-
Notifications
You must be signed in to change notification settings - Fork 0
/
corr_tests
374 lines (285 loc) · 14.1 KB
/
corr_tests
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
#correlation test
#testing to see if there is correlation between a seals diving behaviour and the age of their pup, or maternal mass, fatness, and age, date tagged (day-month).
setwd("D:/WEDE ANALYSIS/WESE_chapter2")
d1 <- read.csv("D:/WEDE ANALYSIS/WESE_chapter2/corr_test.csv", sep = ",", dec = ".", skip = 0)
#file with all dive stats & metadata ranked
#data in file
#number of dives (total, shallow, and deep)
#max, mean dive duration
#max, mean dive depth
#seal age
#seal mass
#seal fatness ratio (axillary girth/straight length)
#number previous pups
#pup age
#date tagged
#We want to compute the correlation between >50 dives and pup age first
# Visualize data using scatter plots
library("ggpubr")
ggscatter(d1, x = "pup_age", y = "dives_50m",
add = "reg.line", conf.int = TRUE,
cor.coef = TRUE, cor.method = "pearson",
xlab = "Pup age (days)", ylab = "Dives deeper than 50 m")
#p value = 0.0064
#R value = 0.53
ggscatter(d1, x = "pup_age", y = "dives_all",
add = "reg.line", conf.int = TRUE,
cor.coef = TRUE, cor.method = "pearson",
xlab = "Pup age (days)", ylab = "Dives deeper than 10 m")
#p value = 0.00033
#R value = 0.66
#test for normality
# Shapiro-Wilk normality test for mpg
#shapiro.test(my_data$mpg) # => p = 0.1229
# Shapiro-Wilk normality test for wt
#shapiro.test(my_data$wt) # => p = 0.09
# Shapiro-Wilk normality test
shapiro.test(d1$pup_age) # => p = 0.03424
shapiro.test(d1$dives_10m) # => p = <0.00001
shapiro.test(d1$dives_50m) # => p = <0.00001
shapiro.test(d1$mass) # => p = <0.01
shapiro.test(d1$day_month) # => p = factor - need to use julian days
shapiro.test(d1$julian_day) #=> p = 0.052
shapiro.test(d1$num_pups) # => p = <0.002
shapiro.test(d1$min_mum_age) # => p = <0.02
shapiro.test(d1$fatness) # => p = <0.19
#next test is the Q-Q plots
ggqqplot(d1$pup_age, ylab = "pup age")
ggqqplot(d1$dives_50m, ylab = "num 50 m dives")
ggqqplot(d1$dives_10m, ylab = "10 m dives")
ggqqplot(d1$mass, ylab = "mass")
ggqqplot(d1$julian_day, ylab = "julian date")
ggqqplot(d1$num_pups, ylab = "num prev pups")
ggqqplot(d1$min_mum_age, ylab = "mum age")
ggqqplot(d1$fatness, ylab = "fatness")
#choose to investigate correlation using Spearman's ranked
#Spearman rank correlation coefficient
#Spearman’s rho statistic is also used to estimate a rank-based measure of association.
#This test may be used if the data do not come from a bivariate normal distribution.
#### PUP AGE ####
##10m dives - all dives deeper than 10m ranked
#age of females pup ranked
cor.test(d1$norm_allrank, d1$pupage_ranked, method = "spearman", exact = FALSE)
#Spearman's rank correlation rho
#data: d1$norm_allrank and d1$pupage_ranked
#S = 1007.2, p-value = 0.001132
#alternative hypothesis: true rho is not equal to 0
#sample estimates:
# rho
#0.6126146
library("ggpubr")
ggscatter(d1, x = "pup_age", y = "norm_allrank",
add = "reg.line", conf.int = TRUE,
cor.coef = TRUE, cor.method = "spearman",
xlab = "Pup age (days)", ylab = "Dives deeper than 10 m")
#rho is the Spearman's correlation coefficient
#Interpret correlation coefficient
#Correlation coefficient is comprised between -1 and 1:
# -1 indicates a strong negative correlation : this means that every time x increases, y decreases (left panel figure)
# 0 means that there is no association between the two variables (x and y) (middle panel figure)
# 1 indicates a strong positive correlation : this means that y increases with x (right panel figure)
##50 m dives
#testing all dives deeper than 50m against age of females pup
cor.test(d1$norm_deeprank, d1$pupage_ranked, method = "spearman", exact = FALSE)
##shallow dives >= 50m
#testing all dives between 10m and 50m against age of females pup
cor.test(d1$norm_shallrank, d1$pupage_ranked, method = "spearman", exact = FALSE)
## Mum mass
t3 <- cor.test(d1$mass_ranked, d1$pupage_ranked, method = "spearman", exact = FALSE)
##Mum fatness
t4 <- cor.test(d1$fatness_ranked, d1$pupage_ranked, method = "spearman", exact = FALSE)
## day-month
t5 <- cor.test(d1$daymonth_ranked, d1$pupage_ranked, method = "spearman", exact = FALSE)
#### all dives####
names(d1)
"mass_ranked" #seal mass
"daymonth_ranked" #date tagged
"fatness_ranked" #fatness ratio (ax girth/str length
"minage_ranked" #seal minimum age
"pupage_ranked" #pup age
"numpups_ranked" #number previous pups
"norm_allrank" #standardised number of all dives completed (dives/hr)
##pup age
cor.test(d1$norm_allrank, d1$pupage_ranked, method = "spearman", exact = FALSE)
##mum mass
cor.test(d1$norm_allrank, d1$mass_ranked, method = "spearman", exact = FALSE)
##day month
cor.test(d1$norm_allrank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
##fatness
cor.test(d1$norm_allrank, d1$fatness_ranked, method = "spearman", exact = FALSE)
##mum age
cor.test(d1$norm_allrank, d1$minage_ranked, method = "spearman", exact = FALSE)
#num pups
cor.test(d1$norm_allrank, d1$numpups_ranked, method = "spearman", exact = FALSE)
#### deep dives####
names(d1)
"mass_ranked" #seal mass
"daymonth_ranked" #date tagged
"fatness_ranked" #fatness ratio (ax girth/str length
"minage_ranked" #seal minimum age
"pupage_ranked" #pup age
"numpups_ranked" #number previous pups
"norm_deeprank" #standardised number of deep dives completed greater than 50m (dives/hr)
##pup age
cor.test(d1$norm_deeprank, d1$pupage_ranked, method = "spearman", exact = FALSE)
##mum mass"norm_deeprank"
cor.test(d1$norm_deeprank, d1$mass_ranked, method = "spearman", exact = FALSE)
##day month
cor.test(d1$norm_deeprank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
##fatness
cor.test(d1$norm_deeprank, d1$fatness_ranked, method = "spearman", exact = FALSE)
##mum age
cor.test(d1$norm_deeprank, d1$minage_ranked, method = "spearman", exact = FALSE)
#num pups
cor.test(d1$norm_deeprank, d1$numpups_ranked, method = "spearman", exact = FALSE)
#### shallow dives####
names(d1)
"mass_ranked"
"daymonth_ranked"
"fatness_ranked"
"minage_ranked"
"pupage_ranked"
"numpups_ranked"
"norm_shallrank" #standardised shallow dives completed, greater than 10m, less than 50m (dives/hr)
##pup age
cor.test(d1$norm_shallrank, d1$pupage_ranked, method = "spearman", exact = FALSE)
##mum mass
cor.test(d1$norm_shallrank, d1$mass_ranked, method = "spearman", exact = FALSE)
##day month
cor.test(d1$norm_shallrank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
##fatness
cor.test(d1$norm_shallrank, d1$fatness_ranked, method = "spearman", exact = FALSE)
##mum age
cor.test(d1$norm_shallrank, d1$minage_ranked, method = "spearman", exact = FALSE)
#num pups
cor.test(d1$norm_shallrank, d1$numpups_ranked, method = "spearman", exact = FALSE)
####depth duration mean max etc ####
# "maxdep_rank" "meandep_rank"
# "maxdur_rank" "meandur_rank"
#against
#"mass_ranked" "daymonth_ranked" "fatness_ranked" "minage_ranked" "pupage_ranked" "numpups_ranked"
#depth
cor.test(d1$maxdep_rank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdep_rank, d1$mass_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdep_rank, d1$fatness_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdep_rank, d1$minage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdep_rank, d1$pupage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdep_rank, d1$numpups_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$mass_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$fatness_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$minage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$pupage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandep_rank, d1$numpups_ranked, method = "spearman", exact = FALSE)
#duration
# "maxdur_rank" "meandur_rank"
cor.test(d1$maxdur_rank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdur_rank, d1$mass_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdur_rank, d1$fatness_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdur_rank, d1$minage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdur_rank, d1$pupage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$maxdur_rank, d1$numpups_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$daymonth_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$mass_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$fatness_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$minage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$pupage_ranked, method = "spearman", exact = FALSE)
cor.test(d1$meandur_rank, d1$numpups_ranked, method = "spearman", exact = FALSE)
####T.tests####
#t.test for metadata between foraging groups
#asks is there a significant difference between foragers and non foragers
#we have:
#non foragers 9
#foragers 17
#all 26
setwd("D:/WEDE ANALYSIS/WESE_chapter2")
#importing file that has data for each seal
#foraging status
#pup age
#mass
#fatness
#age minimum
#previous pups
#behaviour times from BORIS
data <- read.csv("D:/WEDE ANALYSIS/WESE_chapter2/t-test.csv", sep = ",", dec = ".", skip = 0)
non_forager <- subset(data, group == "Non-forager", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness", "Searching", "Pup",
"Resting", "Aggression", 'swimming'))
forager <- subset(data, group == "Forager", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness","Searching", "Pup",
"Resting", "Aggression", 'swimming'))
#one or two tailed?
#can look in either direction on the bell curve for the answer
#our data has two tails: Testing whether foragers have older or younger pups than non foragers
#is there a significant difference between the pup ages of foragers and non foragers
#our data is unpaired
t.test(forager$pup_age, non_forager$pup_age, alternative =
"two.sided", paired = FALSE )
t.test(forager$mass, non_forager$mass, alternative =
"two.sided", paired = FALSE )
t.test(forager$prev_pup, non_forager$prev_pup, alternative =
"two.sided", paired = FALSE )
t.test(forager$fatness, non_forager$fatness, alternative =
"two.sided", paired = FALSE )
t.test(forager$age_min, non_forager$age_min, alternative =
"two.sided", paired = FALSE )
####now test for BORIS behaviours####
#- differences between groups
#time each seal spent displaying behaviour quantified in BORIS
t.test(forager$Searching, non_forager$Searching, alternative =
"two.sided", paired = FALSE )
t.test(forager$Pup, non_forager$Pup, alternative =
"two.sided", paired = FALSE )
t.test(forager$Resting, non_forager$Resting, alternative =
"two.sided", paired = FALSE )
t.test(forager$Aggression, non_forager$Aggression, alternative =
"two.sided", paired = FALSE )
t.test(forager$swimming, non_forager$swimming, alternative =
"two.sided", paired = FALSE )
# only searching significantly different between two groups
####unsuccessful and successful foragers####
suc_forager <- subset(data, success == "Successful", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness", "Searching", "Pup",
"Resting", "Aggression", 'swimming'))
unsuc_forager <- subset(data, success == "Unsuccessful", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness","Searching", "Pup",
"Resting", "Aggression", 'swimming'))
t.test(suc_forager$pup_age, unsuc_forager$pup_age, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$mass, unsuc_forager$mass, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$prev_pup, unsuc_forager$prev_pup, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$fatness, unsuc_forager$fatness, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$age_min, unsuc_forager$age_min, alternative =
"two.sided", paired = FALSE )
#BORIS behaviours ####
#differences between foraging groups
t.test(suc_forager$Searching, unsuc_forager$Searching, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$Pup, unsuc_forager$Pup, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$Resting, unsuc_forager$Resting, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$Aggression, unsuc_forager$Aggression, alternative =
"two.sided", paired = FALSE )
t.test(suc_forager$swimming, unsuc_forager$swimming, alternative =
"two.sided", paired = FALSE )
####diving behaviour 2018 v 2019####
#did seals tagged in 2019 dive more often that seals tagged in 2018
#year vs dives
seals2018 <- subset(data, year == "2018", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness", "Searching", "Pup",
"Resting", "Aggression", 'swimming', "dives",
"dive_standard"))
seals2019 <- subset(data, year == "2019", select = c("pup_age", "mass", "age_min",
"prev_pup", "fatness","Searching", "Pup",
"Resting", "Aggression", 'swimming', "dives",
"dive_standard"))
t.test(seals2018$pup_age, seals2019$pup_age, alternative =
"two.sided", paired = FALSE )
t.test(seals2018$dives, seals2019$dives, alternative =
"two.sided", paired = FALSE )
t.test(seals2018$dive_standard, seals2019$dive_standard, alternative =
"two.sided", paired = FALSE )