-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathanalysis_hyp_1.R
More file actions
343 lines (301 loc) · 9.95 KB
/
analysis_hyp_1.R
File metadata and controls
343 lines (301 loc) · 9.95 KB
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
library(lavaan)
source("constants.R")
if (sys.nframe() == 0) {
source("data_management_hyp_1.R")
}
################
# Hypothesis 1 #
################
# To test hypothesis 1,
# we will use Structural Equation Modeling (SEM)
# in order to determine the longitudinal phenotypic association
# of earlier peer victimization (MPVS score) with later BDD symptoms (DCQ score).
# Potential confounders, namely age and sex
# Without covid
model_scaled_32_without_covid <- "
# DCQ
dcq_total_26_1 ~ mpvs_total_12_1_scaled_32
dcq_total_26_1 ~ mpvs_total_child_14_1_scaled_32
dcq_total_26_1 ~ mpvs_total_16_1_scaled_32
dcq_total_26_1 ~ mpvs_total_phase_2_21_1_scaled_32
# Mpvs
mpvs_total_child_14_1_scaled_32 ~ mpvs_total_12_1_scaled_32
mpvs_total_16_1_scaled_32 ~ mpvs_total_child_14_1_scaled_32
mpvs_total_phase_2_21_1_scaled_32 ~ mpvs_total_16_1_scaled_32
# Age
dcq_total_26_1 ~ age_26_1
mpvs_total_12_1_scaled_32 ~ age_child_12_1
mpvs_total_child_14_1_scaled_32 ~ age_child_14_1
mpvs_total_16_1_scaled_32 ~ age_child_web_16_1
mpvs_total_phase_2_21_1_scaled_32 ~ age_phase2_child_21_1
# Sex
dcq_total_26_1 ~ sex_1_fct
mpvs_total_12_1_scaled_32 ~ sex_1_fct
mpvs_total_child_14_1_scaled_32 ~ sex_1_fct
mpvs_total_16_1_scaled_32 ~ sex_1_fct
mpvs_total_phase_2_21_1_scaled_32 ~ sex_1_fct
"
labels <- list(
dcq_total_26_1 = "DCQ (26y)",
mpvs_total_12_1_scaled_32 = "MPVS (12y)",
mpvs_total_child_14_1_scaled_32 = "MPVS (14y)",
mpvs_total_16_1_scaled_32 = "MPVS (16y)",
mpvs_total_phase_2_21_1_scaled_32 = "MPVS (21y)",
sex_1_fct = "Sex",
age_child_12_1 = "Age (12y)",
age_child_14_1 = "Age (14y)",
age_child_web_16_1 = "Age (16y)",
age_phase2_child_21_1 = "Age (21y)",
age_26_1 = "Age (26y)"
)
fit_fiml_scaled_32_without_covid <- sem(
model = model_scaled_32_without_covid,
data = df_essential_vars,
cluster = "fam_id",
missing = "fiml"
)
fit_fiml_scaled_32_without_covid_summary <- summary(
fit_fiml_scaled_32_without_covid,
standardized = T,
fit.measures = TRUE
)
modindices(fit_fiml_scaled_32_without_covid, sort = T)
resid(fit_fiml_scaled_32_without_covid, type = "cor.bollen")
fit_fiml_scaled_32_without_covid_residuals <- round(
change_df_labels(
df = extract_cov_residuals(
residual_obj = resid(fit_fiml_scaled_32_without_covid, type = "cor.bollen")
),
labels = var_labels
),
digits = 3
)
##################
# Modified model #
##################
model_scaled_32_without_covid_modified <- "
# DCQ
dcq_total_26_1 ~ mpvs_total_12_1_scaled_32
dcq_total_26_1 ~ mpvs_total_child_14_1_scaled_32
dcq_total_26_1 ~ mpvs_total_16_1_scaled_32
dcq_total_26_1 ~ mpvs_total_phase_2_21_1_scaled_32
# Mpvs
mpvs_total_child_14_1_scaled_32 ~ mpvs_total_12_1_scaled_32
mpvs_total_16_1_scaled_32 ~ mpvs_total_child_14_1_scaled_32
mpvs_total_phase_2_21_1_scaled_32 ~ mpvs_total_16_1_scaled_32
# Age
dcq_total_26_1 ~ age_26_1
mpvs_total_12_1_scaled_32 ~ age_child_12_1
mpvs_total_child_14_1_scaled_32 ~ age_child_14_1
mpvs_total_16_1_scaled_32 ~ age_child_web_16_1
mpvs_total_phase_2_21_1_scaled_32 ~ age_phase2_child_21_1
# Sex
dcq_total_26_1 ~ sex_1_fct
mpvs_total_12_1_scaled_32 ~ sex_1_fct
mpvs_total_child_14_1_scaled_32 ~ sex_1_fct
mpvs_total_16_1_scaled_32 ~ sex_1_fct
mpvs_total_phase_2_21_1_scaled_32 ~ sex_1_fct
# Added
mpvs_total_16_1_scaled_32 ~ mpvs_total_12_1_scaled_32
mpvs_total_phase_2_21_1_scaled_32 ~ mpvs_total_12_1_scaled_32
mpvs_total_phase_2_21_1_scaled_32 ~ mpvs_total_child_14_1_scaled_32
# Covs
# mpvs_total_12_1_scaled_32 ~~ mpvs_total_16_1_scaled_32
# mpvs_total_12_1_scaled_32 ~~ mpvs_total_phase_2_21_1_scaled_32
# mpvs_total_child_14_1_scaled_32 ~~ mpvs_total_phase_2_21_1_scaled_32
"
fit_fiml_scaled_32_without_covid_modified <- sem(
model = model_scaled_32_without_covid_modified,
data = df_essential_vars,
cluster = "fam_id",
missing = "fiml"
)
fit_fiml_scaled_32_without_covid_modified_sumary <- summary(
fit_fiml_scaled_32_without_covid_modified,
standardized = T,
fit.measures = TRUE
)
parameters_fit_fiml_without_covid_modified_phenotypic <- modify_parameter_estimates(
df = parameterestimates(
fit_fiml_scaled_32_without_covid_modified,
standardized = F
),
round_digits = 2
)
parameters_fit_fiml_without_covid_phenotypic_modified_standardized <- standardizedsolution(
fit_fiml_scaled_32_without_covid_modified
)
parameters_fit_fiml_without_covid_phenotypic_modified_standardized <- modify_parameter_estimates(
df = parameters_fit_fiml_without_covid_phenotypic_modified_standardized,
round_digits = 2
)
resid(fit_fiml_scaled_32_without_covid_modified, type = "cor.bollen")
# lavResiduals(fit_fiml_scaled_32_without_covid_modified)
# residuals(fit_fiml_scaled_32_without_covid_modified, type = "standardized")
# residuals(fit_fiml_scaled_32_without_covid_modified, type = "normalized")
fit_fiml_scaled_32_without_covid_modified_residuals <- round(
change_df_labels(
df = extract_cov_residuals(
residual_obj = resid(
fit_fiml_scaled_32_without_covid_modified,
type = "cor.bollen"
)
),
labels = var_labels
),
digits = 3
)
color_corr_residuals(
resid_df = (round(
change_df_labels(
df = extract_cov_residuals(
residual_obj = resid(
fit_fiml_scaled_32_without_covid_modified,
type = "cor.bollen"
)
),
labels = var_labels
),
digits = 3
) %>% rownames_to_column(var = "vars")),
limit = 0.1,
bg_color = "gray"
)
fit_plot_scaled_32_without_covid_modified <- lavaanPlot::lavaanPlot(
model = fit_fiml_scaled_32_without_covid_modified,
edge_options = list(color = "grey"),
coefs = TRUE, # covs = TRUE,
graph_options = list(
rankdir = "TB", fontsize = "15",
overlap = "true",
labelloc = "b", label = footnote
),
stars = c("regress", "latent", "covs"),
labels = labels,
stand = F,
conf.int = T,
edge_styles = T
)
fit_plot_scaled_32_without_covid_modified
fit_plot_scaled_32_without_covid_modified_standardized_lavaanplot <- lavaanPlot::lavaanPlot(
model = fit_fiml_scaled_32_without_covid_modified,
edge_options = list(color = "grey"),
coefs = TRUE, # covs = TRUE,
graph_options = list(
rankdir = "TB", fontsize = "14",
overlap = "true",
labelloc = "b", label = footnote
),
stars = c("regress", "latent", "covs"),
labels = labels,
stand = T,
conf.int = T,
edge_styles = T
)
fit_plot_scaled_32_without_covid_modified_standardized_lavaanplot
source("dags\\dag_hyp1.R")
# The rows in the analysis above are the following;
# test <- df_essential_vars %>%
# select(
# c(
# "twin_id",
# "fam_id",
# "sex_1",
# "age_child_12_1",
# "age_child_14_1",
# "age_child_web_16_1",
# "age_phase2_child_21_1",
# "age_26_1",
# "mpvs_total_12_1_scaled_32",
# "mpvs_total_child_14_1_scaled_32",
# "mpvs_total_16_1_scaled_32",
# "mpvs_total_phase_2_21_1_scaled_32",
# "dcq_total_26_1"
# )
# )
# dim(test[complete.cases(test[, c(
# "sex_1",
# "age_child_12_1",
# "age_child_14_1",
# "age_child_web_16_1",
# "age_phase2_child_21_1",
# "age_26_1"
# )]), ])
fit_ml_scaled_32_without_covid <- sem(
model = model_scaled_32_without_covid,
data = df_essential_vars,
cluster = "fam_id"
)
summary(fit_ml_scaled_32_without_covid)
# The rows in the complete case analysis above are the following;
# dim(test[complete.cases(test), ])
# With covid
# model_scaled_32_with_covid <- "
# # DCQ
# dcq_total_26_1 ~ mpvs_total_12_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_child_14_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_16_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_phase_2_21_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_cov1_21_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_cov2_21_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_cov3_21_1_scaled_32
# dcq_total_26_1 ~ mpvs_total_cov4_21_1_scaled_32
#
# # Mpvs
# mpvs_total_child_14_1_scaled_32 ~ mpvs_total_12_1_scaled_32
# mpvs_total_16_1_scaled_32 ~ mpvs_total_child_14_1_scaled_32
# mpvs_total_phase_2_21_1_scaled_32 ~ mpvs_total_16_1_scaled_32
# mpvs_total_cov1_21_1_scaled_32 ~ mpvs_total_phase_2_21_1_scaled_32
# mpvs_total_cov2_21_1_scaled_32 ~ mpvs_total_cov1_21_1_scaled_32
# mpvs_total_cov3_21_1_scaled_32 ~ mpvs_total_cov2_21_1_scaled_32
# mpvs_total_cov4_21_1_scaled_32 ~ mpvs_total_cov3_21_1_scaled_32
#
# # Age
# dcq_total_26_1 ~ age_26_1
# mpvs_total_12_1_scaled_32 ~ age_child_12_1
# mpvs_total_child_14_1_scaled_32 ~ age_child_14_1
# mpvs_total_16_1_scaled_32 ~ age_child_web_16_1
# mpvs_total_phase_2_21_1_scaled_32 ~ age_phase2_child_21_1
# mpvs_total_cov2_21_1_scaled_32 ~ age_cov1_child_21_1
# mpvs_total_cov3_21_1_scaled_32 ~ age_cov2_child_21_1
# mpvs_total_cov3_21_1_scaled_32 ~ age_cov3_child_21_1
# mpvs_total_cov4_21_1_scaled_32 ~ age_cov4_child_21_1
#
# # Sex
# dcq_total_26_1 ~ sex_1
# mpvs_total_12_1_scaled_32 ~ sex_1
# mpvs_total_child_14_1_scaled_32 ~ sex_1
# mpvs_total_16_1_scaled_32 ~ sex_1
# mpvs_total_phase_2_21_1_scaled_32 ~ sex_1
# mpvs_total_cov2_21_1_scaled_32 ~ sex_1
# mpvs_total_cov3_21_1_scaled_32 ~ sex_1
# mpvs_total_cov3_21_1_scaled_32 ~ sex_1
# mpvs_total_cov4_21_1_scaled_32 ~ sex_1
# "
# fit_fiml_scaled_32_with_covid <- sem(
# model = model_scaled_32_with_covid,
# data = df_essential_vars,
# cluster = "fam_id",
# missing = "fiml"
# )
# summary(fit_fiml_scaled_32_with_covid)
############
# Using MI #
############
#
# if (sys.nframe() == 0) {
# if (exists("imp_derived") == F) {
# if (file.exists("G:\\imp_derived.Rdata")) {
# load("G:\\imp_derived.Rdata")
# } else {
# source("imputation_derived.R")
# }
# }
#
# # Do not use semTools, it's deprecated
# library(lavaan.mi)
#
# fit_mi <- sem.mi(model = model_scaled_32_without_covid, data = imp_data_derived)
# summary(fit_mi)
# parameterEstimates.mi(fit_mi)
# }