ggstattsplot : Why ggwithinstats not working with categorical data - r

I'm trying to run the ggwithinstats function from ggstatplot but I get the following error.
This is I'm running
ggwithinstats( # independent samples
data = dat,
x = FAB,
y = BM_percentage,
plot.type = "box", # for boxplot
type = "nonparametric", # for wilcoxon
centrality.plotting = FALSE # remove median
)
########################
ggwithinstats(
df2,
x = FAB,
y = BM_percentage
)
I get the error for the first code
Error in validObject(.Object) : invalid class “dsparseModelMatrix”
object: superclass "Mnumeric" not defined in the environment of the
object's class Error in validObject(.Object) : invalid class
“dsparseModelMatrix” object: superclass "Mnumeric" not defined in the
environment of the object's class Error in complete.cases(x, y) : not
all arguments have the same length
And for the second code I get this
Error in p.adjust(pp[lower.tri(pp, TRUE)], p.adjust.method) :
(list) object cannot be coerced to type 'double'
My data which I'm trying to run
b <- dput(dat)
structure(list(FAB = structure(c(5L, 1L, 5L, 3L, 2L, 4L, 6L,
2L, 1L, 6L, 5L, 1L, 5L, 1L, 5L, 6L, 3L, 5L, 2L, 5L, 3L, 3L, 3L,
1L, 3L, 1L, 1L, 1L, 6L, 4L, 2L, 5L, 4L, 3L, 2L, 3L, 2L, 3L, 3L,
1L, 5L, 2L, 2L, 3L, 2L, 5L, 4L, 6L, 5L, 3L, 1L, 3L, 5L, 5L, 3L,
5L, 2L, 2L, 1L, 5L, 2L, 2L, 3L, 2L, 5L, 4L, 4L, 6L, 3L, 3L, 5L,
2L, 2L, 2L, 3L, 5L, 2L, 3L, 6L, 1L, 2L, 3L, 2L, 3L, 3L, 6L, 2L,
2L, 5L, 3L, 3L, 3L, 2L, 5L, 2L, 4L, 1L, 6L, 6L, 3L, 3L, 5L, 6L,
2L, 1L, 5L, 2L, 4L, 5L, 2L, 6L, 6L, 3L, 4L, 5L, 3L, 2L, 4L, 6L,
2L, 5L, 4L, 2L, 4L, 5L, 3L, 3L, 3L, 3L, 5L, 2L, 2L, 3L, 1L, 3L,
3L, 2L, 2L, 6L, 4L, 2L, 4L, 4L, 3L, 2L, 5L, 5L), .Label = c("M0",
"M1", "M2", "M3", "M4", "M5"), class = "factor"), WBC = c(76.7,
5, 5, 27.7, 10.7, 2.1, 78.5, 8.2, 47.2, 72.1, 67.5, 2.9, 22.2,
1, 15.2, 7.3, 12.6, 27.6, 46.4, 27.1, 34.2, 33.5, 2.5, 2.3, 8.3,
61.6, 47.6, 5.6, 137.2, 3.4, 48, 13.6, 0.9, 5.5, 1.5, 4.1, 90.4,
34.8, 3.1, 2.3, 37, 34, 2.7, 17, 29.4, 50.3, 0.5, 4, 12.4, 12,
111, 77.3, 2.9, 37.9, 8.3, 57.1, 11.5, 37.5, 6.1, 90.6, 80.5,
10.1, 1.5, 30.8, 2.3, 0.4, 86.4, 34.6, 15.1, 35.9, 17.9, 0.7,
33.2, 45.6, 98.8, 26.1, 134.4, 98.2, 8.4, 2.1, 67.9, 51.8, 5.1,
2.6, 43.1, 6.7, 30.5, 171.9, 29.7, 75.2, 45, 11.5, 22.9, 131.5,
63.7, 1.6, 5.4, 116.2, 14.9, 202.7, 18.7, 52.9, 99.2, 13.5, 14.5,
2.7, 1.2, 8.2, 30.9, 103.6, 93, 5.1, 3.4, 0.9, 4.9, 42.1, 6.4,
1.5, 59.3, 88.1, 25.9, 31.5, 223.8, 29, 9.9, 1.7, 0.6, 14.3,
61.6, 2.2, 1.2, 16, 11, 92, 29.4, 32.4, 42.8, 2.9, 6.7, 1.2,
13.1, 1, 3.6, 4.3, 39.8, 19.6, 101.3), TMB = c(0, 0.733333333333,
0.3, 0.266666666667, 0.466666666667, 0.333333333333, 0.233333333333,
0.2, 0.5, 0.133333333333, 0.333333333333, 0.566666666667, 0.3,
0.766666666667, 0.166666666667, 0.233333333333, 0.4, 0.266666666667,
0.533333333333, 1.13333333333, 0.233333333333, 0.1, 0.4, 0.4,
0.333333333333, 0.4, 0.5, 0.4, 0.1, 0.2, 0.566666666667, 0.466666666667,
0.2, 0.733333333333, 0.5, 0.333333333333, 0.2, 0.333333333333,
0.4, 0.266666666667, 0.0666666666667, 0.266666666667, 0.2, 0.433333333333,
0.566666666667, 0.0666666666667, 0.166666666667, 0.533333333333,
0.3, 0.433333333333, 0, 0.4, 0.466666666667, 0.0666666666667,
0.333333333333, 0, 0.7, 0.4, 0.233333333333, 0.3, 0.0333333333333,
0.4, 0.566666666667, 0.0333333333333, 0.0333333333333, 0.266666666667,
0.0333333333333, 0.4, 0.466666666667, 0.166666666667, 0.633333333333,
0.366666666667, 0.233333333333, 0.466666666667, 0.1, 0.0666666666667,
0.4, 0.366666666667, 0.1, 0.166666666667, 0.266666666667, 0.466666666667,
0.266666666667, 0.333333333333, 0.0333333333333, 0.1, 0.5, 0.333333333333,
0.333333333333, 0.266666666667, 0, 0.466666666667, 0.233333333333,
0.166666666667, 0.266666666667, 0.333333333333, 0.433333333333,
0.1, 0.0666666666667, 0.4, 0.2, 0.133333333333, 0.533333333333,
0.2, 0.4, 0.433333333333, 0.1, 0.2, 0.0666666666667, 0.233333333333,
0.1, 0, 0.3, 0.266666666667, 0.233333333333, 0.6, 0.533333333333,
0.2, 0.2, 0.5, 0.0333333333333, 0.0333333333333, 0.0666666666667,
0.166666666667, 0.5, 0.5, 0.166666666667, 0.3, 0.4, 0.3, 0.4,
0.466666666667, 0.433333333333, 0.4, 0.266666666667, 0.3, 0.4,
0.6, 0.0333333333333, 0.0666666666667, 0.333333333333, 0.3, 0.1,
0.333333333333, 0.333333333333, 0.2, 0.0333333333333), BM_percentage = c(82L,
83L, 91L, 72L, 68L, 88L, 32L, 91L, 59L, 87L, 89L, 99L, 35L, 90L,
75L, 41L, 63L, 69L, 81L, 51L, 53L, 34L, 63L, 75L, 47L, 95L, 42L,
55L, 83L, 90L, 84L, 61L, 100L, 64L, 62L, 67L, 77L, 39L, 43L,
75L, 69L, 73L, 72L, 80L, 90L, 39L, 74L, 78L, 51L, 37L, 92L, 57L,
85L, 40L, 48L, 81L, 86L, 88L, 60L, 98L, 77L, 42L, 46L, 89L, 95L,
90L, 73L, 71L, 32L, 70L, 62L, 32L, 75L, 76L, 56L, 30L, 92L, 76L,
89L, 50L, 79L, 55L, 94L, 80L, 47L, 81L, 90L, 87L, 75L, 46L, 67L,
70L, 86L, 72L, 85L, 40L, 97L, 83L, 57L, 60L, 52L, 90L, 52L, 86L,
74L, 37L, 71L, 91L, 52L, 85L, 90L, 95L, 70L, 82L, 40L, 64L, 40L,
90L, 85L, 86L, 71L, 51L, 77L, 85L, 40L, 37L, 35L, 57L, 48L, 81L,
60L, 62L, 72L, 67L, 56L, 59L, 81L, 33L, 94L, 85L, 72L, 42L, 93L,
40L, 86L, 71L, 79L), Risk_Cyto = structure(c(2L, 4L, 2L, 2L,
4L, 1L, 2L, 2L, 4L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 4L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L,
4L, 4L, 2L, 4L, 1L, 1L, 4L, 4L, 1L, 4L, 1L, 4L, 2L, 4L, 4L, 4L,
2L, 1L, 1L, 1L, 2L, 4L, 2L, 2L, 2L, 2L, 4L, 2L, 2L, 1L, 1L, 4L,
4L, 2L, 2L, 4L, 1L, 2L, 2L, 2L, 3L, 2L, 2L, 2L, 2L, 1L, 2L, 2L,
3L, 4L, 2L, 4L, 2L, 2L, 2L, 4L, 2L, 2L, 2L, 1L, 4L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 4L, 2L, 2L, 1L, 1L, 2L, 2L, 4L, 2L, 1L, 1L, 2L,
2L, 1L, 2L, 2L, 4L, 1L, 2L, 1L, 4L, 4L, 2L, 1L, 3L, 4L, 2L, 4L,
1L, 2L, 4L, 2L, 1L, 2L, 4L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("Good",
"Intermediate", "N.D.", "Poor"), class = "factor"), Risk_Molecular = structure(c(4L,
4L, 2L, 4L, 4L, 1L, 2L, 2L, 4L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L,
2L, 4L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 2L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 4L, 4L, 2L, 4L, 1L, 1L, 4L, 4L, 1L, 4L, 1L, 4L, 2L,
4L, 4L, 4L, 2L, 1L, 1L, 1L, 2L, 4L, 2L, 2L, 4L, 2L, 4L, 2L, 4L,
1L, 1L, 4L, 4L, 2L, 2L, 4L, 1L, 2L, 2L, 2L, 3L, 2L, 2L, 2L, 2L,
1L, 2L, 2L, 3L, 2L, 2L, 4L, 2L, 2L, 2L, 4L, 2L, 2L, 2L, 1L, 4L,
2L, 2L, 2L, 2L, 4L, 2L, 2L, 4L, 2L, 2L, 1L, 1L, 2L, 2L, 4L, 2L,
1L, 1L, 2L, 2L, 1L, 2L, 2L, 4L, 1L, 2L, 1L, 4L, 4L, 2L, 1L, 3L,
4L, 2L, 4L, 1L, 2L, 4L, 2L, 1L, 2L, 4L, 1L, 2L, 1L, 1L, 1L, 2L,
2L, 2L), .Label = c("Good", "Intermediate", "N.D.", "Poor"), class = "factor")), class = "data.frame", row.names = c("TCGA-AB-2856",
"TCGA-AB-2849", "TCGA-AB-2971", "TCGA-AB-2930", "TCGA-AB-2891",
"TCGA-AB-2872", "TCGA-AB-2851", "TCGA-AB-3011", "TCGA-AB-2949",
"TCGA-AB-2981", "TCGA-AB-2965", "TCGA-AB-2822", "TCGA-AB-2828",
"TCGA-AB-2959", "TCGA-AB-2973", "TCGA-AB-2987", "TCGA-AB-2986",
"TCGA-AB-2921", "TCGA-AB-2863", "TCGA-AB-3009", "TCGA-AB-2812",
"TCGA-AB-2940", "TCGA-AB-2996", "TCGA-AB-2983", "TCGA-AB-2859",
"TCGA-AB-2913", "TCGA-AB-2917", "TCGA-AB-2929", "TCGA-AB-2825",
"TCGA-AB-2897", "TCGA-AB-2900", "TCGA-AB-2846", "TCGA-AB-2862",
"TCGA-AB-3002", "TCGA-AB-2871", "TCGA-AB-2819", "TCGA-AB-2901",
"TCGA-AB-2920", "TCGA-AB-2966", "TCGA-AB-2814", "TCGA-AB-2942",
"TCGA-AB-2870", "TCGA-AB-2847", "TCGA-AB-2844", "TCGA-AB-2806",
"TCGA-AB-2911", "TCGA-AB-2980", "TCGA-AB-2861", "TCGA-AB-2916",
"TCGA-AB-2878", "TCGA-AB-2944", "TCGA-AB-2817", "TCGA-AB-2830",
"TCGA-AB-2892", "TCGA-AB-2858", "TCGA-AB-2815", "TCGA-AB-2877",
"TCGA-AB-2939", "TCGA-AB-2890", "TCGA-AB-2811", "TCGA-AB-2918",
"TCGA-AB-2898", "TCGA-AB-2908", "TCGA-AB-2866", "TCGA-AB-2842",
"TCGA-AB-2991", "TCGA-AB-2823", "TCGA-AB-2910", "TCGA-AB-2915",
"TCGA-AB-2977", "TCGA-AB-2912", "TCGA-AB-2943", "TCGA-AB-2881",
"TCGA-AB-2988", "TCGA-AB-3000", "TCGA-AB-2948", "TCGA-AB-2895",
"TCGA-AB-2931", "TCGA-AB-2956", "TCGA-AB-2936", "TCGA-AB-2934",
"TCGA-AB-2914", "TCGA-AB-2992", "TCGA-AB-2869", "TCGA-AB-2946",
"TCGA-AB-2894", "TCGA-AB-2963", "TCGA-AB-2928", "TCGA-AB-2924",
"TCGA-AB-2818", "TCGA-AB-2975", "TCGA-AB-2874", "TCGA-AB-2979",
"TCGA-AB-2826", "TCGA-AB-2990", "TCGA-AB-3001", "TCGA-AB-2885",
"TCGA-AB-2835", "TCGA-AB-2873", "TCGA-AB-2955", "TCGA-AB-2845",
"TCGA-AB-2836", "TCGA-AB-2925", "TCGA-AB-2884", "TCGA-AB-2820",
"TCGA-AB-2899", "TCGA-AB-3008", "TCGA-AB-2994", "TCGA-AB-2889",
"TCGA-AB-2853", "TCGA-AB-2896", "TCGA-AB-2893", "TCGA-AB-2867",
"TCGA-AB-2999", "TCGA-AB-2888", "TCGA-AB-2839", "TCGA-AB-2865",
"TCGA-AB-3007", "TCGA-AB-2932", "TCGA-AB-2976", "TCGA-AB-2834",
"TCGA-AB-2840", "TCGA-AB-2880", "TCGA-AB-2998", "TCGA-AB-2813",
"TCGA-AB-2882", "TCGA-AB-2995", "TCGA-AB-2950", "TCGA-AB-2810",
"TCGA-AB-2935", "TCGA-AB-2821", "TCGA-AB-2952", "TCGA-AB-2886",
"TCGA-AB-2805", "TCGA-AB-2876", "TCGA-AB-2808", "TCGA-AB-2937",
"TCGA-AB-2927", "TCGA-AB-2883", "TCGA-AB-2982", "TCGA-AB-2919",
"TCGA-AB-3012", "TCGA-AB-2841", "TCGA-AB-2875", "TCGA-AB-2984",
"TCGA-AB-2970", "TCGA-AB-2933"))
I'm not sure what is going wrong here given that in my X there are groups and in y there is the dependent variable.
Any suggestion or help would be really appreciated.


ggwithinstats is for plotting repeated measures in individual subjects, but the fact that you have different sized groups for FAB and no ID column suggests that this is not what you have. If the groups are different sizes, you will always get an error because you cannot have a repeated measures structure.
I suspect you are looking for ggbetweenstats rather than ggwithinstats, since all you appear to be doing is comparing different groups.
ggbetweenstats( # independent samples
data = dat,
x = FAB,
y = BM_percentage,
type = "nonparametric", # for wilcoxon
plot.type = "box", # for boxplot
centrality.plotting = FALSE # remove median
)

Related

Error using 'poly': 'degree' must be less than number of unique points while using 'effects' package

I am trying to use the effects package to create plots of effects in a linear mixed model. I specify the model
fit1 <- lmer(Values ~ stimuli + timeperiod + scale(poly(distance.code,3,raw=FALSE))*habitat + wind.speed + (1|location.code), data=ex.df, REML=FALSE)
For this model I can generate results for analysis as I expect using summary or anova but when I try to look at specific effects:
allEffects(fit1)
#or
plot(allEffects(fit1))
#or
emmeans(fit1, pairwise ~ stimuli)
An error is returned:
Error in poly(distance.code, 3, raw = FALSE) :
'degree' must be less than number of unique points
(with the plot function the error is different but is probably arising from the error with allEffects)
I understand, based on the responses to this question and this question, that "numerical overflow" can be an issue with poly terms. However, I am not clear on what this means or how to overcome the issue.
I also saw in this post and in another post about lme4 that I can no longer find, that I might need to update packages so I have updated 'effects' and 'lme4' in an attempt to remedy this but to no avail.
So if this error is happening because of "numerical overflow" how can I remedy the problem? or if it is not numerical overflow what is happening and how can I work around this?
a subset of my data using dput is:
structure(list(location.code = structure(c(1L, 1L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 4L, 4L,
4L, 4L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 3L,
3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 4L, 4L, 4L,
4L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 4L,
4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 3L, 3L,
3L, 3L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 4L, 4L, 4L), .Label = c("BSF1", "BSG1", "RLF3",
"RLG3", "CCBSF1", "CCBSG1", "CPF1", "CPF2", "CPG1", "CPG2", "OSG1",
"OSG2", "RLF4", "RLF5", "RLF1", "RLF2", "RLG1", "RLG2", "BNPF1",
"BNPG1", "OSG3", "OSF1", "CMG3", "CMF1", "BSG2", "BSG3", "WSF1",
"WSF2", "HPG1", "HPG2"), class = "factor"), stimuli = structure(c(3L,
3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L,
3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L,
3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("FOSP",
"BHCO", "COHA", "YEWA", "TUTI"), class = "factor"), habitat = structure(c(2L,
2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Grassland",
"Forest"), class = "factor"), exp.period = 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, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
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,
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), .Label = c("before",
"during", "after"), class = "factor"), timeperiod = c(6L, 6L,
6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 15L, 15L, 15L, 15L,
15L, 15L, 15L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 19L, 19L, 19L,
19L, 19L, 19L, 19L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 21L, 21L,
21L, 21L, 21L, 21L, 21L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 23L,
23L, 23L, 23L, 23L, 23L, 23L, 24L, 24L, 24L, 24L, 24L, 24L, 24L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 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, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 13L, 13L), distance.code = c(0L, 30L, 60L,
120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L,
60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L,
30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L,
0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L,
60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L,
30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L,
0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L,
120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 60L, 120L, 0L, 30L,
60L, 120L, 0L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L,
30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L,
60L, 120L, 0L, 30L, 60L, 120L, 0L, 60L, 120L, 0L, 30L, 60L, 120L,
0L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L,
120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L,
0L, 30L, 60L, 120L, 0L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 60L,
120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L,
30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L,
60L, 120L, 0L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 60L, 120L,
0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L,
60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L,
120L, 0L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 60L, 120L, 0L, 30L,
60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L,
0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 120L, 0L,
60L, 120L, 0L, 30L, 60L, 120L, 0L, 60L, 120L, 0L, 30L, 60L),
Values = c(910.721895276374, 922.652711611841, 926.219785713456,
918.776924477918, 1030.28919690464, 1121.98321368732, 992.741416151102,
910.878353926705, 920.201901019659, 922.134996121665, 917.610324052986,
992.059286431433, 1042.05240231832, 1018.99804250179, 911.976009884021,
918.215389274037, 931.037495260958, 913.49701806948, 981.032280455129,
983.700699744073, 989.716307418049, 911.476759038955, 918.554393750162,
920.391856289719, 911.795802370903, 994.583211567691, 1006.58290843226,
1005.52479816571, 908.665064025178, 917.940176257067, 922.746174825048,
921.752449434568, 986.419049170517, 1042.41789735969, 1082.89658057517,
916.02310296116, 918.254868924698, 931.01648294424, 924.221021573334,
982.154409713674, 1008.54477137219, 996.577798511801, 912.914857937818,
916.937508116615, 920.933077377339, 917.443294381608, 997.669828575817,
1007.44452218386, 1151.25894192961, 909.463528658898, 915.293665875472,
921.917039784441, 912.073280663674, 983.866984633392, 1002.04551764872,
986.791628665069, 907.695668282537, 917.845214744473, 932.330755620455,
917.500330773026, 972.609449456089, 1155.55960936774, 1083.40557091613,
909.903267624225, 914.846316952797, 921.279328283221, 914.498616645498,
1000.3672969178, 1021.78461788922, 1011.40975353271, 915.037273600535,
914.099859036178, 924.116937361394, 913.523739017819, 994.428182266452,
1123.09745015276, 1004.1485272116, 914.431649376896, 915.27037594587,
929.411251949862, 910.549315840806, 974.273124973661, 1145.99211507205,
1013.58184367388, 913.467056616881, 920.213007520924, 919.794369158301,
912.333012054637, 983.816025282468, 1103.11322201674, 974.792027063404,
910.532609655114, 917.616832229923, 923.462599912213, 913.432298686233,
1015.24811721269, 1070.61183211249, 1016.57332551186, 910.196695694198,
923.403802532832, 905.400995326023, 934.612035397761, 1036.98011238981,
963.147077473505, 953.792949959199, 916.899569521736, 931.240844862156,
919.11781354823, 938.028220926723, 995.408916523572, 960.825305234446,
993.019295484939, 1026.22960551445, 1000.13773127026, 962.347584090332,
1074.31979099791, 904.090295814044, 908.836747102913, 928.867625382891,
918.100799763641, 906.282906701285, 913.146312873635, 921.224088728859,
977.094140033575, 972.599778534534, 964.658406857446, 1197.35130424458,
921.91272768213, 910.507770576621, 942.269786765654, 922.718235872787,
1014.34022271036, 1128.29327664605, 1043.1365958913, 1238.18704569961,
919.185972424773, 925.486310755197, 908.769520270226, 919.644447501213,
1030.20866627018, 956.104935565803, 955.159231718685, 922.01947330213,
934.451182538208, 928.626906337293, 941.089746683706, 986.326936258622,
1003.40797963907, 1007.57786522109, 1021.91264348048, 995.68658929192,
993.102343807935, 1114.80420865448, 901.633626404701, 908.255562868123,
922.840049924103, 917.012733437446, 907.541530752433, 915.050696506642,
925.95358291661, 983.542956895186, 972.236377246083, 965.082329354352,
1205.36753472358, 918.337944633569, 910.137012141557, 952.89462134025,
923.334999242316, 977.420371016686, 1154.17994731565, 1022.82998099991,
1186.66254220951, 927.061613377597, 926.745527716988, 908.284054932259,
921.213190559531, 966.157586219165, 974.986841619676, 959.421220417498,
916.559494755925, 935.817296050643, 918.835719171662, 912.457217113586,
1023.62078549133, 1009.23121097376, 978.938675917385, 1005.81651905991,
981.715747809821, 953.127134375762, 1088.16577366048, 902.809201411559,
907.462229880533, 921.595454423298, 919.198277947855, 904.969515265664,
913.438353334218, 918.91715550342, 974.889830301362, 970.58615968713,
963.029605541189, 1182.94093491074, 915.889893279581, 908.147726780027,
942.742415528349, 928.20319656241, 979.939535179807, 1153.51966568673,
1020.93502990084, 1154.799618481, 916.246150801212, 936.016759720656,
914.4488779132, 918.823772018551, 962.397352323664, 986.957848140285,
972.131488585193, 985.364195731404, 932.548910038465, 917.363220594089,
919.124801182577, 1085.89850605988, 1031.66330597084, 974.763804119707,
1005.64983154588, 991.988118229379, 975.384741587994, 1064.14809010237,
902.60240793926, 907.989086075871, 923.287310593779, 912.878571722023,
904.107623756648, 905.563259817979, 917.423553921906, 991.530368160932,
975.190212414434, 965.951810135591, 1192.3330908297, 915.334621878897,
910.857441830446, 936.093336975328, 932.960789822422, 972.074491630181,
1106.77459226532, 993.45400883741, 1138.94109332484, 951.911391767329,
927.688604859773, 915.194279622847, 920.98264624041, 971.414103170297,
956.138106650696, 969.385400747507, 965.458656222347, 944.097918792458,
947.157460200658, 915.929397317864, 1029.14870726558, 992.151638322899,
964.680220137879, 954.129642526236, 981.48182339388, 968.10870393618,
1097.48462256339, 906.941701681267, 917.956716926981, 923.05649603805,
934.459432014683, 922.801034508827, 920.724850575215, 935.811146196027,
981.478432929603, 1012.67364507927, 966.471299899978, 1192.4066704659,
912.640460101352, 906.34455384334, 923.738349342148, 916.883929696437,
970.987788560016, 1210.42940542072, 975.753397539076, 1138.97675920151,
911.747488522664, 928.34872697947, 910.852487444859, 916.227875349016,
982.304620375747, 1028.52794775628, 999.236663664046, 913.408967803895,
934.334726415048, 916.354017093653, 918.660674732388, 1036.08727658415,
974.408618327141, 1006.21629092128, 1004.71633485176, 995.142763465394,
987.00017276687), wind.speed = c(0.8, 0.8, 0.8, 0.8, 0.2,
0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8,
0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8,
0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2,
0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8,
0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8,
0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2,
0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2,
0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 65, 65, 65,
65, 65, 65, 65, 55, 55, 55, 55, 50, 50, 50, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.9, 0.9, 0.9,
0.9, 65, 65, 65, 65, 65, 65, 65, 55, 55, 55, 55, 50, 50,
50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0.9, 0.9, 0.9, 0.9, 65, 65, 65, 65, 65, 65, 65, 55, 55,
55, 55, 50, 50, 50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0.9, 0.9, 0.9, 0.9, 65, 65, 65, 65, 65,
65, 65, 55, 55, 55, 55, 50, 50, 50, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.9, 0.9, 0.9, 0.9, 65,
65, 65, 65, 65, 65, 65, 55, 55, 55, 55, 50, 50, 50, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.9, 0.9,
0.9, 0.9, 65, 65, 65, 65, 65, 65, 65, 55, 55, 55, 55, 50,
50, 50, 0, 0, 0)), row.names = c(85L, 86L, 87L, 88L, 89L,
90L, 91L, 99L, 100L, 101L, 102L, 103L, 104L, 105L, 113L, 114L,
115L, 116L, 117L, 118L, 119L, 127L, 128L, 129L, 130L, 131L, 132L,
133L, 141L, 142L, 143L, 144L, 145L, 146L, 147L, 155L, 156L, 157L,
158L, 159L, 160L, 161L, 169L, 170L, 171L, 172L, 173L, 174L, 175L,
183L, 184L, 185L, 186L, 187L, 188L, 189L, 197L, 198L, 199L, 200L,
201L, 202L, 203L, 211L, 212L, 213L, 214L, 215L, 216L, 217L, 225L,
226L, 227L, 228L, 229L, 230L, 231L, 239L, 240L, 241L, 242L, 243L,
244L, 245L, 253L, 254L, 255L, 256L, 257L, 258L, 259L, 267L, 268L,
269L, 270L, 271L, 272L, 273L, 615L, 616L, 617L, 618L, 619L, 620L,
621L, 622L, 623L, 624L, 625L, 626L, 627L, 628L, 629L, 630L, 631L,
632L, 640L, 641L, 642L, 643L, 644L, 645L, 646L, 647L, 648L, 649L,
650L, 651L, 652L, 653L, 654L, 655L, 656L, 657L, 658L, 659L, 660L,
661L, 662L, 663L, 664L, 665L, 666L, 667L, 668L, 669L, 670L, 671L,
672L, 673L, 674L, 675L, 676L, 684L, 685L, 686L, 687L, 688L, 689L,
690L, 691L, 692L, 693L, 694L, 695L, 696L, 697L, 698L, 699L, 700L,
701L, 702L, 703L, 704L, 705L, 706L, 707L, 708L, 709L, 710L, 711L,
712L, 713L, 714L, 715L, 716L, 717L, 718L, 719L, 720L, 728L, 729L,
730L, 731L, 732L, 733L, 734L, 735L, 736L, 737L, 738L, 739L, 740L,
741L, 742L, 743L, 744L, 745L, 746L, 747L, 748L, 749L, 750L, 751L,
752L, 753L, 754L, 755L, 756L, 757L, 758L, 759L, 760L, 761L, 762L,
763L, 764L, 772L, 773L, 774L, 775L, 776L, 777L, 778L, 779L, 780L,
781L, 782L, 783L, 784L, 785L, 786L, 787L, 788L, 789L, 790L, 791L,
792L, 793L, 794L, 795L, 796L, 797L, 798L, 799L, 800L, 801L, 802L,
803L, 804L, 805L, 806L, 807L, 808L, 816L, 817L, 818L, 819L, 820L,
821L, 822L, 823L, 824L, 825L, 826L, 827L, 828L, 829L, 830L, 831L,
832L, 833L, 834L, 835L, 836L, 837L, 838L, 839L, 840L, 841L, 842L,
843L, 844L, 845L, 846L, 847L, 848L, 849L, 850L, 851L), class = "data.frame")
> ex.df <- head(ex.df, 100)
> dput(ex.df)
structure(list(location.code = structure(c(1L, 1L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L), .Label = c("BSF1",
"BSG1", "RLF3", "RLG3", "CCBSF1", "CCBSG1", "CPF1", "CPF2", "CPG1",
"CPG2", "OSG1", "OSG2", "RLF4", "RLF5", "RLF1", "RLF2", "RLG1",
"RLG2", "BNPF1", "BNPG1", "OSG3", "OSF1", "CMG3", "CMF1", "BSG2",
"BSG3", "WSF1", "WSF2", "HPG1", "HPG2"), class = "factor"), stimuli = structure(c(3L,
3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L,
3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L,
2L, 1L, 1L), .Label = c("FOSP", "BHCO", "COHA", "YEWA", "TUTI"
), class = "factor"), habitat = structure(c(2L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L), .Label = c("Grassland",
"Forest"), class = "factor"), exp.period = 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, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 1L), .Label = c("before", "during", "after"), class = "factor"),
timeperiod = c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 17L,
17L, 17L, 17L, 17L, 17L, 17L, 19L, 19L, 19L, 19L, 19L, 19L,
19L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 21L, 21L, 21L, 21L,
21L, 21L, 21L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 23L, 23L,
23L, 23L, 23L, 23L, 23L, 24L, 24L, 24L, 24L, 24L, 24L, 24L,
6L, 6L), distance.code = c(0L, 30L, 60L, 120L, 0L, 30L, 60L,
0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L,
30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L,
120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L,
30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L,
60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L,
0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L,
60L, 120L, 0L, 30L, 60L, 0L, 30L, 60L, 120L, 0L, 30L, 60L,
0L, 30L, 60L, 120L, 0L, 30L, 60L, 0L, 30L), Values = c(910.721895276374,
922.652711611841, 926.219785713456, 918.776924477918, 1030.28919690464,
1121.98321368732, 992.741416151102, 910.878353926705, 920.201901019659,
922.134996121665, 917.610324052986, 992.059286431433, 1042.05240231832,
1018.99804250179, 911.976009884021, 918.215389274037, 931.037495260958,
913.49701806948, 981.032280455129, 983.700699744073, 989.716307418049,
911.476759038955, 918.554393750162, 920.391856289719, 911.795802370903,
994.583211567691, 1006.58290843226, 1005.52479816571, 908.665064025178,
917.940176257067, 922.746174825048, 921.752449434568, 986.419049170517,
1042.41789735969, 1082.89658057517, 916.02310296116, 918.254868924698,
931.01648294424, 924.221021573334, 982.154409713674, 1008.54477137219,
996.577798511801, 912.914857937818, 916.937508116615, 920.933077377339,
917.443294381608, 997.669828575817, 1007.44452218386, 1151.25894192961,
909.463528658898, 915.293665875472, 921.917039784441, 912.073280663674,
983.866984633392, 1002.04551764872, 986.791628665069, 907.695668282537,
917.845214744473, 932.330755620455, 917.500330773026, 972.609449456089,
1155.55960936774, 1083.40557091613, 909.903267624225, 914.846316952797,
921.279328283221, 914.498616645498, 1000.3672969178, 1021.78461788922,
1011.40975353271, 915.037273600535, 914.099859036178, 924.116937361394,
913.523739017819, 994.428182266452, 1123.09745015276, 1004.1485272116,
914.431649376896, 915.27037594587, 929.411251949862, 910.549315840806,
974.273124973661, 1145.99211507205, 1013.58184367388, 913.467056616881,
920.213007520924, 919.794369158301, 912.333012054637, 983.816025282468,
1103.11322201674, 974.792027063404, 910.532609655114, 917.616832229923,
923.462599912213, 913.432298686233, 1015.24811721269, 1070.61183211249,
1016.57332551186, 910.196695694198, 923.403802532832), wind.speed = c(0.8,
0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2,
0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8,
0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8,
0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2,
0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2,
0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8,
0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8,
0.8, 0.8, 0.8, 0.2, 0.2, 0.2, 0.8, 0.8, 0.8, 0.8, 0.2, 0.2,
0.2, 65, 65)), row.names = c(85L, 86L, 87L, 88L, 89L, 90L,
91L, 99L, 100L, 101L, 102L, 103L, 104L, 105L, 113L, 114L, 115L,
116L, 117L, 118L, 119L, 127L, 128L, 129L, 130L, 131L, 132L, 133L,
141L, 142L, 143L, 144L, 145L, 146L, 147L, 155L, 156L, 157L, 158L,
159L, 160L, 161L, 169L, 170L, 171L, 172L, 173L, 174L, 175L, 183L,
184L, 185L, 186L, 187L, 188L, 189L, 197L, 198L, 199L, 200L, 201L,
202L, 203L, 211L, 212L, 213L, 214L, 215L, 216L, 217L, 225L, 226L,
227L, 228L, 229L, 230L, 231L, 239L, 240L, 241L, 242L, 243L, 244L,
245L, 253L, 254L, 255L, 256L, 257L, 258L, 259L, 267L, 268L, 269L,
270L, 271L, 272L, 273L, 615L, 616L), class = "data.frame")
Thanks for any help!
EDIT!!
I ran terms(fit1) as suggested in the comments, the results were as follows:
terms(fit1)
Values ~ stimuli + timeperiod + scale(poly(distance.code, 3,
raw = FALSE)) * habitat + wind.speed
attr(,"variables")
list(Values, stimuli, timeperiod, scale(poly(distance.code, 3,
raw = FALSE)), habitat, wind.speed)
attr(,"factors")
stimuli timeperiod scale(poly(distance.code, 3, raw = FALSE)) habitat wind.speed
Values 0 0 0 0 0
stimuli 1 0 0 0 0
timeperiod 0 1 0 0 0
scale(poly(distance.code, 3, raw = FALSE)) 0 0 1 0 0
habitat 0 0 0 1 0
wind.speed 0 0 0 0 1
scale(poly(distance.code, 3, raw = FALSE)):habitat
Values 0
stimuli 0
timeperiod 0
scale(poly(distance.code, 3, raw = FALSE)) 1
habitat 1
wind.speed 0
attr(,"term.labels")
[1] "stimuli" "timeperiod"
[3] "scale(poly(distance.code, 3, raw = FALSE))" "habitat"
[5] "wind.speed" "scale(poly(distance.code, 3, raw = FALSE)):habitat"
attr(,"order")
[1] 1 1 1 1 1 2
attr(,"intercept")
[1] 1
attr(,"response")
[1] 1
attr(,".Environment")
<environment: R_GlobalEnv>
attr(,"predvars")
list(Values, stimuli, timeperiod, scale(poly(distance.code, 3,
raw = FALSE)), habitat, wind.speed)

Here is a simple parallel example illustrating that wrapping poly() in scale() is the culprit:
> library(emmeans)
> mod1 = lm(mpg ~ am + poly(disp, 3), data = mtcars)
> ref_grid(mod1)
'emmGrid' object with variables:
am = 0, 1
disp = 230.72
> mod2 = lm(mpg ~ am + scale(poly(disp, 3)), data = mtcars)
> ref_grid(mod2)
Error in poly(disp, 3) :
'degree' must be less than number of unique points
Specifically, the call to scale() messes up the predvars attribute in the model's terms component:
> attr(terms(mod1), "predvars")
list(mpg, am, poly(disp, 3, coefs = list(alpha = c(230.721875,
279.549822668452, 298.198735227759), norm2 = c(1, 32, 476184.7946875,
5315202742.2241, 64139299346388.8))))
This provides the coefficients needed to construct the orthogonal polynomial basis; whereas...
> attr(terms(mod2), "predvars")
list(mpg, am, scale(poly(disp, 3)))
That information is excluded.
Note that the scale() call is completely unnecessary anyway, as poly() generates an orthonormal matrix of predictors.

R: Compute multiple correlations by group (and save output to csv file)

Is there a way to make a file with the correlation statistic between the raw number of fish observed ("num") and each environmental data column ("temp", "do", etc.) by species ("group")?
*As well as correlations between the means and medians of num vs. env. factors?
I'd also like to be able to choose which correlation method to use (Pearson correlation, Kendall rank correlation, Spearman correlation, etc.)
My data:
zeros <- structure(list(year = structure(c(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), .Label = c("2019", "2020"), class = "factor"), season = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("dry", "wet"), class = "factor"),
site = structure(c(1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L,
1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 1L, 1L, 2L, 2L, 3L,
3L, 4L, 4L, 5L, 5L, 1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L
), .Label = c("1", "2", "3", "4", "5"), class = "factor"),
group = 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
), .Label = c("Hardhead silverside", "Sailfin molly"), class = "factor"),
num = c(0, 8, 0, 9, 0, 13, 0, 9, 0, 10, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 7, 0, 2,
0, 3, 0, 13, 0), temp = c(23L, 36L, 35L, 34L, 30L, 28L, 18L,
19L, 33L, 33L, 25L, 20L, 33L, 23L, 36L, 32L, 28L, 17L, 34L,
31L, 26L, 34L, 26L, 35L, 15L, 25L, 26L, 20L, 18L, 14L, 23L,
17L, 26L, 17L, 17L, 19L, 29L, 31L, 18L, 15L), sal = c(12.5,
25.5, 8.5, 15.5, 17.5, 27.5, 9.5, 31.5, 1.5, 34.5, 25.5,
21.5, 10.5, 8.5, 32.5, 19.5, 6.5, 5.5, 15.5, 28.5, 6.5, 3.5,
29.5, 13.5, 7.5, 16.5, 3.5, 28.5, 22.5, 5.5, 9.5, 12.5, 29.5,
24.5, 8.5, 32.5, 37.5, 3.5, 12.5, 19.5), do = c(9.66, 7.66,
1.66, 14.66, 15.66, 1.66, 14.66, 15.66, 0.66, 5.66, 10.66,
11.66, 4.66, 0.66, 13.66, 1.66, 13.66, 6.66, 6.66, 10.66,
9.66, 15.66, 9.66, 15.66, 4.66, 13.66, 1.66, 11.66, 6.66,
8.66, 12.66, 0.66, 6.66, 0.66, 9.66, 16.66, 1.66, 10.66,
15.66, 10.66), depth = c(120L, 161L, 52L, 52L, 43L, 105L,
165L, 23L, 79L, 136L, 41L, 59L, 65L, 118L, 122L, 69L, 137L,
88L, 152L, 105L, 108L, 79L, 96L, 80L, 22L, 110L, 157L, 118L,
126L, 93L, 156L, 64L, 74L, 24L, 111L, 113L, 157L, 78L, 121L,
130L)), class = "data.frame", row.names = c(NA, -40L))

The first part of your question is straightforward:
zeros.spl <- split(zeros, zeros$group)
zeros.cors <- sapply(zeros.spl, function(x) cor(x[, "num"], x[, 6:9]))
dimnames(zeros.cors)[[1]] <- colnames(zeros)[6:9]
zeros.cors
# Hardhead silverside Sailfin molly
# temp -0.3080334 0.36174046
# sal 0.1393580 0.47095129
# do 0.2544695 -0.06646818
# depth 0.1296208 0.08777425
t(zeros.cors)
# temp sal do depth
# Hardhead silverside -0.3080334 0.1393580 0.25446948 0.12962078
# Sailfin molly 0.3617405 0.4709513 -0.06646818 0.08777425
Use write.csv(zeros.cors, file="results.csv") or write.csv(t(zeros.cors), file="results.csv") depending on what you want the rows/cols to be.
The second question is not clear. The means/medians of a group will be a single value so you cannot correlate it with the environmental variables. You could compute the means by group with aggregate:
aggregate(zeros[, 5:9], by=list(zeros$group), "mean")
# Group.1 num temp sal do depth
# 1 Hardhead silverside 1.45 25.95 15.35 8.51 105.20
# 2 Sailfin molly 2.45 25.00 18.90 9.06 90.25
aggregate(zeros[, 5:9], by=list(zeros$group), "median")
# Group.1 num temp sal do depth
# 1 Hardhead silverside 0 26 11.5 9.66 115.5
# 2 Sailfin molly 0 24 19.5 10.66 90.5

Changing the style of symbols in the legend so they are identical to those shown on the plot

I am trying change the legend so it is more representative of what is shown on the plot and is up to a publishing standard.
Here is an example I am trying to follow....
As you can see, the symbols in the legend are identical to those shown in the plot.
Here is my graph....
I am not happy with the legend that ggplot produces and I cant find a way to alter it so it matches the published example above.

If I understood your question correctly, you could just modify the the answer to your previous question by #dc37 Moving error bars in a line graph with three factors. I only added two lines for linetype.
library(Rmisc)
library(ggplot2)
tglf3 <- summarySE(df, measurevar="form",
groupvars=c("P","cultivar","Waterlogging"),na.rm=TRUE)
pd <- position_dodge(0.5)
ggplot(tglf3,aes(x=P, y=form,
shape = interaction(cultivar, Waterlogging),
color = interaction(cultivar, Waterlogging),
linetype = interaction(cultivar, Waterlogging)))+
geom_errorbar(aes(ymin=form-se, ymax=form+se), width=.6,position=pd) +
geom_point(size=3.5,position=pd) +
geom_line(position=pd) +
theme_bw() +
theme(legend.position = 'top') +
guides(color=guide_legend(ncol=2, title = "Legend"),
shape = guide_legend(ncol =2, title = "Legend"),
linetype = guide_legend(ncol =2, title = "Legend"))
Edit
Initially, I thought it cannot be done in ggplot2, but I have managed to trick ggplot2 to get what you want(?). I have learned some new tricks through this.
p <-ggplot(tglf3, aes(x=P, y=form,
color = interaction(cultivar, Waterlogging),
shape = interaction(cultivar, Waterlogging),
linetype = interaction(cultivar, Waterlogging)))+
geom_errorbar(aes(ymin=form-se, ymax=form+se), width=.6,position=pd) +
geom_point(size=3.5,position=pd) +
geom_line(position=pd) +
theme_bw() +
theme(legend.position = 'top') +
guides(linetype = guide_legend(ncol=2, title = "Riverina \nYarloop"),
shape = guide_legend(ncol =2, title = "Riverina \nYarloop"),
color = guide_legend(ncol =2, title = "Riverina \nYarloop"))
df <- droplevels(df)
brks <- levels(interaction(df$cultivar, df$Waterlogging))
lbs <- c("Non-waterlogged", "Non-waterlogged", "Waterlogged", "Waterlogged")
p + scale_shape_discrete(breaks=brks, labels=lbs) +
scale_color_discrete(breaks=brks, labels=lbs) +
scale_linetype_discrete(breaks=brks, labels=lbs)
Data
> dput(df)
structure(list(pot = c(41L, 42L, 43L, 44L, 61L, 62L, 63L, 64L,
45L, 46L, 47L, 48L, 65L, 66L, 67L, 68L, 49L, 50L, 51L, 52L, 69L,
70L, 71L, 72L, 53L, 54L, 55L, 56L, 73L, 74L, 75L, 76L, 57L, 58L,
59L, 60L, 77L, 78L, 79L, 80L, 81L, 82L, 83L, 84L, 101L, 102L,
103L, 104L, 85L, 86L, 87L, 88L, 105L, 106L, 107L, 108L, 89L,
90L, 91L, 92L, 109L, 110L, 111L, 112L, 93L, 94L, 95L, 96L, 113L,
114L, 115L, 116L, 97L, 98L, 99L, 100L, 117L, 118L, 119L, 120L
), rep = c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L), cultivar = structure(c(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, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 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("Dinninup", "Riverina",
"Seaton Park", "Yarloop"), class = "factor"), Waterlogging = structure(c(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), .Label = c("Non-waterlogged",
"Waterlogged"), class = "factor"), P = c(12.1, 12.1, 12.1, 12.1,
12.1, 12.1, 12.1, 12.1, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17,
15.17, 15.17, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24,
18.24, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39,
48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 12.1,
12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 15.17, 15.17, 15.17,
15.17, 15.17, 15.17, 15.17, 15.17, 18.24, 18.24, 18.24, 18.24,
18.24, 18.24, 18.24, 18.24, 24.39, 24.39, 24.39, 24.39, 24.39,
24.39, 24.39, 24.39, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35,
48.35, 48.35), form = c(2.81, 2.64, 2.59, 3.28, 3.18, 2.57, 2.9,
3, 2.38, 2.72, 2.58, 2.73, 3.06, 3.01, 3.01, 2.77, 2.95, 2.36,
2.91, 2.38, 3.33, 3.19, 3.17, 3.16, 3.16, 3.2, 2.58, 3.71, 3.11,
2.7, 2.92, 1.93, 2.95, 2.57, 2.68, 2.48, 3.34, 2.75, 2.52, 1.88,
1.19, 0.57, 0.64, 0.66, 1.13, 1.28, 0.85, 0.96, 1.34, 2.14, 0.63,
1.27, 1.13, 0.64, 1.21, 1.95, 1.11, 0.91, 0.75, 0.63, 1.06, 1.07,
1.05, 0.8, 1.41, 1.13, 0.75, 0.89, 1.98, 1.27, 1.01, 1, 1.16,
0.64, 0.64, 1.02, 1.03, 1.13, 0.79, 0.6)), row.names = 41:120, class = "data.frame")

How to show the id of outliers on a boxplot

How can you view the id of the outliers in a boxplot?
structure(list(pot = c(1L, 2L, 3L, 4L, 21L, 22L, 23L, 24L, 5L,
6L, 7L, 8L, 25L, 26L, 27L, 28L, 9L, 10L, 11L, 12L, 29L, 30L,
31L, 32L, 13L, 14L, 15L, 16L, 33L, 34L, 35L, 36L, 17L, 18L, 19L,
20L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 61L, 62L, 63L, 64L,
45L, 46L, 47L, 48L, 65L, 66L, 67L, 68L, 49L, 50L, 51L, 52L, 69L,
70L, 71L, 72L, 53L, 54L, 55L, 56L, 73L, 74L, 75L, 76L, 57L, 58L,
59L, 60L, 77L, 78L, 79L, 80L, 81L, 82L, 83L, 84L, 101L, 102L,
103L, 104L, 85L, 86L, 87L, 88L, 105L, 106L, 107L, 108L, 89L,
90L, 91L, 92L, 109L, 110L, 111L, 112L, 93L, 94L, 95L, 96L, 113L,
114L, 115L, 116L, 97L, 98L, 99L, 100L, 117L, 118L, 119L, 120L,
121L, 122L, 123L, 124L, 141L, 142L, 143L, 144L, 125L, 126L, 127L,
128L, 145L, 146L, 147L, 148L, 129L, 130L, 131L, 132L, 149L, 150L,
151L, 152L, 133L, 134L, 135L, 136L, 153L, 154L, 155L, 156L, 137L,
138L, 139L, 140L, 157L, 158L, 159L, 160L), rep = c(1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L,
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L), cultivar = 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, 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, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("Dinninup",
"Riverina", "Seaton Park", "Yarloop"), class = "factor"), Waterlogging = structure(c(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), .Label = c("Non-waterlogged",
"Waterlogged"), class = "factor"), P = c(12.1, 12.1, 12.1, 12.1,
12.1, 12.1, 12.1, 12.1, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17,
15.17, 15.17, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24,
18.24, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39,
48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 12.1,
12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 15.17, 15.17, 15.17,
15.17, 15.17, 15.17, 15.17, 15.17, 18.24, 18.24, 18.24, 18.24,
18.24, 18.24, 18.24, 18.24, 24.39, 24.39, 24.39, 24.39, 24.39,
24.39, 24.39, 24.39, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35,
48.35, 48.35, 12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 12.1, 12.1,
15.17, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17, 18.24,
18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 24.39, 24.39,
24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 48.35, 48.35, 48.35,
48.35, 48.35, 48.35, 48.35, 48.35, 12.1, 12.1, 12.1, 12.1, 12.1,
12.1, 12.1, 12.1, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17, 15.17,
15.17, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24, 18.24,
24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 24.39, 48.35,
48.35, 48.35, 48.35, 48.35, 48.35, 48.35, 48.35), total = c(3.66,
2.02, 1.59, 1.67, 2.12, 2.46, 1.79, 2.09, 2.03, 2.13, 1.83, 2.34,
2.66, 2.2, 1.79, 1.97, 2.17, 2.44, 1.49, 2.19, 2.92, 2.43, 1.58,
2.07, 2.48, 2.49, 1.69, 2.1, 2.38, 2.52, 2.41, 2.46, 2.22, 2.07,
1.97, 2.3, 2.48, 3.16, 1.76, 2.38, 2.81, 2.64, 2.59, 3.28, 3.18,
2.57, 2.9, 3, 2.38, 2.72, 2.58, 2.73, 3.06, 3.01, 3.01, 2.77,
2.95, 2.36, 2.91, 2.38, 3.33, 3.19, 3.17, 3.16, 3.16, 3.2, 2.58,
3.71, 3.11, 2.7, 2.92, 1.93, 2.95, 2.57, 2.68, 2.48, 3.34, 2.75,
2.52, 1.88, 1.19, 0.57, 0.64, 0.66, 1.13, 1.28, 0.85, 0.96, 1.34,
2.14, 0.63, 1.27, 1.13, 0.64, 1.21, 1.95, 1.11, 0.91, 0.75, 0.63,
1.06, 1.07, 1.05, 0.8, 1.41, 1.13, 0.75, 0.89, 1.98, 1.27, 1.01,
1, 1.16, 0.64, 0.64, 1.02, 1.03, 1.13, 0.79, 0.6, 3.88, 2.79,
2.73, 2.77, 3.54, 2.05, 1.51, 1.88, 3.86, 3.13, 1.97, 3.46, 3.98,
3.6, 2.12, 2.86, 2.95, 1.65, 1.94, 2.53, 2.21, 1.94, 2.05, 2.22,
3, 3.28, 1.55, 3.85, 2.4, 2.1, 1.98, 1.81, 2.48, 1.66, 2.06,
1.23, 3.75, 1.99, 1.67, 1.93)), class = "data.frame", row.names = c(NA,
-160L))
boxplot(total~cultivar*as.factor(P),data=x)
This is what I am after....
I have tried following example but does not work....
boxplot(total~cultivar*as.factor(P),data=x,id=list(n=Inf))
Identifying the outliers on the plot will make it easier to remove them from analysis. For some reason its not as straightforward as I thought. The post is asking me to add more details but I think there is sufficient.

You can use the car package:
library(car)
Boxplot(total ~ cultivar*as.factor(P), id.method="y", data = x)
Update:
Is it possible to flip the coordinates in car::Boxplot?
For the sake of the challenge, I tried some hacky methods. After all, I was able to rotate the plot, but it's not as conventional as it is for ggplot2::coord_flip. Here, I am just rotating the plot. So, the labels are still in their previous alignment. We can go further, remove the labels and rewrite them, but that would defeat the whole purpose of this solution which is simplicity.
library(car)
library(gridGraphics)
p <- Boxplot(total ~ cultivar*as.factor(P), id.method="y", data = x)
grab_grob <- function(){
grid.echo()
grid.grab()
}
g <- grab_grob()
grid.newpage()
pushViewport(viewport(width=0.5,angle=90))
grid.draw(g)

Unfortunately, though boxplot does return a list structure that provides the values of the outliers (e.g., boxplot(..., plot=FALSE)$out), this doesn't help here since there are equal values in other groups that are not outliers there. (In fact, I find using $out always a bit risky unless it is just one group.)
But you can use $stats to get the whisker parameters and find everything yourself. Unfortunately, this is not a one-liner.
First, though, since I don't know what you mean by "id", I'll add something to the data:
x$id <- seq_len(nrow(x))
base R
bp <- boxplot(total ~ cultivar * as.factor(P), data = x)
lims <- data.frame(nm = bp$names, t(bp$stats[c(1,5),]))
tmpx <- merge(transform(x, nm = paste(cultivar, as.factor(P), sep = ".")), lims, by = "nm", all.x = TRUE)
tmpx <- subset(tmpx, total < X1 | total > X2)
tmpx$xval <- match(tmpx$nm, bp$names)
text(total ~ xval, id, data = tmpx, adj = c(-0.5, 0.5))
Overlaying text over boxplots might be a problem for you; you can play with various shifting and/or flipping the coordinates to control this. Clipping (not shown here, but when a text label disappears out of the plot region) can also be a problem, so you might need to manually control the limits of the plot region.
dplyr
In case you like the tidyverse-way of looking at data-munging, here's an alternative that produces the same plot.
library(dplyr)
bp <- boxplot(total ~ cultivar * as.factor(P), data = x)
x %>%
mutate( nm = paste(cultivar, as.factor(P), sep = ".") ) %>%
left_join(data.frame(nm = bp$names, t(bp$stats[c(1,5),]), stringsAsFactors = FALSE),
by = "nm") %>%
filter(total < X1 | total > X2) %>%
mutate(xval = match(nm, bp$names)) %>%
text(data = ., total ~ xval, as.character(id), adj = c(-0.5, 0.5))
(Same plot.)
dplyr and ggplot2
library(dplyr)
library(ggplot2)
bp <- boxplot(total ~ cultivar * as.factor(P), data = x, plot = FALSE)
x %>%
mutate( nm = paste(cultivar, as.factor(P), sep = ".") ) %>%
left_join(data.frame(nm = bp$names, t(bp$stats[c(1,5),]), stringsAsFactors = FALSE),
by = "nm") %>%
mutate(outlier = total < X1 | total > X2) %>%
ggplot(aes(interaction(cultivar, P), total)) +
geom_boxplot() +
geom_text(aes(label = id), hjust = -0.5, data = ~ filter(., outlier)) +
coord_flip()
I chose to flip the coordinates so that the labels would be all included and shown, but it's not required for the method. One trick I used is that the data= argument to the ggplot2 functions can take an expression (I think of it as a tilde-function), which allows subsetting of the main dataset in-place. Here I use dplyr::filter, but in this case it is just as easy to use subset (base R) in case you are not otherwise using dplyr.

x-axis position for datapoints from stat_summary() in ggplot2()

I'd like to put subgroup's means above my boxplots, but can't find a way to position them correctly on the x-axis. With my current code, the symbols for the mean values are all put at the x-axis position of the top-level groups.
Here's my data, and the ggplot2() code below:
cc <- structure(list(Individuum = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L,
22L, 23L, 24L, 25L, 26L, 76L, 27L, 28L, 29L, 30L, 31L, 32L, 33L,
34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L,
47L, 48L, 49L, 50L, 51L, 52L, 53L, 54L, 55L, 56L, 57L, 58L, 59L,
60L, 61L, 62L, 63L, 64L, 65L, 66L, 67L, 68L, 69L, 70L, 71L, 72L,
73L, 74L, 75L, 77L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L,
24L, 25L, 26L, 76L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L,
36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L,
49L, 50L, 51L, 52L, 53L, 54L, 55L, 56L, 57L, 58L, 59L, 60L, 61L,
62L, 63L, 64L, 65L, 66L, 67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L,
75L, 77L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L,
26L, 76L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L,
38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L,
51L, 52L, 53L, 54L, 55L, 56L, 57L, 58L, 59L, 60L, 61L, 62L, 63L,
64L, 65L, 66L, 67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 77L
), Fachgruppe = 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, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 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, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 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, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("F1",
"F2", "F3"), class = "factor"), Kategorie = 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, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 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, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L), .Label = c("K1", "K2", "K3"), class = "factor"),
Antwort = c(0.384615384615385, 1, 0.538461538461538, 0.461538461538462,
0.769230769230769, 0.153846153846154, 0.230769230769231,
0.461538461538462, 0, 0.230769230769231, 0.153846153846154,
0, 0.769230769230769, 0.461538461538462, 0.692307692307692,
0, 0.230769230769231, 0.307692307692308, 0.692307692307692,
0.307692307692308, 0.230769230769231, 0.615384615384615,
0.615384615384615, 0.538461538461538, 0, 0.461538461538462,
0, 0.538461538461538, 0.538461538461538, 0.538461538461538,
0, 0.538461538461538, 0.0769230769230769, 0.692307692307692,
0.384615384615385, 0, 0.384615384615385, 0.461538461538462,
0.923076923076923, 0.384615384615385, 0.307692307692308,
0, 1, 0.461538461538462, 0.307692307692308, 0.153846153846154,
0.230769230769231, 0.692307692307692, 0, 0, 0, 0.615384615384615,
0.384615384615385, 0, 0.384615384615385, 0.384615384615385,
0.384615384615385, 0.461538461538462, 0.307692307692308,
0.384615384615385, 0.384615384615385, 0.153846153846154,
0.538461538461538, 0.153846153846154, 0.307692307692308,
0, 0.461538461538462, 0.615384615384615, 0, 0, 0.307692307692308,
0.307692307692308, 0.307692307692308, 0, 0, 0.538461538461538,
0.307692307692308, 0.214285714285714, 0.142857142857143,
0.357142857142857, 0.214285714285714, 0.785714285714286,
0.0714285714285714, 0.0714285714285714, 0.142857142857143,
0, 0, 0, 0, 0.5, 0, 0.571428571428571, 0, 0, 0.285714285714286,
0.142857142857143, 0.357142857142857, 0.0714285714285714,
0.357142857142857, 0.285714285714286, 0.142857142857143,
0, 0.357142857142857, 0, 0.285714285714286, 0.428571428571429,
0.357142857142857, 0, 0, 0.142857142857143, 0, 0.571428571428571,
0, 0.214285714285714, 0.357142857142857, 0.928571428571429,
0.214285714285714, 0.285714285714286, 0, 1, 0.285714285714286,
0.285714285714286, 0.0714285714285714, 0.214285714285714,
0.214285714285714, 0, 0, 0, 0.285714285714286, 0, 0, 0.357142857142857,
0.285714285714286, 0, 0.571428571428571, 0.428571428571429,
0.357142857142857, 0, 0.0714285714285714, 0.428571428571429,
0, 0.285714285714286, 0, 0.428571428571429, 0.714285714285714,
0, 0, 0.285714285714286, 0.214285714285714, 0.142857142857143,
0, 0, 0.5, 0.142857142857143, 0.2, 0.3, 0.4, 0.7, 0.7, 0.2,
0.2, 0.1, 0, 0.1, 0.1, 0, 0.5, 0, 0.4, 0, 0.3, 0.1, 0.4,
0.3, 0, 0.5, 0.7, 0, 0, 0.3, 0, 0.2, 0.4, 0.5, 0, 0.2, 0.1,
0, 0.3, 0, 0.3, 0, 0.7, 0.3, 0.2, 0, 1, 0.5, 0.3, 0, 0.2,
0.4, 0, 0, 0, 0.7, 0, 0, 0.4, 0.1, 0, 0.3, 0.3, 0.5, 0.2,
0.2, 0.4, 0, 0.3, 0, 0.5, 0.5, 0, 0, 0.4, 0, 0.1, 0, 0, 0.8,
0)), .Names = c("Individuum", "Fachgruppe", "Kategorie",
"Antwort"), row.names = c(NA, -231L), class = "data.frame")
The code:
p_cc <- ggplot(cc, aes(x = Fachgruppe, y = Antwort, fill = Kategorie)) +
geom_boxplot(outlier.size=0) +
stat_summary(fun.y=mean, colour="darkred", geom="point",
shape=16, size=2) +
labs(y = "Mittlerer Anteil\nbekannter Themen")

Encorporating the comment by #MLavoie: use position=position_dodge(0.75)
p_cc <- ggplot(cc, aes(x = Fachgruppe, y = Antwort, fill = Kategorie)) +
geom_boxplot(outlier.size=0) +
stat_summary(fun.y=mean, colour="darkred", geom="point",
shape=16, size=2, position=position_dodge(0.75)) +
labs(y = "Mittlerer Anteil\nbekannter Themen")

Resources