Rating", names_sep="_") %>% select(-c("conj"))
answer$Choice_binary <-ifelse(substr(answer$org, 4,4) == rep(choiceRate$Choice_Rating,each=2), 1, 0)
answer
It may be possible to simplify the above. Good luck.
Update per Comment
The final data frame has pairs of rows which corresponds to org 1 or 2. I duplicated the choice so that Choice_Rating column is the same length as the Organization ("org" column). I then compared Choice_Rating & Organization and setting the final value to either 0 or 1 depending on the match.
For question in the comment, A simple way is to convert the factor column to integers with as.integer() function, then the first factor becomes 1 and the second becomes 2 etc. (may need to relevel in order to get the proper order).
Another option is to create a new "org" column with your factor names properly listed.
Hopefully this provides enough guidance.

ordered logistic regression with a four way interaction in R

I have been trying to perform an ordered logistic regression with a four-way interaction and get the error message:
Error in Design(eval.parent(m)) : interaction term not second or
third order
The design is:
Dependent variable:
Developmental stage - 5 levels numbered 1-5
Independent variables:
Age - 4 different age points for which data was collected;
Ancestry - 2 categories numbered 1 & 2;
Rearing environment - 2 categories numbered 1 & 2;
Current environment - 2 categories numbered 1 & 2
As there is the potential for pseudo-replication the model is run clustered by "Colony".
As such, the code that I have been trying to use is:
library(rms)
Data$Ancestry <- factor(Data$Ancestry)
Data$Rearing <- factor(Data$Rearing)
Data$Queenless <- factor(Data$Queenless)
m <- lrm(Level ~ Age * Ancestry * Rearing * Queenless, x=T, y=T, dat = Data)
robcov(m, cluster = Data$Colony)
I'm assuming that the error message means that lrm doesn't support a 4-way interaction. Is there another way of doing this? I'm having no luck searching for alternate solutions online and I know I had problems trying to cluster using the polr function.
Many thanks for your help.
Here is my data:
structure(list(Bee.Age = c(8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L), Colony = structure(c(1L, 1L, 1L, 1L, 5L, 5L,
5L, 5L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 1L, 1L, 1L, 1L, 9L, 9L,
9L, 9L, 2L, 2L, 2L, 2L, 10L, 10L, 10L, 10L, 3L, 3L, 3L, 3L, 7L,
7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 3L, 3L, 3L, 3L, 7L,
7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 1L, 1L, 1L, 1L, 5L,
5L, 5L, 5L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 1L, 1L, 1L, 1L, 9L,
9L, 9L, 9L, 2L, 2L, 2L, 2L, 10L, 10L, 10L, 10L, 3L, 3L, 3L, 3L,
7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 3L, 3L, 3L, 3L,
7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 1L, 1L, 1L, 1L,
5L, 5L, 5L, 5L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 1L, 1L, 1L, 1L,
9L, 9L, 9L, 9L, 2L, 2L, 2L, 2L, 10L, 10L, 10L, 10L, 3L, 3L, 3L,
3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 3L, 3L, 3L,
3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 1L, 1L, 1L,
1L, 5L, 5L, 5L, 5L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 1L, 1L, 1L,
1L, 9L, 9L, 9L, 9L, 2L, 2L, 2L, 2L, 10L, 10L, 10L, 10L, 3L, 3L,
3L, 3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 3L, 3L,
3L, 3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 1L, 1L,
1L, 1L, 5L, 5L, 5L, 5L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 1L, 1L,
1L, 1L, 9L, 9L, 9L, 9L, 2L, 2L, 2L, 2L, 10L, 10L, 10L, 10L, 3L,
3L, 3L, 3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L, 3L,
3L, 3L, 3L, 7L, 7L, 7L, 7L, 4L, 4L, 4L, 4L, 8L, 8L, 8L, 8L), .Label = c("A1",
"A2", "A3", "A4", "E1", "E2", "E3", "E4", "I1", "I2"), class = "factor"),
Ancestry = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("1",
"2"), class = "factor"), Queenless = structure(c(1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L), .Label = c("1", "2"), class = "factor"), Rearing = structure(c(1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L), .Label = c("1", "2"), class = "factor"),
LevelOA = c(1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L,
1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L,
1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L,
3L, 1L, 1L, 3L, 1L, 1L, 3L, 1L, 3L, 1L, 2L, 3L, 1L, 2L, 2L,
3L, 1L, 3L, 1L, 3L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 3L, 1L,
2L, 1L, 2L, 1L, 1L, 3L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 3L,
1L, 3L, 3L, 1L, 2L, 2L, 2L, 1L, 3L, 1L, 3L, 2L, 1L, 2L, 3L,
3L, 2L, 3L, 1L, 4L, 1L, 4L, 3L, 4L, 3L, 3L, 4L, 3L, 1L, 3L,
3L, 3L, 2L, 2L, 3L, 2L, 3L, 3L, 4L, 2L, 4L, 4L, 2L, 2L, 2L,
2L, 3L, 3L, 4L, 4L, 1L, 5L, 1L, 4L, 3L, 1L, 3L, 2L, 4L, 1L,
4L, 1L, 3L, 3L, 4L, 3L, 3L, 4L, 4L, 2L, 3L, 3L, 3L, 1L, 3L,
2L, 1L, 3L, 3L, 4L, 2L, 4L, 4L, 4L, 3L, 3L, 4L, 4L, 5L, 3L,
4L, 5L, 1L, 2L, 5L, 3L, 4L, 5L, 5L, 4L, 3L, 1L, 4L, 3L, 4L,
2L, 5L, 5L, 4L, 3L, 5L, 4L, 1L, 5L, 5L, 5L, 5L, 4L, 5L, 5L,
5L, 5L, 2L, 5L, 4L, 4L, 5L, 3L, 5L, 4L, 4L, 5L, 4L, 5L, 2L,
4L, 5L, 4L, 5L, 4L, 5L, 4L, 5L), X = c(NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA
)), .Names = c("Bee.Age", "Colony", "Ancestry", "Queenless",
"Rearing", "LevelOA", "X"), row.names = c(NA, -320L), class = "data.frame")

This is only a partial answer.
If you need to fit an ordinal model with clustered data, you can use the ordinal package:
Process data:
library(ordinal)
Data <- transform(Data,
Ancestry=factor(Ancestry),
Rearing=factor(Rearing),
Queenless=factor(Queenless),
LevelOA=ordered(LevelOA))
The only special point here is that the response variable needs to be an ordered factor (ordered()).
There are two versions of clustered cumulative-link models in ordinal (you can read about their options in the package's help files):
c1 <- clmm(LevelOA ~ Bee.Age*Ancestry*Rearing*Queenless + (1|Colony),
dat = Data)
c2 <- clmm2(ordered(LevelOA) ~ Bee.Age*Ancestry*Rearing*Queenless,
random = Colony, data= Data, Hess=TRUE)
Both of these give estimates, but not standard deviations - I think the model is too complex and something is going wrong with the SD computation, but it would take more work (maybe a lot more) to figure it out. The estimated among-colony variance is also nearly/effectively zero with both models (std. dev approx. 2.7e-5), which implies that As a preliminary, you can use MASS::polr to fit the model without clustering:
c0 <- polr(LevelOA ~ Bee.Age * Ancestry * Rearing * Queenless,
dat = Data)
because the estimated among-colony variance is zero, this gives the same coefficient estimates as the ordinal functions.

How to add significance letters (anova) to ggplot geom_bar with facet wrap

When I make a barplot with significance letters from anova above the bars, I use following code:
anova_NDW_geel<-aov(nodule_dry_weight~treatment,inoculatieproef_geel_variety2)
HSD_NDW_geel <- HSD.test(anova_NDW_geel,"treatment",alpha=0.05,group=TRUE)$groups
HSD_NDW_means_geel <- HSD.test(anova_NDW_geel,"treatment",alpha=0.05,group=TRUE)$means
HSD_NDW_means_geel <- HSD_NDW_means_geel[order(-HSD_NDW_means_geel$nodule_dry_weight),]
p_HSD_NDW_geel <- ggplot(aes(x=treatment, y=NDW_mean_geel, width=0.6), data=inoculatieproef_mean_geel)+
geom_bar(stat="identity", data=HSD_NDW_geel, aes(x=trt, y=means), fill="gray40")+
geom_text(data=HSD_NDW_geel, aes(x=trt, y=means, label=M), size=5, vjust=-1, hjust=1)+
ggtitle("Zand")+
ylab("Droog gewicht wortelknolletjes (g)")+
xlab("Behandeling")+
geom_errorbar(aes(ymin=NDW_mean_geel-NDW_sd_geel,ymax=NDW_mean_geel+NDW_sd_geel),
position=position_dodge(width=0.5),width=0.1,size=0.3)+
theme_bw() +
theme(axis.line = element_line(colour="black"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank())+
scale_y_continuous(expand = c(0, 0))+
theme(axis.text.x = element_text(angle = 0, hjust = 1, vjust = 0.5))+
theme(text = element_text(size=12))
which results in following graph: http://i.stack.imgur.com/bZidZ.png
This is probably not the best way to do this and when I want to add the letters to the barplots with facet wrap.
Here is a sample of the data I want to make a facet wrap with significance letters with:
structure(list(treatment = structure(c(1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L), .Label = c("1", "2",
"3", "4", "5", "6", "7", "8"), class = "factor"), block = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("I",
"II", "III", "IV"), class = "factor"), position = structure(c(2L,
1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L,
2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("b",
"gem(ab)"), class = "factor"), variety = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("1",
"2"), class = "factor"), location = structure(c(2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Geel",
"Merelbeke"), class = "factor"), year = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("2014",
"2015"), class = "factor"), nodule_dry_weight = c(0, 0.0467,
0.0328, 0.0885, 0.0081, 0.1086, 0.0788, 0.0267, 0, 0.0128, 0.0143,
0.0333, 0.006, 0.098, 0.0286, 0.011, 0, 0.0627, 0.0769, 0.0784,
0.023, 0.1504, 0.1026, 0.0254, 0, 0.0597, 0.0158, 0.0354, 0.0226,
0.3261, 0.0436, 0, 0, 0.0203, 0.0469, 0.0904, 0.1593, 0.0836,
0.056, 0.0037, 0, 0.0534, 0.0901, 0.0435, 0.0248, 0.0435, 0.0279,
0.0029, 0, 0.0545, 0.038, 0.0991, 0.0099, 0.1453, 0.1096, 0.0272,
0, 0.0319, 0.0624, 0.0508, 0.0415, 0.11, 0.0079, 0, 0, 0.1257,
0.1242, 0.2899, 0.024, 0.2175, 0.2979, 0.0396, 0, 0.1583, 0.2935,
0.2541, 0.1027, 0.4196, 0.2059, 0.0396, 0, 0.0891, 0.167, 0.0907,
0.2153, 0.3063, 0.2921, 0.0528, 0, 0.0928, 0.2109, 0.1514, 0.0821,
0.3607, 0.0996, 0.0069, 0, 0.0685, 0.3109, 0.1862, 0.0393, 0.286,
0.3418, 0.0459, 0, 0.0765, 0.3486, 0.3988, 0.1155, 0.6341, 0.3653,
0.039, 0, 0.0766, 0.3112, 0.1988, 0.05, 0.2856, 0.34, 0.0862,
0, 0.2621, 0.1146, 0.393, 0.1644, 0.3415, 0.1343, 0.019, 0, 0.0976,
0.1853, 0.0691, 0.0248, 0.1764, 0.1244, 0.1525, 0, 0.1529, 0.1069,
0.2833, 0.0204, 0.2966, 0.2371, 0.1464, 0, 0.0691, 0.2094, 0.1633,
0.0264, 0.1344, 0.0694, 0.1175, 0, 0.1783, 0.1434, 0.2136, 0.0873,
0.19, 0.1683, 0.1927, 0, 0.0571, 0.0599, 0.1061, 0.0244, 0.1256,
0.0894, 0.0123, 0, 0.1696, 0.1046, 0.2164, 0.0939, 0.1552, 0.2942,
0.1652, 0, 0.0844, 0.102, 0.0227, 0.025, 0.0654, 0.1234, 0.0702,
0, 0.0979, 0.1246, 0.0958, 0.0867, 0.1104, 0.1969, 0.227, 0,
0.3704, 0.4727, 0.2527, 0.2078, 0.3377, 0.308, 0.1293, 0, 0.2417,
0.3744, 0.2916, 0.1773, 0.433, 0.2446, 0.1382, 0, 0.4718, 0.4271,
0.4882, 0.1799, 0.4178, 0.518, 0.3915, 0, 0.3421, 0.3804, 0.2112,
0.4292, 0.3829, 0.1315, 0.2719, 0, 0.3197, 0.6867, 0.414, 0.3112,
0.2914, 0.4994, 0.369, 0.0256, 0.1494, 0.5577, 0.2538, 0.3854,
0.4151, 0.544, 0.4009, 0, 0.5208, 0.2962, 0.4175, 0.2689, 0.3374,
0.5075, 0.3601, 0, 0.704, 0.4631, 0.4573, 0.154, 0.5087, 0.4319,
0.4155)), .Names = c("treatment", "block", "position", "variety",
"location", "year", "nodule_dry_weight"), row.names = c(NA, -256L
), class = "data.frame")
I use following code for my graph with facet wrap:
inoculatieproef <- inoculatieproef %>%
group_by(treatment, location, variety, year) %>%
mutate(NDW_mean = mean(nodule_dry_weight),
NDW_sd = sd(nodule_dry_weight))
ggplot(data=inoculatieproef,aes(x=treatment, y=NDW_mean))+
facet_wrap(~location*variety*year,ncol=2)+
geom_bar(position="dodge", stat="identity")+
geom_errorbar(aes(ymin = NDW_mean - NDW_sd,
ymax = NDW_mean + NDW_sd),
width=0.1,size=0.3,
color = "darkgrey")+
theme_bw() +
theme(axis.line = element_line(colour="black"),
panel.grid.minor = element_blank(),
panel.background = element_blank())
How do I add on each barplot the significance letters (anova) in de the facet wrap graph?

No idea if the test fits your data distribution, but you can start with that:
library(tidyverse)
stat_pvalue <- dd %>%
group_by(location, variety, year) %>%
rstatix::t_test(nodule_dry_weight~treatment) %>%
filter(p < 0.05) %>%
group_by(location, variety, year) %>%
rstatix::add_significance("p") %>%
rstatix::add_y_position() %>%
mutate(y.position = seq(min(y.position), max(y.position),length.out = n())*1.1) %>%
ungroup()
ggplot(data=dd,aes(x=treatment, y=nodule_dry_weight))+
geom_boxplot() +
facet_wrap(~location + variety + year,ncol=2, scales = "free_y") +
ggpubr::stat_pvalue_manual(stat_pvalue, label = "p")

drawing line segments connecting sets of points

I am trying to connect sets of (two) points at each level of x, in each facet. Here is a reproducible example:
datum <- structure(list(frequency = c(8L, 7L, 6L, 18L, 5L, 11L, 16L, 15L,
9L, 8L, 8L, 10L, 2L, 20L, 14L, 3L, 6L, 2L, 2L, 11L, 10L, 6L,
15L, 19L, 18L, 18L, 8L, 2L, 10L, 15L, 12L, 17L, 1L, 18L, 7L,
8L, 16L, 4L, 9L, 2L, 7L, 3L, 16L, 7L, 18L, 20L, 9L, 10L, 13L,
2L, 15L, 7L, 3L, 20L, 4L, 15L, 5L, 7L, 9L, 16L, 5L, 8L, 10L,
10L, 7L, 10L, 10L, 17L, 7L, 8L, 13L, 13L, 16L, 5L, 20L, 18L,
13L, 19L, 3L, 8L, 14L, 12L, 20L, 2L, 9L, 13L, 7L, 2L, 5L, 5L,
13L, 9L, 13L, 7L, 9L, 4L, 4L, 20L, 1L, 4L), band = structure(c(2L,
4L, 2L, 3L, 2L, 1L, 4L, 1L, 2L, 1L, 3L, 4L, 2L, 4L, 3L, 4L, 3L,
2L, 3L, 2L, 2L, 4L, 2L, 1L, 1L, 2L, 1L, 4L, 4L, 1L, 4L, 4L, 2L,
1L, 4L, 4L, 3L, 4L, 1L, 1L, 3L, 4L, 1L, 3L, 4L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 3L, 4L, 2L, 1L, 2L, 4L, 2L, 2L, 4L, 4L, 2L, 4L, 4L,
1L, 1L, 4L, 2L, 3L, 4L, 1L, 2L, 4L, 1L, 2L, 4L, 1L, 1L, 3L, 4L,
4L, 2L, 2L, 2L, 1L, 3L, 2L, 2L, 2L, 3L, 3L, 1L, 3L, 4L, 3L, 3L,
1L, 3L, 4L), .Label = c("1", "2", "3", "4"), class = "factor"),
test = structure(c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L
), .Label = c("1", "2"), class = "factor"), knowledge = structure(c(2L,
3L, 1L, 3L, 1L, 1L, 3L, 3L, 1L, 3L, 1L, 3L, 2L, 2L, 1L, 1L,
1L, 1L, 3L, 3L, 1L, 2L, 3L, 1L, 1L, 2L, 2L, 1L, 1L, 3L, 2L,
3L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 3L, 3L, 1L, 1L, 2L, 3L,
3L, 2L, 2L, 3L, 1L, 1L, 2L, 2L, 2L, 3L, 1L, 3L, 1L, 1L, 2L,
1L, 1L, 2L, 3L, 1L, 1L, 1L, 1L, 3L, 2L, 2L, 1L, 2L, 3L, 2L,
1L, 2L, 3L, 3L, 2L, 1L, 3L, 1L, 3L, 2L, 1L, 3L, 2L, 2L, 3L,
1L, 1L, 2L, 1L, 2L, 3L, 1L, 3L, 1L), .Label = c("1", "2",
"3"), class = "factor")), .Names = c("frequency", "band",
"test", "knowledge"), row.names = c(NA, -100L), class = "data.frame")
Here is the code I have so far:
ggplot(datum, aes(knowledge, frequency, color=test)) +
stat_summary(fun.y='mean', geom='point', position=position_dodge(width=.9), size=3) +
facet_grid(~band) +
labs(y='number of words (max = 20)', x='self-report knowledge') +
scale_x_discrete(labels=c('none', 'form', 'meaning'))
Looking at the left-most facet ('1') in the graph, I would like a line to connect the pretest to posttest in the none column, another line connecting pretest to posttest in the form column, and a line connecting the pretest to the posttest in the meaning column. I would like this done in each facet.
I hope that makes sense, and thanks!

I find relying on ggplot too much for data manipulation/summarizing can hurt more than it helps. I have no idea how to connect the position-dodged points with a line. Instead, I'd do something like this:
library(dplyr)
datsum = datum %>%
group_by(band, knowledge, test) %>%
summarize(mean = mean(frequency)) %>%
ungroup %>%
mutate(knowledge_fac = factor(knowledge, labels = c('none', 'form', 'meaning')))
ggplot(datsum, aes(x = test, y = mean)) +
geom_path(aes(group = band:knowledge)) +
geom_point(aes(color = factor(test))) +
facet_grid(band ~ knowledge_fac) +
labs(y='number of words (max = 20)', x='self-report knowledge')

Borrowing from Gregor's work in munging the data, I think this does what was requested. The mutate() chunk creates Test to be a numeric offset of -0.1 for test 1 and 0.1 for test 2. This is then added to the numeric value of knowledge. The result is the numeric x passed to ggplot2. Gregor correctly defined the groups, so the rest is straightforward.
library(dplyr)
datsum <- datum %>%
group_by(band, knowledge, test) %>%
summarize(mean = mean(frequency)) %>%
mutate(Test = 0.1 * (2 * (test == 2) - 1),
Knowledge = as.numeric(knowledge) + Test) %>%
ungroup
ggplot(datsum, aes(x = Knowledge, y = mean, color = test)) +
geom_path(aes(group = band:knowledge), color = "black") +
geom_point(size = 3) +
facet_wrap(~ band, nrow = 1) +
labs(y='number of words (max = 20)', x='self-report knowledge') +
scale_color_manual(values = c("orange", "blue")) +
scale_x_continuous(limits = c(0.5, 3.5), breaks = 1:3,
labels = c("none", "form", "meaning"))

Bar chart for factorial designs in R

I'm currently trying to create a clustered bar chart using ggplot2. It's basically just mean response times for a 2x2x2 factorial design. The three factors are load, compatibility and salience. I'm having a hard time jamming the third factor (salience) in there though. It shouldn't be a stacked graph though
This is what I currently have
bar+stat_summary(fun.y = mean, geom = "bar", position = "dodge") +
+ stat_summary(fun.data = mean_cl_normal, geom = "errorbar", position = position_dodge(width = 0.90), width = 0.2)+
+ labs(x = "Compatibility", y = "Mean RT", fill = "Load")
Here's a small sample of the data I'm trying to graph:
ID load comp sal rt
1 1 High Incompatible Non_Salient 787
2 1 Low Compatible Salient 754
3 2 High Incompatible Salient 654
I've seen graphs like these numerous times before but I have no idea how to get ggplot2 to display three independent variables at the same time.
I've tried splitting the graphs by adding
+ facet_wrap( ~ sal)
but that doesn't work either. It just says "Invalid argument to unary operator"
Any help would be appreciated.

Is this the kind of plot you are looking for?
I used the Wii data from the book "Discovering Statistics Using R", which is in a similar format to yours.
structure(list(athlete = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("Athlete", "Non-Athlete"), class = "factor"),
stretch = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No Stretching", "Stretching"
), class = "factor"), wii = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Playing Wii",
"Watching Wii"), class = "factor"), injury = c(2L, 2L, 1L,
2L, 0L, 1L, 2L, 0L, 2L, 2L, 2L, 1L, 4L, 2L, 2L, 0L, 0L, 3L,
3L, 3L, 2L, 1L, 0L, 2L, 2L, 3L, 2L, 2L, 3L, 1L, 2L, 4L, 1L,
2L, 2L, 2L, 1L, 4L, 4L, 1L, 2L, 3L, 3L, 3L, 3L, 2L, 3L, 2L,
2L, 2L, 1L, 0L, 3L, 3L, 2L, 1L, 2L, 4L, 1L, 2L, 5L, 5L, 3L,
6L, 4L, 3L, 4L, 5L, 5L, 2L, 6L, 4L, 4L, 4L, 3L, 4L, 3L, 2L,
1L, 4L, 3L, 2L, 2L, 1L, 3L, 1L, 1L, 3L, 4L, 2L, 7L, 8L, 6L,
9L, 4L, 7L, 5L, 9L, 6L, 4L, 8L, 5L, 4L, 7L, 10L, 1L, 3L,
2L, 1L, 3L, 3L, 2L, 3L, 4L, 2L, 0L, 1L, 3L, 2L, 0L)),
.Names = c("athlete", "stretch", "wii", "injury"),
class = "data.frame", row.names = c(NA, -120L))
Here is how to produce the plot.
library(ggplot2)
library(Hmisc)
ggplot(data=Wii, aes(x=stretch, y=injury, fill=wii)) +
facet_wrap(~athlete) +
stat_summary(fun.y = mean, geom = "bar", position = "dodge") +
stat_summary(fun.data = mean_cl_normal, geom = "errorbar", position = position_dodge(width = 0.90), width = 0.2)

Resources