Analyses Using Proportional Averages
Load packages
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(here) ## here() starts at /Users/sarahdaniels/Desktop/All_Analyseslibrary(janitor) ##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(haven)
library(naniar)
library(ggpubr)
library(report)
library(ggplot2)
library(reshape2)##
## Attaching package: 'reshape2'
##
## The following object is masked from 'package:tidyr':
##
## smithslibrary(lme4)## Loading required package: Matrix
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpacklibrary(sjPlot)
library(parameters)
library(mediation)## Loading required package: MASS
##
## Attaching package: 'MASS'
##
## The following object is masked from 'package:dplyr':
##
## select
##
## Loading required package: mvtnorm
## Loading required package: sandwich
## mediation: Causal Mediation Analysis
## Version: 4.5.0library(lavaan)## This is lavaan 0.6-15
## lavaan is FREE software! Please report any bugs.library(lmerTest)##
## Attaching package: 'lmerTest'
##
## The following object is masked from 'package:lme4':
##
## lmer
##
## The following object is masked from 'package:stats':
##
## stepSet up
Reading the EC data
Mean scores for the EC data
PRE_IUS_tm <- mutate(PRE_IUS_EC, PRE_IUS_mean = rowMeans(dplyr::select(PRE_IUS_EC, c(B_IUS_1, B_IUS_2, B_IUS_3, B_IUS_4, B_IUS_5, B_IUS_6, B_IUS_7, B_IUS_8, B_IUS_9, B_IUS_10, B_IUS_11, B_IUS_12)), na.rm = TRUE))
POST_IUS_tm <- mutate(POST_IUS_EC, POST_IUS_mean = rowMeans(dplyr::select(POST_IUS_EC, c(POST_IUS_1, POST_IUS_2, POST_IUS_3, POST_IUS_4, POST_IUS_5, POST_IUS_6, POST_IUS_7, POST_IUS_8, POST_IUS_9, POST_IUS_10, POST_IUS_11, POST_IUS_12)), na.rm = TRUE))
PRE_FI_tm <- mutate(PRE_FI_EC, PRE_FI_mean = rowMeans(dplyr::select(PRE_FI_EC, c(B_FI_friends, B_FI_strangers, B_FI_work, B_FI_education, B_FI_hobbies)), na.rm = TRUE))
PRE_RTQ_tm <- mutate(PRE_RTQ_EC, PRE_RTQ_mean = rowMeans(dplyr::select(PRE_RTQ_EC, c(B_RTQ_1, B_RTQ_2, B_RTQ_3, B_RTQ_4, B_RTQ_5, B_RTQ_6, B_RTQ_7, B_RTQ_8, B_RTQ_9, B_RTQ_10)), na.rm = TRUE))
PRE_ERQ_tm <- mutate(PRE_ERQ_EC, PRE_ERQ_mean = rowMeans(dplyr::select(PRE_ERQ_EC, c(B_ERQ_1, B_ERQ_2, B_ERQ_3, B_ERQ_4, B_ERQ_5, B_ERQ_6, B_ERQ_7, B_ERQ_8, B_ERQ_9, B_ERQ_10)), na.rm = TRUE))
#PRE_ERQ_R_tm <- mutate(PRE_ERQ_EC, PRE_ERQ_mean_R = rowMeans(dplyr::select(PRE_ERQ_EC, c(B_ERQ_1, B_ERQ_3, B_ERQ_5, B_ERQ_7, B_ERQ_8, B_ERQ_10)), na.rm = TRUE))
PRE_PHQ_tm <- mutate(PRE_PHQ_EC, PRE_PHQ_mean = rowMeans(dplyr::select(PRE_PHQ_EC, c(B_PHQ_1, B_PHQ_2, B_PHQ_3, B_PHQ_4, B_PHQ_5, B_PHQ_6, B_PHQ_7, B_PHQ_8)), na.rm = TRUE))
PRE_GAD_tm <- mutate(PRE_GAD_EC, PRE_GAD_mean = rowMeans(dplyr::select(PRE_GAD_EC, c(B_GAD_1, B_GAD_2, B_GAD_3, B_GAD_4, B_GAD_5, B_GAD_6, B_GAD_7)), na.rm = TRUE))
W1_IUS_tm <- mutate(W1_IUS_EC, W1_IUS_mean = rowMeans(dplyr::select(W1_IUS_EC, c(W1_IUS_1, W1_IUS_2, W1_IUS_3, W1_IUS_4, W1_IUS_5, W1_IUS_6, W1_IUS_7, W1_IUS_8, W1_IUS_9, W1_IUS_10, W1_IUS_11, W1_IUS_12)), na.rm = TRUE))
W1_FI_tm <- mutate(W1_FI_EC, W1_FI_mean = rowMeans(dplyr::select(W1_FI_EC, c(W1_FI_friends, W1_FI_strangers, W1_FI_work, W1_FI_education, W1_FI_hobbies)), na.rm = TRUE))
W1_RTQ_tm <- mutate(W1_RTQ_EC, W1_RTQ_mean = rowMeans(dplyr::select(W1_RTQ_EC, c(W1_RTQ_1, W1_RTQ_2, W1_RTQ_3, W1_RTQ_4, W1_RTQ_5, W1_RTQ_6, W1_RTQ_7, W1_RTQ_8, W1_RTQ_9, W1_RTQ_10)), na.rm = TRUE))
W1_ERQ_tm <- mutate(W1_ERQ_EC, W1_ERQ_mean = rowMeans(dplyr::select(W1_ERQ_EC, c(W1_ERQ_1, W1_ERQ_2, W1_ERQ_3, W1_ERQ_4, W1_ERQ_5, W1_ERQ_6, W1_ERQ_7, W1_ERQ_8, W1_ERQ_9, W1_ERQ_10)), na.rm = TRUE))
#W1_ERQ_R_tm <- mutate(W1_ERQ_EC, W1_ERQ_mean_R = rowMeans(dplyr::select(W1_ERQ_EC, c(W1_ERQ_1, W1_ERQ_3, W1_ERQ_5, W1_ERQ_7, W1_ERQ_8, W1_ERQ_10)), na.rm = TRUE))
W1_PHQ_tm <- mutate(W1_PHQ_EC, W1_PHQ_mean = rowMeans(dplyr::select(W1_PHQ_EC, c(W1_PHQ_1, W1_PHQ_2, W1_PHQ_3, W1_PHQ_4, W1_PHQ_5, W1_PHQ_6, W1_PHQ_7, W1_PHQ_8)), na.rm = TRUE))
W1_GAD_tm <- mutate(W1_GAD_EC, W1_GAD_mean = rowMeans(dplyr::select(W1_GAD_EC, c(W1_GAD_1, W1_GAD_2, W1_GAD_3, W1_GAD_4, W1_GAD_5, W1_GAD_6, W1_GAD_7)), na.rm = TRUE))Complete dataframe for the ECs
merge_1 <- merge(PRE_IUS_tm,PRE_GM_EC,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_2 <- merge(merge_1,PRE_FI_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_3 <- merge(merge_2,PRE_Mood_EC,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_4 <- merge(merge_3,PRE_RTQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_5 <- merge(merge_4,PRE_ERQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_6 <- merge(merge_5,PRE_PHQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_7 <- merge(merge_6,PRE_GAD_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_8 <- merge(merge_7,POST_IUS_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_9 <- merge(merge_8,POST_GM_EC,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_10 <- merge(merge_9,POST_Mood_EC,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_11 <- merge(merge_10,W1_IUS_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_12 <- merge(merge_11,W1_GM_EC,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_13 <- merge(merge_12,W1_FI_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_14 <- merge(merge_13,W1_RTQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_15 <- merge(merge_14,W1_ERQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
merge_16 <- merge(merge_15,W1_PHQ_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
EC_MI_data <- merge(merge_16,W1_GAD_tm,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)Downloading full dataframe
write.csv(EC_MI_data, "Full_MI_Data_EC.csv")Reading the full data (intervention group, psychoeducation control group, and EC group)
Full_MI_data_B1W <- read_csv("Full_MI_Data.csv") %>%
dplyr::select(-"...147", -"...148", -"...149", -"...150", -"...151", -"...152", -"...153", -"W1_GM")## New names:
## Rows: 259 Columns: 153
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (144): ...1, ID, B_IUS_1, B_IUS_2, B_IUS_3,
## B_IUS_4, B_IUS_5, B_IUS_6, B... lgl (7): ...147, ...148, ...149, ...150,
## ...151, ...152, ...153
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `` -> `...147`
## • `` -> `...148`
## • `` -> `...149`
## • `` -> `...150`
## • `` -> `...151`
## • `` -> `...152`
## • `` -> `...153`Adding one month data
# loading 1M data
M1_Mood <- read_csv("M1_Mood_fm.csv")## New names:
## Rows: 185 Columns: 7
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (5): ...1, ...2, ID, M1_distressed_pleasant,
## M1_anxious_relaxed
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_IUS <- read_csv("M1_IUS_fm.csv")## New names:
## Rows: 185 Columns: 20
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (3): Prolific_ID, Group, 13. Please select response option 'Not at all'... dbl
## (17): ...1, ...2, ID, M1_IUS_1, M1_IUS_2, M1_IUS_3, M1_IUS_4, M1_IUS_5, ...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_GM <- read_csv("M1_GM_fm.csv")## New names:
## Rows: 184 Columns: 6
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (4): ...1, ...2, ID, M1_GM
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_FI <- read_csv("M1_FI_fm.csv")## New names:
## Rows: 186 Columns: 11
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (9): ...1, ...2, ID, M1_FI_friends,
## M1_FI_strangers, M1_FI_work, M1_FI_e...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_RTQ <- read_csv("M1_RTQ_fm.csv")## New names:
## Rows: 185 Columns: 16
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (14): ...1, ...2, ID, M1_RTQ_1, M1_RTQ_2, M1_RTQ_3,
## M1_RTQ_4, M1_RTQ_5, ...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_PHQ <- read_csv("M1_PHQ_fm.csv")## New names:
## Rows: 185 Columns: 16
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (3): Prolific_ID, Group, 9. Please select response option 'More than ha... dbl
## (13): ...1, ...2, ID, M1_PHQ_1, M1_PHQ_2, M1_PHQ_3, M1_PHQ_4, M1_PHQ_5, ...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_GAD <- read_csv("M1_GAD_fm.csv")## New names:
## Rows: 185 Columns: 13
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (11): ...1, ...2, ID, M1_GAD_1, M1_GAD_2, M1_GAD_3,
## M1_GAD_4, M1_GAD_5, ...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`M1_ERQ <- read_csv("M1_ERQ_fm.csv")## New names:
## Rows: 185 Columns: 18
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (3): Prolific_ID, Group, 11. Please select response option 'Strongly Di... dbl
## (15): ...1, ...2, ID, M1_ERQ_1, M1_ERQ_2, M1_ERQ_3, M1_ERQ_4, M1_ERQ_5, ...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1` -> `...2`W1_GM <- read_csv("W1_GM_fm.csv")## New names:
## Rows: 204 Columns: 5
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Prolific_ID, Group dbl (3): ...1, ID, W1_GM
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`# merging 1 month with the full data
Full_merge_1 <- merge(Full_MI_data_B1W,M1_Mood,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
Full_merge_2 <- merge(Full_merge_1,M1_IUS,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)
Full_merge_3 <- merge(Full_merge_2,M1_GM,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_2, M1_GM, by = c("Prolific_ID", "ID", :
## column names '...1.x', '...1.y' are duplicated in the resultFull_merge_4 <- merge(Full_merge_3,M1_FI,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_3, M1_FI, by = c("Prolific_ID", "ID", :
## column names '...1.x', '...1.y', '...2.x', '...2.y' are duplicated in the
## resultFull_merge_5 <- merge(Full_merge_4,M1_RTQ,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_4, M1_RTQ, by = c("Prolific_ID", :
## column names '...1.x', '...1.y', '...2.x', '...1.x', '...2.y', '...1.y' are
## duplicated in the resultFull_merge_6 <- merge(Full_merge_5,M1_ERQ,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_5, M1_ERQ, by = c("Prolific_ID", :
## column names '...1.x', '...1.y', '...2.x', '...1.x', '...2.y', '...1.y',
## '...2.x', '...2.y' are duplicated in the resultFull_merge_7 <- merge(Full_merge_6,M1_PHQ,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_6, M1_PHQ, by = c("Prolific_ID", :
## column names '...1.x', '...1.y', '...2.x', '...1.x', '...2.y', '...1.y',
## '...2.x', '...1.x', '...2.y', '...1.y' are duplicated in the resultFull_merge_8 <- merge(Full_merge_7,W1_GM,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_7, W1_GM, by = c("Prolific_ID", "ID", :
## column names '...1.x', '...1.y', '...2.x', '...1.x', '...2.y', '...1.y',
## '...2.x', '...1.x', '...2.y', '...1.y' are duplicated in the resultFull_data_B1W1M <- merge(Full_merge_8,M1_GAD,
by=c("Prolific_ID", "ID", "Group"),
all = TRUE)## Warning in merge.data.frame(Full_merge_8, M1_GAD, by = c("Prolific_ID", :
## column names '...1.x', '...1.y', '...2.x', '...1.x', '...2.y', '...1.y',
## '...2.x', '...1.x', '...2.y', '...1.y', '...2.x', '...1.x', '...1.y', '...2.y'
## are duplicated in the resultwrite.csv(Full_data_B1W1M, "Full_MI_Data_alltp.csv")# new columns with average mood
read_full_data <- read_csv("Full_MI_Data_B1W1M.csv")## New names:
## Rows: 262 Columns: 243
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (5): Prolific_ID, Group, 13. Please select response option 'Not at all... dbl
## (226): ...1, ID, ...5, B_IUS_1, B_IUS_2, B_IUS_3, B_IUS_4, B_IUS_5, B_IU... lgl
## (12): ...232, ...233, ...234, ...235, ...236, ...237, ...238, ...239, ....
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
## • `...1.x` -> `...5`
## • `...1.y` -> `...147`
## • `...2.x` -> `...148`
## • `...1.x` -> `...151`
## • `...2.y` -> `...152`
## • `...1.y` -> `...168`
## • `...2.x` -> `...169`
## • `...1.x` -> `...171`
## • `...2.y` -> `...172`
## • `...1.y` -> `...179`
## • `...2.x` -> `...180`
## • `...1.x` -> `...192`
## • `...2.y` -> `...193`
## • `...1.y` -> `...207`
## • `...2.x` -> `...208`
## • `...1.x` -> `...220`
## • `...1.y` -> `...222`
## • `...2.y` -> `...223`
## • `` -> `...232`
## • `` -> `...233`
## • `` -> `...234`
## • `` -> `...235`
## • `` -> `...236`
## • `` -> `...237`
## • `` -> `...238`
## • `` -> `...239`
## • `` -> `...240`
## • `` -> `...241`
## • `` -> `...242`
## • `` -> `...243`Full_data_all <- mutate(read_full_data, PRE_mood_mean = rowMeans(dplyr::select(read_full_data, c(B_distressed_pleasant, B_anxious_relaxed)), na.rm = TRUE)) %>%
mutate(read_full_data, POST_mood_mean = rowMeans(dplyr::select(read_full_data, c(POST_distressed_pleasant, POST_anxious_relaxed)), na.rm = TRUE)) %>%
mutate(read_full_data, W1_mood_mean = rowMeans(dplyr::select(read_full_data, c(W1_distressed_pleasant, W1_anxious_relaxed)), na.rm = TRUE)) %>%
mutate(read_full_data, M1_mood_mean = rowMeans(dplyr::select(read_full_data, c(M1_distressed_pleasant, M1_anxious_relaxed)), na.rm = TRUE)) %>%
mutate(PRE_PHQ_total = B_PHQ_1 + B_PHQ_2 + B_PHQ_3 + B_PHQ_4 + B_PHQ_5 + B_PHQ_6 + B_PHQ_7 + B_PHQ_8) %>%
mutate(W1_PHQ_total = W1_PHQ_1 + W1_PHQ_2 + W1_PHQ_3 + W1_PHQ_4 + W1_PHQ_5 + W1_PHQ_6 + W1_PHQ_7 + W1_PHQ_8)Hypothesis 1
H1a: IUS and Mood association at PRE
#Distressed
PRE_IUS_Distress_lm <- lm(PRE_IUS_mean ~ B_distressed_pleasant, data = Full_data_all)
summary(PRE_IUS_Distress_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_distressed_pleasant, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.15060 -0.48693 0.03397 0.52398 1.67796
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.707087 0.060155 61.626 < 2e-16 ***
## B_distressed_pleasant -0.004779 0.001075 -4.446 1.3e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7143 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.07143, Adjusted R-squared: 0.06782
## F-statistic: 19.77 on 1 and 257 DF, p-value: 1.301e-05anova(PRE_IUS_Distress_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_distressed_pleasant 1 10.086 10.0860 19.77 1.301e-05 ***
## Residuals 257 131.113 0.5102
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#Anxious
PRE_IUS_Anxiety_lm <- lm(PRE_IUS_mean ~ B_anxious_relaxed, data = Full_data_all)
summary(PRE_IUS_Anxiety_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_anxious_relaxed, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.19074 -0.48388 0.04329 0.48709 1.70529
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.6734224 0.0514456 71.40 < 2e-16 ***
## B_anxious_relaxed -0.0046672 0.0008516 -5.48 1.02e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.702 on 256 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.105, Adjusted R-squared: 0.1015
## F-statistic: 30.03 on 1 and 256 DF, p-value: 1.015e-07anova(PRE_IUS_Anxiety_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_anxious_relaxed 1 14.803 14.8029 30.035 1.015e-07 ***
## Residuals 256 126.171 0.4929
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#Combined
PRE_IUS_mood_lm <- lm(PRE_IUS_mean ~ PRE_mood_mean, data = Full_data_all)
summary(PRE_IUS_mood_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ PRE_mood_mean, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1107 -0.5061 0.0222 0.4967 1.7483
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.722527 0.056304 66.115 < 2e-16 ***
## PRE_mood_mean -0.005626 0.001024 -5.495 9.38e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7012 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.1052, Adjusted R-squared: 0.1017
## F-statistic: 30.2 on 1 and 257 DF, p-value: 9.378e-08anova(PRE_IUS_mood_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## PRE_mood_mean 1 14.847 14.8475 30.2 9.378e-08 ***
## Residuals 257 126.352 0.4916
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1H1a: IUS and mental health association at PRE
#Depression
PRE_IUS_PHQ_lm <- lm(PRE_IUS_mean ~ PRE_PHQ_mean, data = Full_data_all)
summary(PRE_IUS_PHQ_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ PRE_PHQ_mean, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.42097 -0.37416 0.01201 0.41236 1.84942
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.49810 0.13252 18.851 < 2e-16 ***
## PRE_PHQ_mean 0.45532 0.05578 8.162 1.48e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6605 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.2059, Adjusted R-squared: 0.2028
## F-statistic: 66.62 on 1 and 257 DF, p-value: 1.481e-14anova(PRE_IUS_PHQ_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## PRE_PHQ_mean 1 29.067 29.0666 66.619 1.481e-14 ***
## Residuals 257 112.133 0.4363
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#Anxiety
PRE_IUS_GAD_lm <- lm(PRE_IUS_mean ~ PRE_GAD_mean, data = Full_data_all)
summary(PRE_IUS_GAD_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ PRE_GAD_mean, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1136 -0.4088 0.0571 0.3468 1.7157
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.44445 0.11995 20.379 <2e-16 ***
## PRE_GAD_mean 0.48141 0.05038 9.556 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6367 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.2622, Adjusted R-squared: 0.2593
## F-statistic: 91.32 on 1 and 257 DF, p-value: < 2.2e-16anova(PRE_IUS_GAD_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## PRE_GAD_mean 1 37.018 37.018 91.319 < 2.2e-16 ***
## Residuals 257 104.181 0.405
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1H1b: IUS and BT at PRE
Hypothesis 2
H2a: difference in change in cognitive IUS over time between groups
IUS_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_IUS_mean", "POST_IUS_mean", "W1_IUS_mean", "M1_IUS_mean")## Formatting table as needed
IUS_alltimepoints_long <- IUS_alltimepoints %>%
pivot_longer(cols = c(PRE_IUS_mean, POST_IUS_mean, W1_IUS_mean, M1_IUS_mean),
names_to = "Time",
values_to = "IUS_Score")IUS_MEM <- lmer(IUS_Score ~ Group * Time + (1|ID), data = IUS_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(IUS_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: IUS_Score ~ Group * Time + (1 | ID)
## Data: IUS_alltimepoints_long
##
## REML criterion at convergence: 1657.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8184 -0.4942 -0.0149 0.4939 4.1676
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.5192 0.7206
## Residual 0.1620 0.4024
## Number of obs: 953, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.38194 0.08174 394.19467 41.372
## GroupECs 0.14436 0.14242 375.78539 1.014
## GroupIntervention -0.15521 0.11648 394.62901 -1.333
## TimePOST_IUS_mean -0.19962 0.05755 689.58626 -3.469
## TimePRE_IUS_mean 0.13045 0.05755 689.58626 2.267
## TimeW1_IUS_mean -0.02265 0.05780 689.44327 -0.392
## GroupECs:TimePOST_IUS_mean 0.07332 0.09883 688.28965 0.742
## GroupIntervention:TimePOST_IUS_mean 0.03307 0.08229 689.89671 0.402
## GroupECs:TimePRE_IUS_mean -0.23342 0.09883 688.28965 -2.362
## GroupIntervention:TimePRE_IUS_mean 0.23402 0.08203 689.63196 2.853
## GroupIntervention:TimeW1_IUS_mean 0.01233 0.08253 689.61657 0.149
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## GroupECs 0.311402
## GroupIntervention 0.183460
## TimePOST_IUS_mean 0.000555 ***
## TimePRE_IUS_mean 0.023707 *
## TimeW1_IUS_mean 0.695203
## GroupECs:TimePOST_IUS_mean 0.458433
## GroupIntervention:TimePOST_IUS_mean 0.687927
## GroupECs:TimePRE_IUS_mean 0.018461 *
## GroupIntervention:TimePRE_IUS_mean 0.004461 **
## GroupIntervention:TimeW1_IUS_mean 0.881265
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPOST_ TPRE_I TW1_IU GEC:TPO GI:TPO GEC:TPR
## GroupECs -0.421
## GrpIntrvntn -0.702 0.296
## TmPOST_IUS_ -0.379 0.001 0.266
## TmPRE_IUS_m -0.379 0.001 0.266 0.539
## TmW1_IUS_mn -0.376 -0.190 0.264 0.535 0.535
## GEC:TPOST_I 0.001 -0.355 0.000 -0.270 -0.001 0.274
## GI:TPOST_IU 0.265 0.000 -0.379 -0.699 -0.377 -0.374 0.189
## GEC:TPRE_IU 0.001 -0.355 0.000 -0.001 -0.270 0.274 0.512 0.001
## GI:TPRE_IUS 0.266 0.000 -0.380 -0.378 -0.702 -0.375 0.001 0.538 0.189
## GI:TW1_IUS_ 0.264 0.133 -0.376 -0.374 -0.374 -0.700 -0.192 0.533 -0.192
## GI:TPR
## GroupECs
## GrpIntrvntn
## TmPOST_IUS_
## TmPRE_IUS_m
## TmW1_IUS_mn
## GEC:TPOST_I
## GI:TPOST_IU
## GEC:TPRE_IU
## GI:TPRE_IUS
## GI:TW1_IUS_ 0.534
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (IUS_MEM)## Missing cells for: GroupECs:TimeM1_IUS_mean.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.2774 0.1387 2 260.39 0.8564 0.4259
## Time 9.9986 3.3329 3 688.76 20.5791 8.851e-13 ***
## Group:Time 5.6815 1.1363 5 688.33 7.0162 2.084e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(IUS_MEM)| Â | IUS Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.38 | 3.22 – 3.54 | <0.001 |
| Group [ECs] | 0.14 | -0.14 – 0.42 | 0.311 |
| Group [Intervention] | -0.16 | -0.38 – 0.07 | 0.183 |
| Time [POST_IUS_mean] | -0.20 | -0.31 – -0.09 | 0.001 |
| Time [PRE_IUS_mean] | 0.13 | 0.02 – 0.24 | 0.024 |
| Time [W1_IUS_mean] | -0.02 | -0.14 – 0.09 | 0.695 |
|
Group [ECs] × Time [POST_IUS_mean] |
0.07 | -0.12 – 0.27 | 0.458 |
|
Group [Intervention] × Time [POST_IUS_mean] |
0.03 | -0.13 – 0.19 | 0.688 |
|
Group [ECs] × Time [PRE_IUS_mean] |
-0.23 | -0.43 – -0.04 | 0.018 |
|
Group [Intervention] × Time [PRE_IUS_mean] |
0.23 | 0.07 – 0.40 | 0.004 |
|
Group [Intervention] × Time [W1_IUS_mean] |
0.01 | -0.15 – 0.17 | 0.881 |
| Random Effects | |||
| σ2 | 0.16 | ||
| Ï„00 ID | 0.52 | ||
| ICC | 0.76 | ||
| N ID | 259 | ||
| Observations | 953 | ||
| Marginal R2 / Conditional R2 | 0.037 / 0.771 | ||
parameters::standardise_parameters(IUS_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------------------
## (Intercept) | 0.05 | [-0.14, 0.24]
## GroupECs | 0.17 | [-0.16, 0.50]
## GroupIntervention | -0.18 | [-0.46, 0.09]
## TimePOST_IUS_mean | -0.24 | [-0.37, -0.10]
## TimePRE_IUS_mean | 0.16 | [ 0.02, 0.29]
## TimeW1_IUS_mean | -0.03 | [-0.16, 0.11]
## GroupECs:TimePOST_IUS_mean | 0.09 | [-0.14, 0.32]
## GroupIntervention:TimePOST_IUS_mean | 0.04 | [-0.15, 0.23]
## GroupECs:TimePRE_IUS_mean | -0.28 | [-0.51, -0.05]
## GroupIntervention:TimePRE_IUS_mean | 0.28 | [ 0.09, 0.47]
## GroupIntervention:TimeW1_IUS_mean | 0.01 | [-0.18, 0.21]Baseline to post
IUS_BP <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_IUS_mean", "POST_IUS_mean", "W1_IUS_mean", "M1_IUS_mean")## Formatting table as needed
IUS_BP_long <- IUS_BP %>%
pivot_longer(cols = c(PRE_IUS_mean, POST_IUS_mean),
names_to = "Time",
values_to = "IUS_Score")IUS_MEM_BP <- lmer(IUS_Score ~ Group * Time + (1|ID), data = IUS_BP_long, REML = TRUE)
summary(IUS_MEM_BP)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: IUS_Score ~ Group * Time + (1 | ID)
## Data: IUS_BP_long
##
## REML criterion at convergence: 1056.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.96151 -0.45865 0.00271 0.41183 2.87810
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4961 0.7043
## Residual 0.1671 0.4088
## Number of obs: 516, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.18232 0.07910 327.94825 40.232
## GroupECs 0.21768 0.13972 327.94825 1.558
## GroupIntervention -0.12034 0.11292 330.02286 -1.066
## TimePRE_IUS_mean 0.33007 0.05616 254.24574 5.878
## GroupECs:TimePRE_IUS_mean -0.30674 0.09919 254.24574 -3.092
## GroupIntervention:TimePRE_IUS_mean 0.19915 0.08035 254.80390 2.479
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## GroupECs 0.12020
## GroupIntervention 0.28736
## TimePRE_IUS_mean 1.3e-08 ***
## GroupECs:TimePRE_IUS_mean 0.00221 **
## GroupIntervention:TimePRE_IUS_mean 0.01384 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPRE_I GEC:TP
## GroupECs -0.566
## GrpIntrvntn -0.700 0.397
## TmPRE_IUS_m -0.355 0.201 0.249
## GEC:TPRE_IU 0.201 -0.355 -0.141 -0.566
## GI:TPRE_IUS 0.248 -0.140 -0.359 -0.699 0.396anova (IUS_MEM_BP)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.0711 0.0356 2 256.08 0.2127 0.8086
## Time 9.9087 9.9087 1 254.52 59.2816 3.029e-13 ***
## Group:Time 4.3147 2.1574 2 254.58 12.9071 4.580e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(IUS_MEM_BP)| Â | IUS Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.18 | 3.03 – 3.34 | <0.001 |
| Group [ECs] | 0.22 | -0.06 – 0.49 | 0.120 |
| Group [Intervention] | -0.12 | -0.34 – 0.10 | 0.287 |
| Time [PRE_IUS_mean] | 0.33 | 0.22 – 0.44 | <0.001 |
|
Group [ECs] × Time [PRE_IUS_mean] |
-0.31 | -0.50 – -0.11 | 0.002 |
|
Group [Intervention] × Time [PRE_IUS_mean] |
0.20 | 0.04 – 0.36 | 0.014 |
| Random Effects | |||
| σ2 | 0.17 | ||
| Ï„00 ID | 0.50 | ||
| ICC | 0.75 | ||
| N ID | 259 | ||
| Observations | 516 | ||
| Marginal R2 / Conditional R2 | 0.057 / 0.762 | ||
parameters::standardise_parameters(IUS_MEM_BP)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ----------------------------------------------------------------
## (Intercept) | -0.20 | [-0.39, -0.02]
## GroupECs | 0.26 | [-0.07, 0.59]
## GroupIntervention | -0.14 | [-0.41, 0.12]
## TimePRE_IUS_mean | 0.40 | [ 0.26, 0.53]
## GroupECs:TimePRE_IUS_mean | -0.37 | [-0.60, -0.13]
## GroupIntervention:TimePRE_IUS_mean | 0.24 | [ 0.05, 0.43]plot_model(IUS_MEM_BP, type = "int")
Baseline to 1W
IUS_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_IUS_mean", "W1_IUS_mean")## Formatting table as needed
IUS_B1W_long <- IUS_B1W %>%
pivot_longer(cols = c(PRE_IUS_mean, W1_IUS_mean),
names_to = "Time",
values_to = "IUS_Score")IUS_MEM_B1W <- lmer(IUS_Score ~ Group * Time + (1|ID), data = IUS_B1W_long, REML = TRUE)
summary(IUS_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: IUS_Score ~ Group * Time + (1 | ID)
## Data: IUS_B1W_long
##
## REML criterion at convergence: 1034.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.04517 -0.40088 -0.00389 0.45985 2.90184
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4460 0.6678
## Residual 0.1726 0.4155
## Number of obs: 511, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.51239 0.07639 334.66363 45.978
## GroupECs -0.08906 0.13494 334.66364 -0.660
## GroupIntervention 0.07881 0.10882 334.66364 0.724
## TimeW1_IUS_mean -0.15695 0.05754 250.26271 -2.728
## GroupECs:TimeW1_IUS_mean 0.23189 0.10228 251.14237 2.267
## GroupIntervention:TimeW1_IUS_mean -0.21486 0.08215 250.58012 -2.616
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## GroupECs 0.50970
## GroupIntervention 0.46943
## TimeW1_IUS_mean 0.00683 **
## GroupECs:TimeW1_IUS_mean 0.02424 *
## GroupIntervention:TimeW1_IUS_mean 0.00945 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_IU GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TmW1_IUS_mn -0.370 0.210 0.260
## GEC:TW1_IUS 0.208 -0.368 -0.146 -0.563
## GI:TW1_IUS_ 0.259 -0.147 -0.370 -0.700 0.394anova (IUS_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.0357 0.01784 2 256.10 0.1034 0.9018413
## Time 2.5576 2.55758 1 251.08 14.8178 0.0001503 ***
## Group:Time 3.4025 1.70123 2 250.97 9.8564 7.572e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(IUS_MEM_B1W)| Â | IUS Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.51 | 3.36 – 3.66 | <0.001 |
| Group [ECs] | -0.09 | -0.35 – 0.18 | 0.510 |
| Group [Intervention] | 0.08 | -0.13 – 0.29 | 0.469 |
| Time [W1_IUS_mean] | -0.16 | -0.27 – -0.04 | 0.007 |
|
Group [ECs] × Time [W1_IUS_mean] |
0.23 | 0.03 – 0.43 | 0.024 |
|
Group [Intervention] × Time [W1_IUS_mean] |
-0.21 | -0.38 – -0.05 | 0.009 |
| Random Effects | |||
| σ2 | 0.17 | ||
| Ï„00 ID | 0.45 | ||
| ICC | 0.72 | ||
| N ID | 259 | ||
| Observations | 511 | ||
| Marginal R2 / Conditional R2 | 0.027 / 0.728 | ||
parameters::standardise_parameters(IUS_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | 0.10 | [-0.09, 0.29]
## GroupECs | -0.11 | [-0.45, 0.22]
## GroupIntervention | 0.10 | [-0.17, 0.37]
## TimeW1_IUS_mean | -0.20 | [-0.34, -0.06]
## GroupECs:TimeW1_IUS_mean | 0.29 | [ 0.04, 0.55]
## GroupIntervention:TimeW1_IUS_mean | -0.27 | [-0.47, -0.07]plot_model(IUS_MEM_B1W, type = "int")
Baseline to 1M
IUS_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_IUS_mean", "M1_IUS_mean") %>%
filter(Group != "ECs")## Formatting table as needed
IUS_B1M_long <- IUS_B1M %>%
pivot_longer(cols = c(PRE_IUS_mean, M1_IUS_mean),
names_to = "Time",
values_to = "IUS_Score")IUS_MEM_B1M <- lmer(IUS_Score ~ Group * Time + (1|ID), data = IUS_B1M_long, REML = TRUE)
summary(IUS_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: IUS_Score ~ Group * Time + (1 | ID)
## Data: IUS_B1M_long
##
## REML criterion at convergence: 856.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.27345 -0.47467 0.03634 0.50494 2.22377
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4587 0.6772
## Residual 0.2146 0.4632
## Number of obs: 394, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.37798 0.08238 296.81398 41.007
## GroupIntervention -0.16442 0.11741 297.16435 -1.400
## TimePRE_IUS_mean 0.13441 0.06696 189.98098 2.007
## GroupIntervention:TimePRE_IUS_mean 0.24323 0.09546 190.07075 2.548
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupIntervention 0.1624
## TimePRE_IUS_mean 0.0461 *
## GroupIntervention:TimePRE_IUS_mean 0.0116 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TPRE_I
## GrpIntrvntn -0.702
## TmPRE_IUS_m -0.446 0.313
## GI:TPRE_IUS 0.313 -0.447 -0.701anova (IUS_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.0356 0.0356 1 207.51 0.1657 0.68438
## Time 6.1748 6.1748 1 190.07 28.7759 2.345e-07 ***
## Group:Time 1.3933 1.3933 1 190.07 6.4928 0.01162 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(IUS_MEM_B1M)| Â | IUS Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.38 | 3.22 – 3.54 | <0.001 |
| Group [Intervention] | -0.16 | -0.40 – 0.07 | 0.162 |
| Time [PRE_IUS_mean] | 0.13 | 0.00 – 0.27 | 0.045 |
|
Group [Intervention] × Time [PRE_IUS_mean] |
0.24 | 0.06 – 0.43 | 0.011 |
| Random Effects | |||
| σ2 | 0.21 | ||
| Ï„00 ID | 0.46 | ||
| ICC | 0.68 | ||
| N ID | 209 | ||
| Observations | 394 | ||
| Marginal R2 / Conditional R2 | 0.029 / 0.691 | ||
parameters::standardise_parameters(IUS_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.07 | [-0.26, 0.13]
## GroupIntervention | -0.20 | [-0.48, 0.08]
## TimePRE_IUS_mean | 0.16 | [ 0.00, 0.32]
## GroupIntervention:TimePRE_IUS_mean | 0.29 | [ 0.07, 0.52]plot_model(IUS_MEM_B1M, type = "int")
H2a: difference in change in growth mindsets over time between groups
GM_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "B_GM", "POST_GM", "W1_GM", "M1_GM")## Formatting table as needed
GM_alltimepoints_long <- GM_alltimepoints %>%
pivot_longer(cols = c(B_GM, POST_GM, W1_GM, M1_GM),
names_to = "Time",
values_to = "GM_Score")GM_MEM <- lmer(GM_Score ~ Group * Time + (1|ID), data = GM_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(GM_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GM_Score ~ Group * Time + (1 | ID)
## Data: GM_alltimepoints_long
##
## REML criterion at convergence: 2986.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1287 -0.4998 -0.0612 0.4345 3.8388
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 1.3135 1.1461
## Residual 0.7778 0.8819
## Number of obs: 952, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.1415 0.1405 456.4143 22.366 < 2e-16 ***
## GroupECs -0.4015 0.2481 456.4143 -1.618 0.10628
## GroupIntervention -0.2386 0.2001 456.4143 -1.193 0.23368
## TimeM1_GM -0.3899 0.1265 690.4737 -3.083 0.00213 **
## TimePOST_GM -0.4906 0.1211 685.4846 -4.050 5.72e-05 ***
## TimeW1_GM -0.3130 0.1219 686.4954 -2.568 0.01045 *
## GroupIntervention:TimeM1_GM -0.2386 0.1799 690.3615 -1.326 0.18523
## GroupECs:TimePOST_GM 0.5306 0.2140 685.4846 2.480 0.01339 *
## GroupIntervention:TimePOST_GM -0.1807 0.1731 685.8503 -1.044 0.29697
## GroupECs:TimeW1_GM 0.2394 0.2165 687.7470 1.106 0.26929
## GroupIntervention:TimeW1_GM -0.2772 0.1740 686.6940 -1.594 0.11146
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TM1_GM TPOST_ TW1_GM GI:TM1 GEC:TP GI:TPO
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TimeM1_GM -0.413 0.234 0.290
## TimePOST_GM -0.431 0.244 0.303 0.479
## TimeW1_GM -0.428 0.243 0.301 0.477 0.497
## GrpI:TM1_GM 0.290 -0.164 -0.414 -0.703 -0.337 -0.336
## GEC:TPOST_G 0.244 -0.431 -0.171 -0.271 -0.566 -0.281 0.191
## GI:TPOST_GM 0.302 -0.171 -0.430 -0.335 -0.700 -0.348 0.478 0.396
## GrEC:TW1_GM 0.241 -0.426 -0.169 -0.269 -0.280 -0.563 0.189 0.494 0.196
## GrpI:TW1_GM 0.300 -0.170 -0.428 -0.335 -0.348 -0.701 0.477 0.197 0.494
## GEC:TW
## GroupECs
## GrpIntrvntn
## TimeM1_GM
## TimePOST_GM
## TimeW1_GM
## GrpI:TM1_GM
## GEC:TPOST_G
## GI:TPOST_GM
## GrEC:TW1_GM
## GrpI:TW1_GM 0.395
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (GM_MEM)## Missing cells for: GroupECs:TimeM1_GM.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 4.6022 2.3011 2 262.56 2.9586 0.05363 .
## Time 22.7195 7.5732 3 688.74 9.7369 2.68e-06 ***
## Group:Time 10.1537 2.0307 5 687.95 2.6110 0.02375 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GM_MEM)| Â | GM Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.14 | 2.87 – 3.42 | <0.001 |
| Group [ECs] | -0.40 | -0.89 – 0.09 | 0.106 |
| Group [Intervention] | -0.24 | -0.63 – 0.15 | 0.233 |
| Time [M1_GM] | -0.39 | -0.64 – -0.14 | 0.002 |
| Time [POST_GM] | -0.49 | -0.73 – -0.25 | <0.001 |
| Time [W1_GM] | -0.31 | -0.55 – -0.07 | 0.010 |
|
Group [Intervention] × Time [M1_GM] |
-0.24 | -0.59 – 0.11 | 0.185 |
|
Group [ECs] × Time [POST_GM] |
0.53 | 0.11 – 0.95 | 0.013 |
|
Group [Intervention] × Time [POST_GM] |
-0.18 | -0.52 – 0.16 | 0.297 |
|
Group [ECs] × Time [W1_GM] |
0.24 | -0.19 – 0.66 | 0.269 |
|
Group [Intervention] × Time [W1_GM] |
-0.28 | -0.62 – 0.06 | 0.111 |
| Random Effects | |||
| σ2 | 0.78 | ||
| Ï„00 ID | 1.31 | ||
| ICC | 0.63 | ||
| N ID | 259 | ||
| Observations | 952 | ||
| Marginal R2 / Conditional R2 | 0.038 / 0.642 | ||
parameters::standardise_parameters(GM_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------------
## (Intercept) | 0.33 | [ 0.14, 0.51]
## GroupECs | -0.27 | [-0.60, 0.06]
## GroupIntervention | -0.16 | [-0.43, 0.10]
## TimeM1_GM | -0.27 | [-0.43, -0.10]
## TimePOST_GM | -0.33 | [-0.50, -0.17]
## TimeW1_GM | -0.21 | [-0.38, -0.05]
## GroupIntervention:TimeM1_GM | -0.16 | [-0.40, 0.08]
## GroupECs:TimePOST_GM | 0.36 | [ 0.08, 0.65]
## GroupIntervention:TimePOST_GM | -0.12 | [-0.35, 0.11]
## GroupECs:TimeW1_GM | 0.16 | [-0.13, 0.45]
## GroupIntervention:TimeW1_GM | -0.19 | [-0.42, 0.04]Baseline to post
GM_BP <- Full_data_all %>%
dplyr::select("ID", "Group", "B_GM", "POST_GM", "W1_GM", "M1_GM")## Formatting table as needed
GM_BP_long <- GM_BP %>%
pivot_longer(cols = c(B_GM, POST_GM),
names_to = "Time",
values_to = "GM_Score")GM_MEM_BP <- lmer(GM_Score ~ Group * Time + (1|ID), data = GM_BP_long, REML = TRUE)
summary(GM_MEM_BP)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GM_Score ~ Group * Time + (1 | ID)
## Data: GM_BP_long
##
## REML criterion at convergence: 1673.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.5473 -0.4356 -0.0320 0.4087 2.9611
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 1.471 1.2128
## Residual 0.614 0.7836
## Number of obs: 516, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.1415 0.1402 341.6189 22.400 < 2e-16 ***
## GroupECs -0.4015 0.2477 341.6189 -1.621 0.10599
## GroupIntervention -0.2386 0.1998 341.6189 -1.194 0.23319
## TimePOST_GM -0.4906 0.1076 254.5431 -4.558 8.03e-06 ***
## GroupECs:TimePOST_GM 0.5306 0.1901 254.5431 2.791 0.00566 **
## GroupIntervention:TimePOST_GM -0.1932 0.1540 255.1798 -1.255 0.21079
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPOST_ GEC:TP
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TimePOST_GM -0.384 0.217 0.269
## GEC:TPOST_G 0.217 -0.384 -0.153 -0.566
## GI:TPOST_GM 0.268 -0.152 -0.382 -0.699 0.396anova (GM_MEM_BP)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 2.0352 1.0176 2 256.34 1.6574 0.1926771
## Time 16.3667 16.3667 1 254.86 26.6558 4.9e-07 ***
## Group:Time 8.8331 4.4165 2 254.92 7.1931 0.0009142 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GM_MEM_BP)| Â | GM Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.14 | 2.87 – 3.42 | <0.001 |
| Group [ECs] | -0.40 | -0.89 – 0.09 | 0.106 |
| Group [Intervention] | -0.24 | -0.63 – 0.15 | 0.233 |
| Time [POST_GM] | -0.49 | -0.70 – -0.28 | <0.001 |
|
Group [ECs] × Time [POST_GM] |
0.53 | 0.16 – 0.90 | 0.005 |
|
Group [Intervention] × Time [POST_GM] |
-0.19 | -0.50 – 0.11 | 0.210 |
| Random Effects | |||
| σ2 | 0.61 | ||
| Ï„00 ID | 1.47 | ||
| ICC | 0.71 | ||
| N ID | 259 | ||
| Observations | 516 | ||
| Marginal R2 / Conditional R2 | 0.043 / 0.718 | ||
parameters::standardise_parameters(GM_MEM_BP)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------------
## (Intercept) | 0.27 | [ 0.09, 0.46]
## GroupECs | -0.27 | [-0.60, 0.06]
## GroupIntervention | -0.16 | [-0.43, 0.10]
## TimePOST_GM | -0.33 | [-0.48, -0.19]
## GroupECs:TimePOST_GM | 0.36 | [ 0.11, 0.61]
## GroupIntervention:TimePOST_GM | -0.13 | [-0.34, 0.07]plot_model(GM_MEM_BP, type = "int")
Baseline to 1W
GM_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "B_GM", "W1_GM")## Formatting table as needed
GM_B1W_long <- GM_B1W %>%
pivot_longer(cols = c(B_GM, W1_GM),
names_to = "Time",
values_to = "GM_Score")GM_MEM_B1W <- lmer(GM_Score ~ Group * Time + (1|ID), data = GM_B1W_long, REML = TRUE)
summary(GM_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GM_Score ~ Group * Time + (1 | ID)
## Data: GM_B1W_long
##
## REML criterion at convergence: 1747.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.2664 -0.5109 -0.1518 0.4940 2.7870
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 1.038 1.019
## Residual 1.010 1.005
## Number of obs: 511, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.1415 0.1390 403.7332 22.603 <2e-16 ***
## GroupECs -0.4015 0.2455 403.7332 -1.635 0.1027
## GroupIntervention -0.2386 0.1980 403.7332 -1.205 0.2289
## TimeW1_GM -0.3160 0.1390 251.9742 -2.273 0.0239 *
## GroupECs:TimeW1_GM 0.2376 0.2470 253.3522 0.962 0.3370
## GroupIntervention:TimeW1_GM -0.2757 0.1985 252.4706 -1.389 0.1659
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_GM GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TimeW1_GM -0.493 0.279 0.346
## GrEC:TW1_GM 0.278 -0.490 -0.195 -0.563
## GrpI:TW1_GM 0.345 -0.196 -0.492 -0.701 0.394anova (GM_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 5.0659 2.5329 2 256.72 2.5080 0.0834210 .
## Time 12.1159 12.1159 1 253.25 11.9969 0.0006256 ***
## Group:Time 4.6763 2.3381 2 253.08 2.3152 0.1008383
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GM_MEM_B1W)| Â | GM Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.14 | 2.87 – 3.41 | <0.001 |
| Group [ECs] | -0.40 | -0.88 – 0.08 | 0.103 |
| Group [Intervention] | -0.24 | -0.63 – 0.15 | 0.229 |
| Time [W1_GM] | -0.32 | -0.59 – -0.04 | 0.023 |
|
Group [ECs] × Time [W1_GM] |
0.24 | -0.25 – 0.72 | 0.337 |
|
Group [Intervention] × Time [W1_GM] |
-0.28 | -0.67 – 0.11 | 0.165 |
| Random Effects | |||
| σ2 | 1.01 | ||
| Ï„00 ID | 1.04 | ||
| ICC | 0.51 | ||
| N ID | 259 | ||
| Observations | 511 | ||
| Marginal R2 / Conditional R2 | 0.035 / 0.524 | ||
parameters::standardise_parameters(GM_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------
## (Intercept) | 0.24 | [ 0.06, 0.43]
## GroupECs | -0.28 | [-0.61, 0.06]
## GroupIntervention | -0.16 | [-0.43, 0.10]
## TimeW1_GM | -0.22 | [-0.41, -0.03]
## GroupECs:TimeW1_GM | 0.16 | [-0.17, 0.50]
## GroupIntervention:TimeW1_GM | -0.19 | [-0.46, 0.08]plot_model(GM_MEM_B1W, type = "int")
Baseline to 1M
GM_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "B_GM", "M1_GM") %>%
filter(Group != "ECs")## Formatting table as needed
GM_B1M_long <- GM_B1M %>%
pivot_longer(cols = c(B_GM, M1_GM),
names_to = "Time",
values_to = "GM_Score")GM_MEM_B1M <- lmer(GM_Score ~ Group * Time + (1|ID), data = GM_B1M_long, REML = TRUE)
summary(GM_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GM_Score ~ Group * Time + (1 | ID)
## Data: GM_B1M_long
##
## REML criterion at convergence: 1324.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.0456 -0.5260 -0.1325 0.4959 2.5974
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 1.1125 1.0547
## Residual 0.8861 0.9413
## Number of obs: 393, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.1415 0.1373 301.9454 22.879 <2e-16 ***
## GroupIntervention -0.2386 0.1956 301.9454 -1.220 0.2235
## TimeM1_GM -0.3461 0.1362 190.0981 -2.542 0.0118 *
## GroupIntervention:TimeM1_GM -0.2835 0.1937 189.8768 -1.464 0.1449
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TM1_GM
## GrpIntrvntn -0.702
## TimeM1_GM -0.447 0.314
## GrpI:TM1_GM 0.314 -0.448 -0.703anova (GM_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 4.1789 4.1789 1 205.06 4.7162 0.03103 *
## Time 22.4858 22.4858 1 189.88 25.3773 1.093e-06 ***
## Group:Time 1.8985 1.8985 1 189.88 2.1427 0.14491
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GM_MEM_B1M)| Â | GM Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.14 | 2.87 – 3.41 | <0.001 |
| Group [Intervention] | -0.24 | -0.62 – 0.15 | 0.223 |
| Time [M1_GM] | -0.35 | -0.61 – -0.08 | 0.011 |
|
Group [Intervention] × Time [M1_GM] |
-0.28 | -0.66 – 0.10 | 0.144 |
| Random Effects | |||
| σ2 | 0.89 | ||
| Ï„00 ID | 1.11 | ||
| ICC | 0.56 | ||
| N ID | 209 | ||
| Observations | 393 | ||
| Marginal R2 / Conditional R2 | 0.047 / 0.578 | ||
parameters::standardise_parameters(GM_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------
## (Intercept) | 0.24 | [ 0.06, 0.43]
## GroupIntervention | -0.17 | [-0.43, 0.10]
## TimeM1_GM | -0.24 | [-0.43, -0.05]
## GroupIntervention:TimeM1_GM | -0.20 | [-0.46, 0.07]plot_model(GM_MEM_B1M, type = "int")
Full_data_all$Group2<-Full_data_all$Group
Full_data_all$Group2[which(Full_data_all$Group2 == "Intervention")]<-1
Full_data_all$Group2[which(Full_data_all$Group2 == "Controls")]<-1
Full_data_all$Group2[which(Full_data_all$Group2 == "ECs")]<-0H2b: difference in change in PHQ over time between groups
PHQ_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "Group2", "PRE_PHQ_mean", "W1_PHQ_mean", "M1_PHQ_mean")## Formatting table as needed
PHQ_alltimepoints_long <- PHQ_alltimepoints %>%
pivot_longer(cols = c(PRE_PHQ_mean, W1_PHQ_mean, M1_PHQ_mean),
names_to = "Time",
values_to = "PHQ_Score")PHQ_MEM <- lmer(PHQ_Score ~ Group2 * Time + (1|ID), data = PHQ_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(PHQ_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PHQ_Score ~ Group2 * Time + (1 | ID)
## Data: PHQ_alltimepoints_long
##
## REML criterion at convergence: 1324.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0460 -0.5327 -0.1059 0.4691 3.1872
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.3544 0.5953
## Residual 0.2029 0.4505
## Number of obs: 695, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.15984 0.11653 527.98009 18.534 <2e-16 ***
## Group21 -0.11877 0.11888 419.99963 -0.999 0.318
## TimePRE_PHQ_mean 0.08516 0.10272 440.25297 0.829 0.408
## TimeW1_PHQ_mean 0.07325 0.04644 441.61844 1.577 0.115
## Group21:TimePRE_PHQ_mean 0.13579 0.10187 439.28076 1.333 0.183
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) Grop21 TPRE_P TW1_PH
## Group21 -0.898
## TmPRE_PHQ_m -0.542 0.438
## TmW1_PHQ_mn -0.398 0.183 0.452
## G21:TPRE_PH 0.450 -0.442 -0.899 -0.214
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (PHQ_MEM)## Missing cells for: Group20:TimeM1_PHQ_mean.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group2 0.0462 0.04617 1 290.11 0.2275 0.6337291
## Time 3.1839 1.59196 2 440.92 7.8445 0.0004491 ***
## Group2:Time 0.3606 0.36058 1 439.28 1.7768 0.1832378
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(PHQ_MEM)| Â | PHQ Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.16 | 1.93 – 2.39 | <0.001 |
| Group2 [1] | -0.12 | -0.35 – 0.11 | 0.318 |
| Time [PRE_PHQ_mean] | 0.09 | -0.12 – 0.29 | 0.407 |
| Time [W1_PHQ_mean] | 0.07 | -0.02 – 0.16 | 0.115 |
|
Group2 [1] × Time [PRE_PHQ_mean] |
0.14 | -0.06 – 0.34 | 0.183 |
| Random Effects | |||
| σ2 | 0.20 | ||
| Ï„00 ID | 0.35 | ||
| ICC | 0.64 | ||
| N ID | 259 | ||
| Observations | 695 | ||
| Marginal R2 / Conditional R2 | 0.015 / 0.641 | ||
parameters::standardise_parameters(PHQ_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------
## (Intercept) | 3.44e-03 | [-0.30, 0.31]
## Group21 | -0.16 | [-0.47, 0.15]
## TimePRE_PHQ_mean | 0.11 | [-0.15, 0.38]
## TimeW1_PHQ_mean | 0.10 | [-0.02, 0.22]
## Group21:TimePRE_PHQ_mean | 0.18 | [-0.09, 0.45]Baseline to 1W
PHQ_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_PHQ_total", "W1_PHQ_total")## Formatting table as needed
PHQ_B1W_long <- PHQ_B1W %>%
pivot_longer(cols = c(PRE_PHQ_total, W1_PHQ_total),
names_to = "Time",
values_to = "PHQ_Score")PHQ_MEM_B1W <- lmer(PHQ_Score ~ Group * Time + (1|ID), data = PHQ_B1W_long, REML = TRUE)
summary(PHQ_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PHQ_Score ~ Group * Time + (1 | ID)
## Data: PHQ_B1W_long
##
## REML criterion at convergence: 3024.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.7498 -0.4928 -0.0437 0.4378 3.1718
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 24.861 4.986
## Residual 9.841 3.137
## Number of obs: 503, groups: ID, 257
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 17.3322 0.5762 335.6547 30.079
## GroupECs 0.6278 1.0130 334.2380 0.620
## GroupIntervention 1.3737 0.8199 334.5945 1.675
## TimeW1_PHQ_total -0.6982 0.4440 248.3306 -1.573
## GroupECs:TimeW1_PHQ_total 0.5964 0.7777 247.5682 0.767
## GroupIntervention:TimeW1_PHQ_total -0.7257 0.6286 247.4411 -1.154
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.5358
## GroupIntervention 0.0948 .
## TimeW1_PHQ_total 0.1171
## GroupECs:TimeW1_PHQ_total 0.4439
## GroupIntervention:TimeW1_PHQ_total 0.2494
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_PH GEC:TW
## GroupECs -0.569
## GrpIntrvntn -0.703 0.400
## TmW1_PHQ_tt -0.373 0.212 0.262
## GEC:TW1_PHQ 0.213 -0.371 -0.149 -0.571
## GI:TW1_PHQ_ 0.263 -0.150 -0.372 -0.706 0.403anova (PHQ_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 19.772 9.886 2 255.34 1.0046 0.36764
## Time 60.628 60.628 1 247.32 6.1608 0.01373 *
## Group:Time 30.964 15.482 2 247.34 1.5732 0.20944
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(PHQ_MEM_B1W)| Â | PHQ Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 17.33 | 16.20 – 18.46 | <0.001 |
| Group [ECs] | 0.63 | -1.36 – 2.62 | 0.536 |
| Group [Intervention] | 1.37 | -0.24 – 2.98 | 0.094 |
| Time [W1_PHQ_total] | -0.70 | -1.57 – 0.17 | 0.116 |
|
Group [ECs] × Time [W1_PHQ_total] |
0.60 | -0.93 – 2.12 | 0.444 |
|
Group [Intervention] × Time [W1_PHQ_total] |
-0.73 | -1.96 – 0.51 | 0.249 |
| Random Effects | |||
| σ2 | 9.84 | ||
| Ï„00 ID | 24.86 | ||
| ICC | 0.72 | ||
| N ID | 257 | ||
| Observations | 503 | ||
| Marginal R2 / Conditional R2 | 0.014 / 0.720 | ||
parameters::standardise_parameters(PHQ_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.04 | [-0.23, 0.15]
## GroupECs | 0.11 | [-0.23, 0.44]
## GroupIntervention | 0.23 | [-0.04, 0.50]
## TimeW1_PHQ_total | -0.12 | [-0.27, 0.03]
## GroupECs:TimeW1_PHQ_total | 0.10 | [-0.16, 0.36]
## GroupIntervention:TimeW1_PHQ_total | -0.12 | [-0.33, 0.09]plot_model(PHQ_MEM_B1W, type = "int")
PHQ_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "Group2", "PRE_PHQ_mean", "W1_PHQ_mean")## Formatting table as needed
PHQ_B1W_long <- PHQ_B1W %>%
pivot_longer(cols = c(PRE_PHQ_mean, W1_PHQ_mean),
names_to = "Time",
values_to = "PHQ_Score")PHQ_MEM_B1W <- lmer(PHQ_Score ~ Group * Time + (1|ID), data = PHQ_B1W_long, REML = TRUE)
summary(PHQ_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PHQ_Score ~ Group * Time + (1 | ID)
## Data: PHQ_B1W_long
##
## REML criterion at convergence: 975.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.69711 -0.49954 -0.04314 0.44241 3.12699
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.3840 0.6197
## Residual 0.1584 0.3980
## Number of obs: 510, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.18548 0.07153 339.59681 30.553
## GroupECs 0.05952 0.12635 339.59681 0.471
## GroupIntervention 0.15530 0.10189 339.59681 1.524
## TimeW1_PHQ_mean -0.11062 0.05534 251.30616 -1.999
## GroupECs:TimeW1_PHQ_mean 0.09798 0.09810 251.81079 0.999
## GroupIntervention:TimeW1_PHQ_mean -0.07156 0.07885 251.33255 -0.908
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.6379
## GroupIntervention 0.1284
## TimeW1_PHQ_mean 0.0467 *
## GroupECs:TimeW1_PHQ_mean 0.3189
## GroupIntervention:TimeW1_PHQ_mean 0.3649
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_PH GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TmW1_PHQ_mn -0.377 0.214 0.265
## GEC:TW1_PHQ 0.213 -0.376 -0.149 -0.564
## GI:TW1_PHQ_ 0.265 -0.150 -0.377 -0.702 0.396anova (PHQ_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.28782 0.14391 2 257.38 0.9086 0.404362
## Time 1.15647 1.15647 1 251.70 7.3019 0.007357 **
## Group:Time 0.47694 0.23847 2 251.62 1.5057 0.223858
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(PHQ_MEM_B1W)| Â | PHQ Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.19 | 2.04 – 2.33 | <0.001 |
| Group [ECs] | 0.06 | -0.19 – 0.31 | 0.638 |
| Group [Intervention] | 0.16 | -0.04 – 0.36 | 0.128 |
| Time [W1_PHQ_mean] | -0.11 | -0.22 – -0.00 | 0.046 |
|
Group [ECs] × Time [W1_PHQ_mean] |
0.10 | -0.09 – 0.29 | 0.318 |
|
Group [Intervention] × Time [W1_PHQ_mean] |
-0.07 | -0.23 – 0.08 | 0.365 |
| Random Effects | |||
| σ2 | 0.16 | ||
| Ï„00 ID | 0.38 | ||
| ICC | 0.71 | ||
| N ID | 259 | ||
| Observations | 510 | ||
| Marginal R2 / Conditional R2 | 0.014 / 0.712 | ||
parameters::standardise_parameters(PHQ_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.02 | [-0.21, 0.17]
## GroupECs | 0.08 | [-0.26, 0.42]
## GroupIntervention | 0.21 | [-0.06, 0.48]
## TimeW1_PHQ_mean | -0.15 | [-0.30, 0.00]
## GroupECs:TimeW1_PHQ_mean | 0.13 | [-0.13, 0.39]
## GroupIntervention:TimeW1_PHQ_mean | -0.10 | [-0.31, 0.11]plot_model(PHQ_MEM_B1W, type = "int")
Baseline to 1M
PHQ_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_PHQ_mean", "M1_PHQ_mean") %>%
filter(Group != "ECs")## Formatting table as needed
PHQ_B1M_long <- PHQ_B1M %>%
pivot_longer(cols = c(PRE_PHQ_mean, M1_PHQ_mean),
names_to = "Time",
values_to = "PHQ_Score")PHQ_MEM_B1M <- lmer(PHQ_Score ~ Group * Time + (1|ID), data = PHQ_B1M_long, REML = TRUE)
summary(PHQ_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PHQ_Score ~ Group * Time + (1 | ID)
## Data: PHQ_B1M_long
##
## REML criterion at convergence: 839.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.55321 -0.57840 -0.09376 0.49367 2.71093
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.3182 0.5641
## Residual 0.2534 0.5034
## Number of obs: 394, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.036e+00 7.660e-02 3.273e+02 26.576
## GroupIntervention 8.969e-03 1.092e-01 3.276e+02 0.082
## TimePRE_PHQ_mean 1.498e-01 7.250e-02 1.937e+02 2.066
## GroupIntervention:TimePRE_PHQ_mean 1.463e-01 1.033e-01 1.938e+02 1.416
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupIntervention 0.9346
## TimePRE_PHQ_mean 0.0402 *
## GroupIntervention:TimePRE_PHQ_mean 0.1584
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TPRE_P
## GrpIntrvntn -0.702
## TmPRE_PHQ_m -0.516 0.362
## GI:TPRE_PHQ 0.362 -0.517 -0.701anova (PHQ_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.1951 0.1951 1 208.34 0.7699 0.3812
## Time 4.7157 4.7157 1 193.82 18.6117 2.551e-05 ***
## Group:Time 0.5080 0.5080 1 193.82 2.0048 0.1584
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(PHQ_MEM_B1M)| Â | PHQ Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.04 | 1.89 – 2.19 | <0.001 |
| Group [Intervention] | 0.01 | -0.21 – 0.22 | 0.935 |
| Time [PRE_PHQ_mean] | 0.15 | 0.01 – 0.29 | 0.040 |
|
Group [Intervention] × Time [PRE_PHQ_mean] |
0.15 | -0.06 – 0.35 | 0.158 |
| Random Effects | |||
| σ2 | 0.25 | ||
| Ï„00 ID | 0.32 | ||
| ICC | 0.56 | ||
| N ID | 209 | ||
| Observations | 394 | ||
| Marginal R2 / Conditional R2 | 0.026 / 0.568 | ||
parameters::standardise_parameters(PHQ_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.16 | [-0.35, 0.04]
## GroupIntervention | 0.01 | [-0.27, 0.29]
## TimePRE_PHQ_mean | 0.20 | [ 0.01, 0.38]
## GroupIntervention:TimePRE_PHQ_mean | 0.19 | [-0.07, 0.46]plot_model(PHQ_MEM_B1M, type = "int")
H2b: difference in change in GAD over time between groups
# Merging across timepoints
GAD_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_GAD_mean", "W1_GAD_mean", "M1_GAD_mean")## Formatting table as needed
GAD_alltimepoints_long <- GAD_alltimepoints %>%
pivot_longer(cols = c(PRE_GAD_mean, W1_GAD_mean, M1_GAD_mean),
names_to = "Time",
values_to = "GAD_Score")GAD_MEM <- lmer(GAD_Score ~ Group * Time + (1|ID), data = GAD_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(GAD_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GAD_Score ~ Group * Time + (1 | ID)
## Data: GAD_alltimepoints_long
##
## REML criterion at convergence: 1406.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9605 -0.4846 -0.0933 0.5205 3.3269
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4402 0.6635
## Residual 0.2158 0.4646
## Number of obs: 695, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.08664 0.08098 423.56297 25.766
## GroupECs 0.06505 0.14035 400.52984 0.463
## GroupIntervention -0.01647 0.11539 424.06097 -0.143
## TimePRE_GAD_mean 0.13214 0.06665 439.20039 1.983
## TimeW1_GAD_mean 0.03867 0.06715 439.16880 0.576
## GroupECs:TimePRE_GAD_mean -0.13811 0.11443 437.49827 -1.207
## GroupIntervention:TimePRE_GAD_mean 0.12479 0.09498 438.95940 1.314
## GroupIntervention:TimeW1_GAD_mean 0.08064 0.09584 439.71544 0.841
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.643
## GroupIntervention 0.887
## TimePRE_GAD_mean 0.048 *
## TimeW1_GAD_mean 0.565
## GroupECs:TimePRE_GAD_mean 0.228
## GroupIntervention:TimePRE_GAD_mean 0.190
## GroupIntervention:TimeW1_GAD_mean 0.401
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPRE_G TW1_GA GEC:TP GI:TPR
## GroupECs -0.366
## GrpIntrvntn -0.702 0.257
## TmPRE_GAD_m -0.446 0.001 0.313
## TmW1_GAD_mn -0.440 -0.224 0.309 0.535
## GEC:TPRE_GA 0.001 -0.420 -0.001 -0.268 0.275
## GI:TPRE_GAD 0.313 -0.001 -0.446 -0.702 -0.376 0.188
## GI:TW1_GAD_ 0.309 0.157 -0.442 -0.375 -0.701 -0.193 0.536
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (GAD_MEM)## Missing cells for: GroupECs:TimeM1_GAD_mean.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.09343 0.04672 2 268.71 0.2164 0.805517
## Time 2.75589 1.37795 2 438.71 6.3842 0.001849 **
## Group:Time 0.87844 0.29281 3 437.88 1.3567 0.255504
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GAD_MEM)| Â | GAD Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.09 | 1.93 – 2.25 | <0.001 |
| Group [ECs] | 0.07 | -0.21 – 0.34 | 0.643 |
| Group [Intervention] | -0.02 | -0.24 – 0.21 | 0.887 |
| Time [PRE_GAD_mean] | 0.13 | 0.00 – 0.26 | 0.048 |
| Time [W1_GAD_mean] | 0.04 | -0.09 – 0.17 | 0.565 |
|
Group [ECs] × Time [PRE_GAD_mean] |
-0.14 | -0.36 – 0.09 | 0.228 |
|
Group [Intervention] × Time [PRE_GAD_mean] |
0.12 | -0.06 – 0.31 | 0.189 |
|
Group [Intervention] × Time [W1_GAD_mean] |
0.08 | -0.11 – 0.27 | 0.400 |
| Random Effects | |||
| σ2 | 0.22 | ||
| Ï„00 ID | 0.44 | ||
| ICC | 0.67 | ||
| N ID | 259 | ||
| Observations | 695 | ||
| Marginal R2 / Conditional R2 | 0.010 / 0.674 | ||
parameters::standardise_parameters(GAD_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.11 | [-0.30, 0.09]
## GroupECs | 0.08 | [-0.26, 0.42]
## GroupIntervention | -0.02 | [-0.30, 0.26]
## TimePRE_GAD_mean | 0.16 | [ 0.00, 0.32]
## TimeW1_GAD_mean | 0.05 | [-0.11, 0.21]
## GroupECs:TimePRE_GAD_mean | -0.17 | [-0.45, 0.11]
## GroupIntervention:TimePRE_GAD_mean | 0.15 | [-0.08, 0.38]
## GroupIntervention:TimeW1_GAD_mean | 0.10 | [-0.13, 0.33]Baseline to 1W
# Merging across timepoints
GAD_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_GAD_mean", "W1_GAD_mean")## Formatting table as needed
GAD_B1W_long <- GAD_B1W %>%
pivot_longer(cols = c(PRE_GAD_mean, W1_GAD_mean),
names_to = "Time",
values_to = "GAD_Score")GAD_MEM_B1W <- lmer(GAD_Score ~ Group * Time + (1|ID), data = GAD_B1W_long, REML = TRUE)
summary(GAD_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GAD_Score ~ Group * Time + (1 | ID)
## Data: GAD_B1W_long
##
## REML criterion at convergence: 1070.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.02603 -0.45914 -0.09977 0.46957 3.16113
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4548 0.6744
## Residual 0.1934 0.4398
## Number of obs: 510, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.21878 0.07820 341.73392 28.372
## GroupECs -0.07306 0.13813 341.73392 -0.529
## GroupIntervention 0.10831 0.11140 341.73392 0.972
## TimeW1_GAD_mean -0.08987 0.06116 251.51643 -1.469
## GroupECs:TimeW1_GAD_mean 0.13424 0.10841 252.03041 1.238
## GroupIntervention:TimeW1_GAD_mean -0.04599 0.08714 251.54331 -0.528
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.597
## GroupIntervention 0.332
## TimeW1_GAD_mean 0.143
## GroupECs:TimeW1_GAD_mean 0.217
## GroupIntervention:TimeW1_GAD_mean 0.598
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_GA GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TmW1_GAD_mn -0.382 0.216 0.268
## GEC:TW1_GAD 0.215 -0.380 -0.151 -0.564
## GI:TW1_GAD_ 0.268 -0.152 -0.382 -0.702 0.396anova (GAD_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.16519 0.08259 2 257.55 0.4270 0.6530
## Time 0.40776 0.40776 1 251.92 2.1079 0.1478
## Group:Time 0.53440 0.26720 2 251.84 1.3813 0.2532sjPlot::tab_model(GAD_MEM_B1W)| Â | GAD Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.22 | 2.07 – 2.37 | <0.001 |
| Group [ECs] | -0.07 | -0.34 – 0.20 | 0.597 |
| Group [Intervention] | 0.11 | -0.11 – 0.33 | 0.331 |
| Time [W1_GAD_mean] | -0.09 | -0.21 – 0.03 | 0.142 |
|
Group [ECs] × Time [W1_GAD_mean] |
0.13 | -0.08 – 0.35 | 0.216 |
|
Group [Intervention] × Time [W1_GAD_mean] |
-0.05 | -0.22 – 0.13 | 0.598 |
| Random Effects | |||
| σ2 | 0.19 | ||
| Ï„00 ID | 0.45 | ||
| ICC | 0.70 | ||
| N ID | 259 | ||
| Observations | 510 | ||
| Marginal R2 / Conditional R2 | 0.007 / 0.704 | ||
parameters::standardise_parameters(GAD_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## --------------------------------------------------------------
## (Intercept) | 0.01 | [-0.18, 0.20]
## GroupECs | -0.09 | [-0.43, 0.25]
## GroupIntervention | 0.13 | [-0.14, 0.41]
## TimeW1_GAD_mean | -0.11 | [-0.26, 0.04]
## GroupECs:TimeW1_GAD_mean | 0.17 | [-0.10, 0.43]
## GroupIntervention:TimeW1_GAD_mean | -0.06 | [-0.27, 0.16]plot_model(GAD_MEM_B1W, type = "int")
Baseline to 1M
# Merging across timepoints
GAD_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_GAD_mean", "M1_GAD_mean") %>%
filter(Group != "ECs")## Formatting table as needed
GAD_B1M_long <- GAD_B1M %>%
pivot_longer(cols = c(PRE_GAD_mean, M1_GAD_mean),
names_to = "Time",
values_to = "GAD_Score")GAD_MEM_B1M <- lmer(GAD_Score ~ Group * Time + (1|ID), data = GAD_B1M_long, REML = TRUE)
summary(GAD_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: GAD_Score ~ Group * Time + (1 | ID)
## Data: GAD_B1M_long
##
## REML criterion at convergence: 883.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.23265 -0.51854 -0.08821 0.48051 2.70521
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4144 0.6438
## Residual 0.2584 0.5083
## Number of obs: 394, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.08869 0.08277 312.88243 25.236
## GroupIntervention -0.01302 0.11797 313.23740 -0.110
## TimePRE_GAD_mean 0.13009 0.07333 191.11893 1.774
## GroupIntervention:TimePRE_GAD_mean 0.12134 0.10454 191.22466 1.161
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupIntervention 0.9122
## TimePRE_GAD_mean 0.0777 .
## GroupIntervention:TimePRE_GAD_mean 0.2472
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TPRE_G
## GrpIntrvntn -0.702
## TmPRE_GAD_m -0.484 0.340
## GI:TPRE_GAD 0.340 -0.485 -0.701anova (GAD_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.055 0.055 1 207.16 0.2128 0.645035
## Time 3.441 3.441 1 191.22 13.3182 0.000339 ***
## Group:Time 0.348 0.348 1 191.22 1.3471 0.247234
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(GAD_MEM_B1M)| Â | GAD Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.09 | 1.93 – 2.25 | <0.001 |
| Group [Intervention] | -0.01 | -0.24 – 0.22 | 0.912 |
| Time [PRE_GAD_mean] | 0.13 | -0.01 – 0.27 | 0.077 |
|
Group [Intervention] × Time [PRE_GAD_mean] |
0.12 | -0.08 – 0.33 | 0.247 |
| Random Effects | |||
| σ2 | 0.26 | ||
| Ï„00 ID | 0.41 | ||
| ICC | 0.62 | ||
| N ID | 209 | ||
| Observations | 394 | ||
| Marginal R2 / Conditional R2 | 0.015 / 0.622 | ||
parameters::standardise_parameters(GAD_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | -0.11 | [-0.31, 0.09]
## GroupIntervention | -0.02 | [-0.30, 0.27]
## TimePRE_GAD_mean | 0.16 | [-0.02, 0.33]
## GroupIntervention:TimePRE_GAD_mean | 0.15 | [-0.10, 0.40]plot_model(GAD_MEM_B1M, type = "int")
H2b: difference in change in mood over time between groups
Mood_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_mood_mean", "POST_mood_mean", "W1_mood_mean", "M1_mood_mean")## Formatting tables as needed
Mood_alltimepoints_long <- Mood_alltimepoints %>%
pivot_longer(cols = c("PRE_mood_mean", "POST_mood_mean", "W1_mood_mean", "M1_mood_mean"),
names_to = "Time",
values_to = "Mood_Score")Mood_MEM <- lmer(Mood_Score ~ Group * Time + (1|ID), data = Mood_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(Mood_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Mood_Score ~ Group * Time + (1 | ID)
## Data: Mood_alltimepoints_long
##
## REML criterion at convergence: 9574.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9122 -0.4761 0.0583 0.5756 3.3824
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 864.6 29.40
## Residual 987.5 31.42
## Number of obs: 952, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 30.7050 4.3539 650.5155 7.052
## GroupECs -5.4729 7.4795 611.7514 -0.732
## GroupIntervention -7.8667 6.2055 651.4517 -1.268
## TimePOST_mood_mean 26.5827 4.4850 695.5235 5.927
## TimePRE_mood_mean 6.6110 4.4850 695.5235 1.474
## TimeW1_mood_mean 0.3582 4.5183 695.9519 0.079
## GroupECs:TimePOST_mood_mean -11.5348 7.7175 691.6156 -1.495
## GroupIntervention:TimePOST_mood_mean 9.6693 6.4019 695.8043 1.510
## GroupECs:TimePRE_mood_mean 8.4569 7.7175 691.6156 1.096
## GroupIntervention:TimePRE_mood_mean 0.1818 6.3922 695.4478 0.028
## GroupIntervention:TimeW1_mood_mean 1.4339 6.4554 697.1122 0.222
## Pr(>|t|)
## (Intercept) 4.51e-12 ***
## GroupECs 0.465
## GroupIntervention 0.205
## TimePOST_mood_mean 4.86e-09 ***
## TimePRE_mood_mean 0.141
## TimeW1_mood_mean 0.937
## GroupECs:TimePOST_mood_mean 0.135
## GroupIntervention:TimePOST_mood_mean 0.131
## GroupECs:TimePRE_mood_mean 0.274
## GroupIntervention:TimePRE_mood_mean 0.977
## GroupIntervention:TimeW1_mood_mean 0.824
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPOST_ TPRE__ TmW1__ GEC:TPO GI:TPO GEC:TPR
## GroupECs -0.251
## GrpIntrvntn -0.702 0.176
## TmPOST_md_m -0.553 0.001 0.388
## TmPRE_md_mn -0.553 0.001 0.388 0.537
## TimW1_md_mn -0.548 -0.285 0.384 0.532 0.532
## GEC:TPOST__ 0.001 -0.528 0.000 -0.270 -0.001 0.276
## GrI:TPOST__ 0.387 0.000 -0.553 -0.701 -0.376 -0.373 0.189
## GrEC:TPRE__ 0.001 -0.528 0.000 -0.001 -0.270 0.276 0.512 0.000
## GrpI:TPRE__ 0.388 0.000 -0.554 -0.377 -0.702 -0.373 0.000 0.537 0.189
## GrpIn:TW1__ 0.383 0.200 -0.548 -0.372 -0.372 -0.700 -0.193 0.531 -0.193
## GI:TPR
## GroupECs
## GrpIntrvntn
## TmPOST_md_m
## TmPRE_md_mn
## TimW1_md_mn
## GEC:TPOST__
## GrI:TPOST__
## GrEC:TPRE__
## GrpI:TPRE__
## GrpIn:TW1__ 0.532
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (Mood_MEM)## Missing cells for: GroupECs:TimeM1_mood_mean.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 1836 918 2 269.40 0.9294 0.396044
## Time 97492 32497 3 693.18 32.9088 < 2.2e-16 ***
## Group:Time 15771 3154 5 691.94 3.1940 0.007368 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(Mood_MEM)| Â | Mood Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 30.71 | 22.16 – 39.25 | <0.001 |
| Group [ECs] | -5.47 | -20.15 – 9.21 | 0.465 |
| Group [Intervention] | -7.87 | -20.04 – 4.31 | 0.205 |
| Time [POST_mood_mean] | 26.58 | 17.78 – 35.38 | <0.001 |
| Time [PRE_mood_mean] | 6.61 | -2.19 – 15.41 | 0.141 |
| Time [W1_mood_mean] | 0.36 | -8.51 – 9.23 | 0.937 |
|
Group [ECs] × Time [POST_mood_mean] |
-11.53 | -26.68 – 3.61 | 0.135 |
|
Group [Intervention] × Time [POST_mood_mean] |
9.67 | -2.89 – 22.23 | 0.131 |
|
Group [ECs] × Time [PRE_mood_mean] |
8.46 | -6.69 – 23.60 | 0.273 |
|
Group [Intervention] × Time [PRE_mood_mean] |
0.18 | -12.36 – 12.73 | 0.977 |
|
Group [Intervention] × Time [W1_mood_mean] |
1.43 | -11.23 – 14.10 | 0.824 |
| Random Effects | |||
| σ2 | 987.50 | ||
| Ï„00 ID | 864.62 | ||
| ICC | 0.47 | ||
| N ID | 259 | ||
| Observations | 952 | ||
| Marginal R2 / Conditional R2 | 0.077 / 0.508 | ||
parameters::standardise_parameters(Mood_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------------------
## (Intercept) | -0.13 | [-0.32, 0.06]
## GroupECs | -0.12 | [-0.45, 0.21]
## GroupIntervention | -0.18 | [-0.45, 0.10]
## TimePOST_mood_mean | 0.59 | [ 0.40, 0.79]
## TimePRE_mood_mean | 0.15 | [-0.05, 0.34]
## TimeW1_mood_mean | 8.01e-03 | [-0.19, 0.21]
## GroupECs:TimePOST_mood_mean | -0.26 | [-0.60, 0.08]
## GroupIntervention:TimePOST_mood_mean | 0.22 | [-0.06, 0.50]
## GroupECs:TimePRE_mood_mean | 0.19 | [-0.15, 0.53]
## GroupIntervention:TimePRE_mood_mean | 4.07e-03 | [-0.28, 0.28]
## GroupIntervention:TimeW1_mood_mean | 0.03 | [-0.25, 0.32]Baseline to post
Mood_BP <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_mood_mean", "POST_mood_mean")## Formatting tables as needed
Mood_BP_long <- Mood_BP %>%
pivot_longer(cols = c("PRE_mood_mean", "POST_mood_mean"),
names_to = "Time",
values_to = "Mood_Score")Mood_MEM_BP <- lmer(Mood_Score ~ Group * Time + (1|ID), data = Mood_BP_long, REML = TRUE)
summary(Mood_MEM_BP)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Mood_Score ~ Group * Time + (1 | ID)
## Data: Mood_BP_long
##
## REML criterion at convergence: 5079
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.1547 -0.3855 0.0476 0.4451 3.3781
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 1035.6 32.18
## Residual 513.4 22.66
## Number of obs: 517, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 57.288 3.823 353.535 14.986
## GroupECs -17.008 6.752 353.535 -2.519
## GroupIntervention 1.665 5.453 354.733 0.305
## TimePRE_mood_mean -19.972 3.112 255.115 -6.417
## GroupECs:TimePRE_mood_mean 19.992 5.498 255.115 3.637
## GroupIntervention:TimePRE_mood_mean -9.350 4.443 255.465 -2.105
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## GroupECs 0.012215 *
## GroupIntervention 0.760334
## TimePRE_mood_mean 6.72e-10 ***
## GroupECs:TimePRE_mood_mean 0.000334 ***
## GroupIntervention:TimePRE_mood_mean 0.036311 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPRE__ GEC:TP
## GroupECs -0.566
## GrpIntrvntn -0.701 0.397
## TmPRE_md_mn -0.407 0.230 0.285
## GrEC:TPRE__ 0.230 -0.407 -0.162 -0.566
## GrpI:TPRE__ 0.285 -0.161 -0.409 -0.701 0.397anova (Mood_MEM_BP)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 677.9 339.0 2 255.99 0.6603 0.5176
## Time 30949.7 30949.7 1 255.29 60.2843 1.989e-13 ***
## Group:Time 14453.2 7226.6 2 255.32 14.0761 1.588e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(Mood_MEM_BP)| Â | Mood Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 57.29 | 49.78 – 64.80 | <0.001 |
| Group [ECs] | -17.01 | -30.27 – -3.74 | 0.012 |
| Group [Intervention] | 1.66 | -9.05 – 12.38 | 0.760 |
| Time [PRE_mood_mean] | -19.97 | -26.09 – -13.86 | <0.001 |
|
Group [ECs] × Time [PRE_mood_mean] |
19.99 | 9.19 – 30.79 | <0.001 |
|
Group [Intervention] × Time [PRE_mood_mean] |
-9.35 | -18.08 – -0.62 | 0.036 |
| Random Effects | |||
| σ2 | 513.40 | ||
| Ï„00 ID | 1035.58 | ||
| ICC | 0.67 | ||
| N ID | 259 | ||
| Observations | 517 | ||
| Marginal R2 / Conditional R2 | 0.079 / 0.695 | ||
parameters::standardise_parameters(Mood_MEM_BP)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -----------------------------------------------------------------
## (Intercept) | 0.31 | [ 0.12, 0.49]
## GroupECs | -0.42 | [-0.74, -0.09]
## GroupIntervention | 0.04 | [-0.22, 0.30]
## TimePRE_mood_mean | -0.49 | [-0.64, -0.34]
## GroupECs:TimePRE_mood_mean | 0.49 | [ 0.23, 0.75]
## GroupIntervention:TimePRE_mood_mean | -0.23 | [-0.44, -0.02]plot_model(Mood_MEM_BP, type = "int")
Baseline to 1W
Mood_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_mood_mean", "W1_mood_mean")## Formatting tables as needed
Mood_B1W_long <- Mood_B1W %>%
pivot_longer(cols = c("PRE_mood_mean", "W1_mood_mean"),
names_to = "Time",
values_to = "Mood_Score")Mood_MEM_B1W <- lmer(Mood_Score ~ Group * Time + (1|ID), data = Mood_B1W_long, REML = TRUE)
summary(Mood_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Mood_Score ~ Group * Time + (1 | ID)
## Data: Mood_B1W_long
##
## REML criterion at convergence: 5220.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1570 -0.4429 0.1159 0.5899 2.4716
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 866.2 29.43
## Residual 1117.7 33.43
## Number of obs: 509, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 37.316 4.326 424.920 8.626 <2e-16
## GroupECs 2.984 7.641 424.920 0.390 0.696
## GroupIntervention -7.685 6.162 424.920 -1.247 0.213
## TimeW1_mood_mean -6.440 4.640 252.527 -1.388 0.166
## GroupECs:TimeW1_mood_mean -8.265 8.220 253.359 -1.005 0.316
## GroupIntervention:TimeW1_mood_mean 1.112 6.623 253.086 0.168 0.867
##
## (Intercept) ***
## GroupECs
## GroupIntervention
## TimeW1_mood_mean
## GroupECs:TimeW1_mood_mean
## GroupIntervention:TimeW1_mood_mean
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TmW1__ GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TimW1_md_mn -0.525 0.297 0.369
## GrpEC:TW1__ 0.296 -0.524 -0.208 -0.564
## GrpIn:TW1__ 0.368 -0.208 -0.524 -0.701 0.395anova (Mood_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 2236.2 1118.1 2 257.40 1.0004 0.36916
## Time 8711.4 8711.4 1 253.43 7.7944 0.00564 **
## Group:Time 1553.5 776.7 2 253.35 0.6950 0.50003
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(Mood_MEM_B1W)| Â | Mood Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 37.32 | 28.82 – 45.82 | <0.001 |
| Group [ECs] | 2.98 | -12.03 – 18.00 | 0.696 |
| Group [Intervention] | -7.68 | -19.79 – 4.42 | 0.213 |
| Time [W1_mood_mean] | -6.44 | -15.56 – 2.68 | 0.166 |
|
Group [ECs] × Time [W1_mood_mean] |
-8.26 | -24.42 – 7.89 | 0.315 |
|
Group [Intervention] × Time [W1_mood_mean] |
1.11 | -11.90 – 14.12 | 0.867 |
| Random Effects | |||
| σ2 | 1117.65 | ||
| Ï„00 ID | 866.19 | ||
| ICC | 0.44 | ||
| N ID | 259 | ||
| Observations | 509 | ||
| Marginal R2 / Conditional R2 | 0.014 / 0.445 | ||
parameters::standardise_parameters(Mood_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ---------------------------------------------------------------
## (Intercept) | 0.14 | [-0.05, 0.33]
## GroupECs | 0.07 | [-0.27, 0.40]
## GroupIntervention | -0.17 | [-0.44, 0.10]
## TimeW1_mood_mean | -0.14 | [-0.35, 0.06]
## GroupECs:TimeW1_mood_mean | -0.19 | [-0.55, 0.18]
## GroupIntervention:TimeW1_mood_mean | 0.02 | [-0.27, 0.32]plot_model(Mood_MEM_B1W, type = "int")
Baseline to 1M
Mood_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_mood_mean", "M1_mood_mean") %>%
filter(Group != "ECs")## Formatting tables as needed
Mood_B1M_long <- Mood_B1M %>%
pivot_longer(cols = c("PRE_mood_mean", "M1_mood_mean"),
names_to = "Time",
values_to = "Mood_Score")Mood_MEM_B1M <- lmer(Mood_Score ~ Group * Time + (1|ID), data = Mood_B1M_long, REML = TRUE)
summary(Mood_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Mood_Score ~ Group * Time + (1 | ID)
## Data: Mood_B1M_long
##
## REML criterion at convergence: 4072.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.84172 -0.48707 0.07157 0.59484 2.32670
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 847.4 29.11
## Residual 1235.9 35.16
## Number of obs: 394, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 30.6176 4.6634 357.1760 6.565
## GroupIntervention -7.5275 6.6483 357.4098 -1.132
## TimePRE_mood_mean 6.6984 5.0411 199.8632 1.329
## GroupIntervention:TimePRE_mood_mean -0.1574 7.1859 200.0128 -0.022
## Pr(>|t|)
## (Intercept) 1.83e-10 ***
## GroupIntervention 0.258
## TimePRE_mood_mean 0.185
## GroupIntervention:TimePRE_mood_mean 0.983
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TPRE__
## GrpIntrvntn -0.701
## TmPRE_md_mn -0.585 0.410
## GrpI:TPRE__ 0.410 -0.586 -0.702anova (Mood_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 2454.6 2454.6 1 210.79 1.9861 0.1602
## Time 4195.3 4195.3 1 200.01 3.3945 0.0669 .
## Group:Time 0.6 0.6 1 200.01 0.0005 0.9825
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(Mood_MEM_B1M)| Â | Mood Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 30.62 | 21.45 – 39.79 | <0.001 |
| Group [Intervention] | -7.53 | -20.60 – 5.54 | 0.258 |
| Time [PRE_mood_mean] | 6.70 | -3.21 – 16.61 | 0.185 |
|
Group [Intervention] × Time [PRE_mood_mean] |
-0.16 | -14.29 – 13.97 | 0.983 |
| Random Effects | |||
| σ2 | 1235.91 | ||
| Ï„00 ID | 847.37 | ||
| ICC | 0.41 | ||
| N ID | 209 | ||
| Observations | 394 | ||
| Marginal R2 / Conditional R2 | 0.012 / 0.414 | ||
parameters::standardise_parameters(Mood_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## ----------------------------------------------------------------
## (Intercept) | 5.58e-03 | [-0.19, 0.21]
## GroupIntervention | -0.16 | [-0.45, 0.12]
## TimePRE_mood_mean | 0.15 | [-0.07, 0.36]
## GroupIntervention:TimePRE_mood_mean | -3.43e-03 | [-0.31, 0.30]plot_model(Mood_MEM_B1M, type = "int")
Hypothesis 3
# Baseline to 1W/1M changes (creating new columns)
changeinvariables <- mutate(Full_data_all,
IUS_BP_change = POST_IUS_mean - PRE_IUS_mean,
IUS_B1W_change = W1_IUS_mean - PRE_IUS_mean,
IUS_B1M_change = M1_IUS_mean - PRE_IUS_mean,
PHQ_B1W_change = W1_PHQ_mean - PRE_PHQ_mean,
PHQ_B1M_change = M1_PHQ_mean - PRE_PHQ_mean,
GAD_B1W_change = W1_GAD_mean - PRE_GAD_mean,
GAD_B1M_change = M1_GAD_mean - PRE_GAD_mean,
Mood_BP_change = POST_mood_mean - PRE_mood_mean,
Mood_B1W_change = W1_mood_mean - PRE_mood_mean,
Mood_B1M_change = M1_mood_mean - PRE_mood_mean)# Separating out each group
Intervention_group <- changeinvariables %>%
filter(Group == "Intervention")
Psychoed_group <- changeinvariables %>%
filter(Group == "Controls")
ECs_group <- changeinvariables %>%
filter(Group == "ECs")H3: IUS mediating change in PHQ over time between groups
Full sample at 1 week: Group to change in PHQ via change in IUS
Mediation.PHQchange.1W <-
'#regressions
PHQ_B1W_change ~ c1 * Group
IUS_B1W_change ~ a1 * Group
PHQ_B1W_change ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.PHQ.1W <- sem(Mediation.PHQchange.1W, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.PHQ.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PHQ_B1W_change ~
## Group (c1) -0.031 0.073 -0.419 0.675 -0.031 -0.027
## IUS_B1W_change ~
## Group (a1) -0.178 0.072 -2.487 0.013 -0.178 -0.160
## PHQ_B1W_change ~
## IUS_B1W_c (b1) 0.160 0.073 2.185 0.029 0.160 0.160
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .PHQ_B1W_change 0.060 0.151 0.397 0.692 0.060 0.060
## .IUS_B1W_change 0.354 0.149 2.371 0.018 0.354 0.354
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .PHQ_B1W_change 0.968 0.125 7.768 0.000 0.968 0.972
## .IUS_B1W_change 0.970 0.120 8.068 0.000 0.970 0.974
##
## R-Square:
## Estimate
## PHQ_B1W_change 0.028
## IUS_B1W_change 0.026
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.029 0.016 -1.767 0.077 -0.029 -0.026
## direct -0.031 0.073 -0.419 0.675 -0.031 -0.027
## total -0.059 0.072 -0.816 0.415 -0.059 -0.053Intervention group at 1 week: pre PHQ to 1 week PHQ via change in IU
Mediation.PHQ.intervention.1W <-
'#regressions
W1_PHQ_mean ~ c1 * PRE_PHQ_mean
IUS_B1W_change ~ a1 * PRE_PHQ_mean
W1_PHQ_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
PHQ.IUS.intervention.1W <- sem(Mediation.PHQ.intervention.1W, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(PHQ.IUS.intervention.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_PHQ_mean ~
## PRE_PHQ_m (c1) 0.876 0.126 6.932 0.000 0.876 0.618
## IUS_B1W_change ~
## PRE_PHQ_m (a1) 0.116 0.137 0.848 0.397 0.116 0.081
## W1_PHQ_mean ~
## IUS_B1W_c (b1) 0.069 0.082 0.846 0.397 0.069 0.069
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean -2.051 0.266 -7.725 0.000 -2.051 -2.069
## .IUS_B1W_change -0.272 0.358 -0.760 0.447 -0.272 -0.273
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean 0.596 0.103 5.811 0.000 0.596 0.607
## .IUS_B1W_change 0.983 0.202 4.865 0.000 0.983 0.993
##
## R-Square:
## Estimate
## W1_PHQ_mean 0.393
## IUS_B1W_change 0.007
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.008 0.012 0.649 0.516 0.008 0.006
## direct 0.876 0.126 6.932 0.000 0.876 0.618
## total 0.884 0.126 7.001 0.000 0.884 0.623Psychoeducation group at 1 week: pre PHQ to 1 week PHQ via change in IU
Mediation.PHQ.psychoed.1W <-
'#regressions
W1_PHQ_mean ~ c1 * PRE_PHQ_mean
IUS_B1W_change ~ a1 * PRE_PHQ_mean
W1_PHQ_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
PHQ.IUS.psychoed.1W <- sem(Mediation.PHQ.psychoed.1W, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(PHQ.IUS.psychoed.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_PHQ_mean ~
## PRE_PHQ_m (c1) 0.979 0.093 10.567 0.000 0.979 0.763
## IUS_B1W_change ~
## PRE_PHQ_m (a1) -0.138 0.119 -1.159 0.246 -0.138 -0.107
## W1_PHQ_mean ~
## IUS_B1W_c (b1) 0.153 0.071 2.161 0.031 0.153 0.153
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean -2.152 0.181 -11.873 0.000 -2.152 -2.171
## .IUS_B1W_change 0.302 0.271 1.115 0.265 0.302 0.304
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean 0.413 0.071 5.817 0.000 0.413 0.420
## .IUS_B1W_change 0.979 0.154 6.359 0.000 0.979 0.989
##
## R-Square:
## Estimate
## W1_PHQ_mean 0.580
## IUS_B1W_change 0.011
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.021 0.021 -1.010 0.312 -0.021 -0.016
## direct 0.979 0.093 10.567 0.000 0.979 0.763
## total 0.958 0.097 9.925 0.000 0.958 0.746EC group at 1 week: pre PHQ to 1 week PHQ via change in IU
Mediation.PHQ.ECs.1W <-
'#regressions
W1_PHQ_mean ~ c1 * PRE_PHQ_mean
IUS_B1W_change ~ a1 * PRE_PHQ_mean
W1_PHQ_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
PHQ.IUS.ECs.1W <- sem(Mediation.PHQ.ECs.1W, data=ECs_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(PHQ.IUS.ECs.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 50
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_PHQ_mean ~
## PRE_PHQ_m (c1) 1.011 0.078 13.005 0.000 1.011 0.736
## IUS_B1W_change ~
## PRE_PHQ_m (a1) 0.397 0.137 2.900 0.004 0.397 0.287
## W1_PHQ_mean ~
## IUS_B1W_c (b1) 0.182 0.075 2.431 0.015 0.182 0.183
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean -2.280 0.174 -13.078 0.000 -2.280 -2.327
## .IUS_B1W_change -0.896 0.277 -3.239 0.001 -0.896 -0.906
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_PHQ_mean 0.333 0.093 3.582 0.000 0.333 0.347
## .IUS_B1W_change 0.896 0.187 4.789 0.000 0.896 0.918
##
## R-Square:
## Estimate
## W1_PHQ_mean 0.653
## IUS_B1W_change 0.082
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.072 0.033 2.208 0.027 0.072 0.053
## direct 1.011 0.078 13.005 0.000 1.011 0.736
## total 1.083 0.073 14.812 0.000 1.083 0.789Full sample at 1 month: Group to change in PHQ via change in IUS
Mediation.PHQchange.1M <-
'#regressions
PHQ_B1M_change ~ c1 * Group
IUS_B1M_change ~ a1 * Group
PHQ_B1M_change ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.PHQ.1M <- sem(Mediation.PHQchange.1M, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.PHQ.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PHQ_B1M_change ~
## Group (c1) -0.075 0.073 -1.030 0.303 -0.075 -0.068
## IUS_B1M_change ~
## Group (a1) -0.177 0.072 -2.447 0.014 -0.177 -0.160
## PHQ_B1M_change ~
## IUS_B1M_c (b1) 0.212 0.092 2.298 0.022 0.212 0.212
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .PHQ_B1M_change 0.150 0.168 0.893 0.372 0.150 0.150
## .IUS_B1M_change 0.350 0.154 2.269 0.023 0.350 0.352
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .PHQ_B1M_change 0.939 0.119 7.906 0.000 0.939 0.946
## .IUS_B1M_change 0.962 0.110 8.719 0.000 0.962 0.974
##
## R-Square:
## Estimate
## PHQ_B1M_change 0.054
## IUS_B1M_change 0.026
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.038 0.022 -1.674 0.094 -0.038 -0.034
## direct -0.075 0.073 -1.030 0.303 -0.075 -0.068
## total -0.113 0.073 -1.553 0.120 -0.113 -0.102Intervention group at 1 month: pre PHQ to 1 month PHQ via change in IU
Mediation.PHQ.intervention.1M <-
'#regressions
M1_PHQ_mean ~ c1 * PRE_PHQ_mean
IUS_B1M_change ~ a1 * PRE_PHQ_mean
M1_PHQ_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
PHQ.IUS.intervention.1M <- sem(Mediation.PHQ.intervention.1M, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(PHQ.IUS.intervention.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_PHQ_mean ~
## PRE_PHQ_m (c1) 0.848 0.094 9.068 0.000 0.848 0.601
## IUS_B1M_change ~
## PRE_PHQ_m (a1) 0.007 0.136 0.051 0.959 0.007 0.005
## M1_PHQ_mean ~
## IUS_B1M_c (b1) 0.156 0.101 1.541 0.123 0.156 0.157
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_PHQ_mean -1.993 0.225 -8.848 0.000 -1.993 -2.021
## .IUS_B1M_change -0.015 0.345 -0.044 0.965 -0.015 -0.015
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_PHQ_mean 0.596 0.103 5.777 0.000 0.596 0.613
## .IUS_B1M_change 0.989 0.153 6.459 0.000 0.989 1.000
##
## R-Square:
## Estimate
## M1_PHQ_mean 0.387
## IUS_B1M_change 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.001 0.021 0.051 0.959 0.001 0.001
## direct 0.848 0.094 9.068 0.000 0.848 0.601
## total 0.850 0.098 8.707 0.000 0.850 0.602Psychoeducation group at 1 month: pre PHQ to 1 month PHQ via change in IU
Mediation.PHQ.psychoed.1M <-
'#regressions
M1_PHQ_mean ~ c1 * PRE_PHQ_mean
IUS_B1M_change ~ a1 * PRE_PHQ_mean
M1_PHQ_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
PHQ.IUS.psychoed.1M <- sem(Mediation.PHQ.psychoed.1M, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(PHQ.IUS.psychoed.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_PHQ_mean ~
## PRE_PHQ_m (c1) 0.690 0.116 5.928 0.000 0.690 0.537
## IUS_B1M_change ~
## PRE_PHQ_m (a1) -0.123 0.135 -0.911 0.362 -0.123 -0.096
## M1_PHQ_mean ~
## IUS_B1M_c (b1) 0.198 0.106 1.877 0.061 0.198 0.198
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_PHQ_mean -1.490 0.247 -6.032 0.000 -1.490 -1.500
## .IUS_B1M_change 0.264 0.308 0.857 0.391 0.264 0.265
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_PHQ_mean 0.683 0.098 6.945 0.000 0.683 0.693
## .IUS_B1M_change 0.979 0.162 6.061 0.000 0.979 0.991
##
## R-Square:
## Estimate
## M1_PHQ_mean 0.307
## IUS_B1M_change 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.024 0.032 -0.768 0.442 -0.024 -0.019
## direct 0.690 0.116 5.928 0.000 0.690 0.537
## total 0.666 0.120 5.569 0.000 0.666 0.518H3: IUS mediating change in GAD over time between groups
Full sample at 1 week: Group to change in GAD via change in IUS
Mediation.GADchange.1W <-
'#regressions
GAD_B1W_change ~ c1 * Group
IUS_B1W_change ~ a1 * Group
GAD_B1W_change ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.GAD.1W <- sem(Mediation.GADchange.1W, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.GAD.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## GAD_B1W_change ~
## Group (c1) 0.006 0.074 0.084 0.933 0.006 0.006
## IUS_B1W_change ~
## Group (a1) -0.178 0.072 -2.487 0.013 -0.178 -0.160
## GAD_B1W_change ~
## IUS_B1W_c (b1) 0.217 0.078 2.798 0.005 0.217 0.217
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_B1W_change -0.013 0.155 -0.086 0.931 -0.013 -0.013
## .IUS_B1W_change 0.354 0.149 2.371 0.018 0.354 0.354
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_B1W_change 0.950 0.144 6.583 0.000 0.950 0.953
## .IUS_B1W_change 0.970 0.120 8.068 0.000 0.970 0.974
##
## R-Square:
## Estimate
## GAD_B1W_change 0.047
## IUS_B1W_change 0.026
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.039 0.021 -1.829 0.067 -0.039 -0.035
## direct 0.006 0.074 0.084 0.933 0.006 0.006
## total -0.032 0.074 -0.441 0.659 -0.032 -0.029Intervention group at 1 week: pre GAD to 1 week GAD via change in IU
Mediation.GAD.intervention.1W <-
'#regressions
W1_GAD_mean ~ c1 * PRE_GAD_mean
IUS_B1W_change ~ a1 * PRE_GAD_mean
W1_GAD_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
GAD.IUS.intervention.1W <- sem(Mediation.GAD.intervention.1W, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(GAD.IUS.intervention.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_GAD_mean ~
## PRE_GAD_m (c1) 0.835 0.104 8.048 0.000 0.835 0.654
## IUS_B1W_change ~
## PRE_GAD_m (a1) 0.018 0.135 0.137 0.891 0.018 0.014
## W1_GAD_mean ~
## IUS_B1W_c (b1) 0.095 0.095 1.002 0.316 0.095 0.095
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean -1.941 0.211 -9.191 0.000 -1.941 -1.958
## .IUS_B1W_change -0.043 0.345 -0.124 0.901 -0.043 -0.043
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean 0.551 0.111 4.972 0.000 0.551 0.561
## .IUS_B1W_change 0.990 0.206 4.814 0.000 0.990 1.000
##
## R-Square:
## Estimate
## W1_GAD_mean 0.439
## IUS_B1W_change 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.002 0.012 0.141 0.888 0.002 0.001
## direct 0.835 0.104 8.048 0.000 0.835 0.654
## total 0.837 0.104 8.015 0.000 0.837 0.656Psychoeducation group at 1 week: pre GAD to 1 week GAD via change in IU
Mediation.GAD.psychoed.1W <-
'#regressions
W1_GAD_mean ~ c1 * PRE_GAD_mean
IUS_B1W_change ~ a1 * PRE_GAD_mean
W1_GAD_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
GAD.IUS.psychoed.1W <- sem(Mediation.GAD.psychoed.1W, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(GAD.IUS.psychoed.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_GAD_mean ~
## PRE_GAD_m (c1) 0.873 0.082 10.652 0.000 0.873 0.731
## IUS_B1W_change ~
## PRE_GAD_m (a1) -0.113 0.108 -1.043 0.297 -0.113 -0.094
## W1_GAD_mean ~
## IUS_B1W_c (b1) 0.173 0.052 3.338 0.001 0.173 0.174
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean -1.944 0.180 -10.801 0.000 -1.944 -1.964
## .IUS_B1W_change 0.251 0.260 0.966 0.334 0.251 0.253
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean 0.450 0.099 4.540 0.000 0.450 0.460
## .IUS_B1W_change 0.981 0.155 6.334 0.000 0.981 0.991
##
## R-Square:
## Estimate
## W1_GAD_mean 0.540
## IUS_B1W_change 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.020 0.019 -1.025 0.305 -0.020 -0.016
## direct 0.873 0.082 10.652 0.000 0.873 0.731
## total 0.853 0.086 9.923 0.000 0.853 0.714EC group at 1 week: pre GAD to 1 week GAD via change in IU
Mediation.GAD.ECs.1W <-
'#regressions
W1_GAD_mean ~ c1 * PRE_GAD_mean
IUS_B1W_change ~ a1 * PRE_GAD_mean
W1_GAD_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
GAD.IUS.ECs.1W <- sem(Mediation.GAD.ECs.1W, data=ECs_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(GAD.IUS.ECs.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 25 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 50
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_GAD_mean ~
## PRE_GAD_m (c1) 1.092 0.099 11.020 0.000 1.092 0.765
## IUS_B1W_change ~
## PRE_GAD_m (a1) 0.218 0.170 1.281 0.200 0.218 0.151
## W1_GAD_mean ~
## IUS_B1W_c (b1) 0.230 0.068 3.390 0.001 0.230 0.232
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean -2.353 0.196 -11.991 0.000 -2.353 -2.404
## .IUS_B1W_change -0.470 0.355 -1.322 0.186 -0.470 -0.475
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_GAD_mean 0.294 0.066 4.479 0.000 0.294 0.307
## .IUS_B1W_change 0.956 0.202 4.732 0.000 0.956 0.977
##
## R-Square:
## Estimate
## W1_GAD_mean 0.693
## IUS_B1W_change 0.023
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.050 0.039 1.279 0.201 0.050 0.035
## direct 1.092 0.099 11.020 0.000 1.092 0.765
## total 1.142 0.101 11.286 0.000 1.142 0.800Full sample at 1 month: Group to change in GAD via change in IUS
Mediation.GADchange.1M <-
'#regressions
GAD_B1M_change ~ c1 * Group
IUS_B1M_change ~ a1 * Group
GAD_B1M_change ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.GAD.1M <- sem(Mediation.GADchange.1M, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.GAD.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## GAD_B1M_change ~
## Group (c1) -0.046 0.073 -0.633 0.527 -0.046 -0.042
## IUS_B1M_change ~
## Group (a1) -0.176 0.072 -2.439 0.015 -0.176 -0.159
## GAD_B1M_change ~
## IUS_B1M_c (b1) 0.314 0.097 3.224 0.001 0.314 0.313
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_B1M_change 0.093 0.168 0.552 0.581 0.093 0.093
## .IUS_B1M_change 0.347 0.154 2.256 0.024 0.347 0.350
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_B1M_change 0.890 0.111 8.009 0.000 0.890 0.896
## .IUS_B1M_change 0.962 0.110 8.720 0.000 0.962 0.975
##
## R-Square:
## Estimate
## GAD_B1M_change 0.104
## IUS_B1M_change 0.025
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.055 0.029 -1.897 0.058 -0.055 -0.050
## direct -0.046 0.073 -0.633 0.527 -0.046 -0.042
## total -0.102 0.073 -1.396 0.163 -0.102 -0.092Intervention group at 1 month: pre GAD to 1 month GAD via change in IU
Mediation.GAD.intervention.1M <-
'#regressions
M1_GAD_mean ~ c1 * PRE_GAD_mean
IUS_B1M_change ~ a1 * PRE_GAD_mean
M1_GAD_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
GAD.IUS.intervention.1M <- sem(Mediation.GAD.intervention.1M, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(GAD.IUS.intervention.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_GAD_mean ~
## PRE_GAD_m (c1) 0.835 0.088 9.506 0.000 0.835 0.659
## IUS_B1M_change ~
## PRE_GAD_m (a1) -0.010 0.131 -0.074 0.941 -0.010 -0.008
## M1_GAD_mean ~
## IUS_B1M_c (b1) 0.219 0.098 2.227 0.026 0.219 0.221
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_GAD_mean -1.961 0.192 -10.194 0.000 -1.961 -1.994
## .IUS_B1M_change 0.024 0.323 0.074 0.941 0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_GAD_mean 0.502 0.084 5.954 0.000 0.502 0.518
## .IUS_B1M_change 0.988 0.154 6.435 0.000 0.988 1.000
##
## R-Square:
## Estimate
## M1_GAD_mean 0.482
## IUS_B1M_change 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.002 0.029 -0.073 0.942 -0.002 -0.002
## direct 0.835 0.088 9.506 0.000 0.835 0.659
## total 0.833 0.091 9.114 0.000 0.833 0.658Psychoeducation group at 1 month: pre GAD to 1 month GAD via change in IU
Mediation.GAD.psychoed.1M <-
'#regressions
M1_GAD_mean ~ c1 * PRE_GAD_mean
IUS_B1M_change ~ a1 * PRE_GAD_mean
M1_GAD_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
GAD.IUS.psychoed.1M <- sem(Mediation.GAD.psychoed.1M, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(GAD.IUS.psychoed.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_GAD_mean ~
## PRE_GAD_m (c1) 0.702 0.093 7.565 0.000 0.702 0.582
## IUS_B1M_change ~
## PRE_GAD_m (a1) -0.022 0.129 -0.173 0.862 -0.022 -0.019
## M1_GAD_mean ~
## IUS_B1M_c (b1) 0.318 0.098 3.241 0.001 0.318 0.316
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_GAD_mean -1.524 0.196 -7.759 0.000 -1.524 -1.526
## .IUS_B1M_change 0.043 0.299 0.143 0.886 0.043 0.043
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_GAD_mean 0.567 0.089 6.348 0.000 0.567 0.568
## .IUS_B1M_change 0.988 0.167 5.927 0.000 0.988 1.000
##
## R-Square:
## Estimate
## M1_GAD_mean 0.432
## IUS_B1M_change 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.007 0.041 -0.171 0.864 -0.007 -0.006
## direct 0.702 0.093 7.565 0.000 0.702 0.582
## total 0.695 0.106 6.545 0.000 0.695 0.576H3: IUS mediating change in mood over time between groups
Full sample at post: Group to change in mood via change in IUS
Mediation.Moodchange.post <-
'#regressions
Mood_BP_change ~ c1 * Group
IUS_BP_change ~ a1 * Group
Mood_BP_change ~ b1*IUS_BP_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.Mood.post <- sem(Mediation.Moodchange.post, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.Mood.post, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Mood_BP_change ~
## Group (c1) 0.086 0.070 1.226 0.220 0.086 0.077
## IUS_BP_change ~
## Group (a1) -0.162 0.070 -2.302 0.021 -0.162 -0.145
## Mood_BP_change ~
## IUS_BP_ch (b1) -0.323 0.068 -4.736 0.000 -0.323 -0.323
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_BP_change -0.170 0.146 -1.164 0.244 -0.170 -0.170
## .IUS_BP_change 0.321 0.138 2.327 0.020 0.321 0.321
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_BP_change 0.879 0.148 5.935 0.000 0.879 0.883
## .IUS_BP_change 0.975 0.123 7.932 0.000 0.975 0.979
##
## R-Square:
## Estimate
## Mood_BP_change 0.117
## IUS_BP_change 0.021
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.052 0.023 2.243 0.025 0.052 0.047
## direct 0.086 0.070 1.226 0.220 0.086 0.077
## total 0.138 0.071 1.944 0.052 0.138 0.124Intervention group at post: pre mood to post mood via change in IU
Mediation.Mood.intervention.post <-
'#regressions
POST_mood_mean ~ c1 * PRE_mood_mean
IUS_BP_change ~ a1 * PRE_mood_mean
POST_mood_mean ~ b1*IUS_BP_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.intervention.post <- sem(Mediation.Mood.intervention.post, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.intervention.post, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## POST_mood_mean ~
## PRE_md_mn (c1) 0.014 0.003 4.726 0.000 0.014 0.607
## IUS_BP_change ~
## PRE_md_mn (a1) 0.002 0.002 0.933 0.351 0.002 0.098
## POST_mood_mean ~
## IUS_BP_ch (b1) -0.181 0.080 -2.254 0.024 -0.181 -0.181
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean -0.416 0.148 -2.810 0.005 -0.416 -0.418
## .IUS_BP_change -0.065 0.108 -0.603 0.546 -0.065 -0.066
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean 0.613 0.128 4.800 0.000 0.613 0.620
## .IUS_BP_change 0.980 0.183 5.351 0.000 0.980 0.990
##
## R-Square:
## Estimate
## POST_mood_mean 0.380
## IUS_BP_change 0.010
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.000 0.001 -0.825 0.409 -0.000 -0.018
## direct 0.014 0.003 4.726 0.000 0.014 0.607
## total 0.014 0.003 4.731 0.000 0.014 0.589Psychoeducation group at post: pre mood to post mood via change in IU
Mediation.Mood.psychoed.post <-
'#regressions
POST_mood_mean ~ c1 * PRE_mood_mean
IUS_BP_change ~ a1 * PRE_mood_mean
POST_mood_mean ~ b1*IUS_BP_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.psychoed.post <- sem(Mediation.Mood.psychoed.post, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.psychoed.post, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 22 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 1
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## POST_mood_mean ~
## PRE_md_mn (c1) 0.016 0.002 8.366 0.000 0.016 0.702
## IUS_BP_change ~
## PRE_md_mn (a1) 0.002 0.002 0.862 0.389 0.002 0.084
## POST_mood_mean ~
## IUS_BP_ch (b1) -0.276 0.069 -3.986 0.000 -0.276 -0.276
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean -0.595 0.114 -5.231 0.000 -0.595 -0.598
## .IUS_BP_change -0.071 0.139 -0.511 0.609 -0.071 -0.071
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean 0.460 0.074 6.193 0.000 0.460 0.464
## .IUS_BP_change 0.984 0.192 5.136 0.000 0.984 0.993
##
## R-Square:
## Estimate
## POST_mood_mean 0.536
## IUS_BP_change 0.007
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.001 0.001 -0.792 0.429 -0.001 -0.023
## direct 0.016 0.002 8.366 0.000 0.016 0.702
## total 0.015 0.002 7.039 0.000 0.015 0.679EC group at post: pre mood to post mood via change in IU
Mediation.Mood.ECs.post <-
'#regressions
POST_mood_mean ~ c1 * PRE_mood_mean
IUS_BP_change ~ a1 * PRE_mood_mean
POST_mood_mean ~ b1*IUS_BP_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.ECs.post <- sem(Mediation.Mood.ECs.post, data=ECs_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.ECs.post, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 25 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 50
## Number of missing patterns 1
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## POST_mood_mean ~
## PRE_md_mn (c1) 0.022 0.002 13.400 0.000 0.022 0.868
## IUS_BP_change ~
## PRE_md_mn (a1) 0.001 0.003 0.236 0.814 0.001 0.025
## POST_mood_mean ~
## IUS_BP_ch (b1) -0.063 0.060 -1.052 0.293 -0.063 -0.063
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean -0.895 0.104 -8.601 0.000 -0.895 -0.904
## .IUS_BP_change -0.026 0.178 -0.147 0.883 -0.026 -0.026
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .POST_mood_mean 0.240 0.063 3.801 0.000 0.240 0.245
## .IUS_BP_change 0.979 0.226 4.336 0.000 0.979 0.999
##
## R-Square:
## Estimate
## POST_mood_mean 0.755
## IUS_BP_change 0.001
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.000 0.000 -0.231 0.817 -0.000 -0.002
## direct 0.022 0.002 13.400 0.000 0.022 0.868
## total 0.022 0.002 13.364 0.000 0.022 0.866Full sample at 1 week: Group to change in mood via change in IUS
Mediation.Moodchange.1W <-
'#regressions
Mood_B1W_change ~ c1 * Group
IUS_B1W_change ~ a1 * Group
Mood_B1W_change ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.Mood.1W <- sem(Mediation.Moodchange.1W, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.Mood.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Mood_B1W_change ~
## Group (c1) -0.030 0.074 -0.400 0.689 -0.030 -0.027
## IUS_B1W_change ~
## Group (a1) -0.178 0.072 -2.487 0.013 -0.178 -0.160
## Mood_B1W_change ~
## IUS_B1W_c (b1) -0.201 0.071 -2.812 0.005 -0.201 -0.201
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_B1W_chang 0.061 0.161 0.375 0.708 0.061 0.061
## .IUS_B1W_change 0.354 0.149 2.371 0.018 0.354 0.354
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_B1W_chang 0.957 0.116 8.240 0.000 0.957 0.961
## .IUS_B1W_change 0.970 0.120 8.068 0.000 0.970 0.974
##
## R-Square:
## Estimate
## Mood_B1W_chang 0.039
## IUS_B1W_change 0.026
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.036 0.017 2.128 0.033 0.036 0.032
## direct -0.030 0.074 -0.400 0.689 -0.030 -0.027
## total 0.006 0.072 0.086 0.931 0.006 0.006Intervention group at 1 week: pre mood to 1 week mood via change in IU
Mediation.Mood.intervention.1W <-
'#regressions
W1_mood_mean ~ c1 * PRE_mood_mean
IUS_B1W_change ~ a1 * PRE_mood_mean
W1_mood_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.intervention.1W <- sem(Mediation.Mood.intervention.1W, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.intervention.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_mood_mean ~
## PRE_md_mn (c1) 0.011 0.002 4.441 0.000 0.011 0.458
## IUS_B1W_change ~
## PRE_md_mn (a1) 0.000 0.002 0.143 0.886 0.000 0.015
## W1_mood_mean ~
## IUS_B1W_c (b1) -0.115 0.097 -1.183 0.237 -0.115 -0.115
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean -0.323 0.109 -2.958 0.003 -0.323 -0.325
## .IUS_B1W_change -0.011 0.095 -0.111 0.912 -0.011 -0.011
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean 0.768 0.155 4.945 0.000 0.768 0.779
## .IUS_B1W_change 0.990 0.207 4.777 0.000 0.990 1.000
##
## R-Square:
## Estimate
## W1_mood_mean 0.221
## IUS_B1W_change 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.000 0.000 -0.145 0.885 -0.000 -0.002
## direct 0.011 0.002 4.441 0.000 0.011 0.458
## total 0.011 0.002 4.294 0.000 0.011 0.456Psychoeducation group at 1 week: pre mood to 1 week mood via change in IU
Mediation.Mood.psychoed.1W <-
'#regressions
W1_mood_mean ~ c1 * PRE_mood_mean
IUS_B1W_change ~ a1 * PRE_mood_mean
W1_mood_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.psychoed.1W <- sem(Mediation.Mood.psychoed.1W, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.psychoed.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 3
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_mood_mean ~
## PRE_md_mn (c1) 0.010 0.002 4.750 0.000 0.010 0.459
## IUS_B1W_change ~
## PRE_md_mn (a1) 0.004 0.002 1.598 0.110 0.004 0.167
## W1_mood_mean ~
## IUS_B1W_c (b1) -0.200 0.092 -2.159 0.031 -0.200 -0.200
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean -0.385 0.132 -2.912 0.004 -0.385 -0.387
## .IUS_B1W_change -0.139 0.148 -0.938 0.348 -0.139 -0.140
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean 0.769 0.120 6.418 0.000 0.769 0.780
## .IUS_B1W_change 0.963 0.149 6.456 0.000 0.963 0.972
##
## R-Square:
## Estimate
## W1_mood_mean 0.220
## IUS_B1W_change 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.001 0.001 -1.212 0.225 -0.001 -0.033
## direct 0.010 0.002 4.750 0.000 0.010 0.459
## total 0.010 0.002 4.062 0.000 0.010 0.426EC group at 1 week: pre mood to 1 week mood via change in IU
Mediation.Mood.ECs.1W <-
'#regressions
W1_mood_mean ~ c1 * PRE_mood_mean
IUS_B1W_change ~ a1 * PRE_mood_mean
W1_mood_mean ~ b1*IUS_B1W_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.ECs.1W <- sem(Mediation.Mood.ECs.1W, data=ECs_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.ECs.1W, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 50
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W1_mood_mean ~
## PRE_md_mn (c1) 0.011 0.003 3.198 0.001 0.011 0.435
## IUS_B1W_change ~
## PRE_md_mn (a1) 0.006 0.003 2.161 0.031 0.006 0.249
## W1_mood_mean ~
## IUS_B1W_c (b1) -0.042 0.130 -0.320 0.749 -0.042 -0.042
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean -0.447 0.181 -2.475 0.013 -0.447 -0.454
## .IUS_B1W_change -0.257 0.179 -1.431 0.152 -0.257 -0.260
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W1_mood_mean 0.795 0.129 6.163 0.000 0.795 0.818
## .IUS_B1W_change 0.916 0.188 4.880 0.000 0.916 0.938
##
## R-Square:
## Estimate
## W1_mood_mean 0.182
## IUS_B1W_change 0.062
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.000 0.001 -0.313 0.754 -0.000 -0.010
## direct 0.011 0.003 3.198 0.001 0.011 0.435
## total 0.011 0.003 3.237 0.001 0.011 0.425Full sample at 1 month: Group to change in mood via change in IUS
Mediation.Moodchange.1M <-
'#regressions
Mood_B1M_change ~ c1 * Group
IUS_B1M_change ~ a1 * Group
Mood_B1M_change ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
group.IUS.Mood.1M <- sem(Mediation.Moodchange.1M, data=changeinvariables, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: 3 cases were deleted due to missing values in
## exogenous variable(s), while fixed.x = TRUE.summary(group.IUS.Mood.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 259 262
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Mood_B1M_change ~
## Group (c1) -0.049 0.075 -0.646 0.519 -0.049 -0.044
## IUS_B1M_change ~
## Group (a1) -0.179 0.072 -2.473 0.013 -0.179 -0.161
## Mood_B1M_change ~
## IUS_B1M_c (b1) -0.253 0.090 -2.831 0.005 -0.253 -0.253
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_B1M_chang 0.095 0.167 0.569 0.569 0.095 0.096
## .IUS_B1M_change 0.351 0.154 2.276 0.023 0.351 0.353
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Mood_B1M_chang 0.933 0.114 8.206 0.000 0.933 0.938
## .IUS_B1M_change 0.963 0.110 8.721 0.000 0.963 0.974
##
## R-Square:
## Estimate
## Mood_B1M_chang 0.062
## IUS_B1M_change 0.026
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 0.045 0.022 2.011 0.044 0.045 0.041
## direct -0.049 0.075 -0.646 0.519 -0.049 -0.044
## total -0.003 0.073 -0.044 0.965 -0.003 -0.003Intervention group at 1 month: pre mood to 1 month mood via change in IU
Mediation.Mood.intervention.1M <-
'#regressions
M1_mood_mean ~ c1 * PRE_mood_mean
IUS_B1M_change ~ a1 * PRE_mood_mean
M1_mood_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.intervention.1M <- sem(Mediation.Mood.intervention.1M, data=Intervention_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.intervention.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 103
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_mood_mean ~
## PRE_md_mn (c1) 0.010 0.002 4.132 0.000 0.010 0.417
## IUS_B1M_change ~
## PRE_md_mn (a1) 0.002 0.002 0.860 0.390 0.002 0.082
## M1_mood_mean ~
## IUS_B1M_c (b1) -0.204 0.092 -2.223 0.026 -0.204 -0.205
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_mood_mean -0.290 0.115 -2.531 0.011 -0.290 -0.293
## .IUS_B1M_change -0.061 0.111 -0.551 0.581 -0.061 -0.062
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_mood_mean 0.784 0.138 5.673 0.000 0.784 0.798
## .IUS_B1M_change 0.983 0.154 6.363 0.000 0.983 0.993
##
## R-Square:
## Estimate
## M1_mood_mean 0.202
## IUS_B1M_change 0.007
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.000 0.001 -0.747 0.455 -0.000 -0.017
## direct 0.010 0.002 4.132 0.000 0.010 0.417
## total 0.009 0.002 3.802 0.000 0.009 0.400Psychoeducation group at 1 month: pre mood to 1 month mood via change in IU
Mediation.Mood.psychoed.1M <-
'#regressions
M1_mood_mean ~ c1 * PRE_mood_mean
IUS_B1M_change ~ a1 * PRE_mood_mean
M1_mood_mean ~ b1*IUS_B1M_change
indirect1 := a1 * b1
direct := c1
total := c1 + (a1 * b1)
'
Mood.IUS.psychoed.1M <- sem(Mediation.Mood.psychoed.1M, data=Psychoed_group, std.lv=T, std.ov=T, missing='fiml', se='robust', estimator='mlr', auto.var = T)
summary(Mood.IUS.psychoed.1M, standardized=T, rsquare=T)## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 106
## Number of missing patterns 4
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1_mood_mean ~
## PRE_md_mn (c1) 0.010 0.002 4.988 0.000 0.010 0.444
## IUS_B1M_change ~
## PRE_md_mn (a1) 0.003 0.002 1.162 0.245 0.003 0.128
## M1_mood_mean ~
## IUS_B1M_c (b1) -0.209 0.106 -1.981 0.048 -0.209 -0.210
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_mood_mean -0.368 0.122 -3.008 0.003 -0.368 -0.372
## .IUS_B1M_change -0.110 0.142 -0.777 0.437 -0.110 -0.111
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1_mood_mean 0.764 0.092 8.285 0.000 0.764 0.782
## .IUS_B1M_change 0.971 0.159 6.127 0.000 0.971 0.984
##
## R-Square:
## Estimate
## M1_mood_mean 0.218
## IUS_B1M_change 0.016
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect1 -0.001 0.001 -0.841 0.400 -0.001 -0.027
## direct 0.010 0.002 4.988 0.000 0.010 0.444
## total 0.009 0.002 4.152 0.000 0.009 0.418Exploratory analyses
E1: Growth mindsets moderating the association between group and PHQ changes across time
# 1 week
moderation_GM_PHQ_1W <- lm(PHQ_B1W_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_PHQ_1W)##
## Call:
## lm(formula = PHQ_B1W_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.26964 -0.28340 0.05757 0.34160 1.55997
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.19467 0.13328 -1.461 0.145
## GroupECs -0.08329 0.22250 -0.374 0.708
## GroupIntervention 0.14585 0.18964 0.769 0.443
## B_GM 0.02577 0.03854 0.669 0.504
## GroupECs:B_GM 0.06963 0.06937 1.004 0.316
## GroupIntervention:B_GM -0.07115 0.05679 -1.253 0.211
##
## Residual standard error: 0.5622 on 245 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.02877, Adjusted R-squared: 0.008945
## F-statistic: 1.451 on 5 and 245 DF, p-value: 0.2066anova(moderation_GM_PHQ_1W)## Analysis of Variance Table
##
## Response: PHQ_B1W_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 2 0.913 0.45669 1.4451 0.2377
## B_GM 1 0.081 0.08117 0.2568 0.6128
## Group:B_GM 2 1.299 0.64939 2.0548 0.1303
## Residuals 245 77.429 0.31604# 1 month
moderation_GM_PHQ_1M <- lm(PHQ_B1M_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_PHQ_1M)##
## Call:
## lm(formula = PHQ_B1M_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1147 -0.3524 0.0226 0.4099 2.4417
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.35353 0.18223 -1.940 0.0539 .
## GroupIntervention 0.06814 0.25254 0.270 0.7876
## B_GM 0.06864 0.05310 1.293 0.1978
## GroupIntervention:B_GM -0.07362 0.07681 -0.958 0.3391
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7148 on 181 degrees of freedom
## (77 observations deleted due to missingness)
## Multiple R-squared: 0.02182, Adjusted R-squared: 0.005611
## F-statistic: 1.346 on 3 and 181 DF, p-value: 0.2609anova(moderation_GM_PHQ_1M)## Analysis of Variance Table
##
## Response: PHQ_B1M_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 1 1.205 1.20540 2.3592 0.1263
## B_GM 1 0.389 0.38854 0.7605 0.3843
## Group:B_GM 1 0.469 0.46937 0.9187 0.3391
## Residuals 181 92.479 0.51093E1: Growth mindsets moderating the association between group and GAD changes across time
# 1 week
moderation_GM_GAD_1W <- lm(GAD_B1W_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_GAD_1W)##
## Call:
## lm(formula = GAD_B1W_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6688 -0.2771 0.0372 0.2975 2.0876
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.12790 0.14686 0.871 0.3847
## GroupECs -0.33642 0.24517 -1.372 0.1713
## GroupIntervention -0.11471 0.20896 -0.549 0.5835
## B_GM -0.06983 0.04246 -1.645 0.1013
## GroupECs:B_GM 0.16081 0.07644 2.104 0.0364 *
## GroupIntervention:B_GM 0.01944 0.06258 0.311 0.7563
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6195 on 245 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.034, Adjusted R-squared: 0.01429
## F-statistic: 1.725 on 5 and 245 DF, p-value: 0.1295anova(moderation_GM_GAD_1W)## Analysis of Variance Table
##
## Response: GAD_B1W_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 2 1.024 0.51189 1.3340 0.26533
## B_GM 1 0.483 0.48273 1.2580 0.26313
## Group:B_GM 2 1.803 0.90129 2.3488 0.09763 .
## Residuals 245 94.014 0.38373
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# 1 month
moderation_GM_PHQ_1M <- lm(GAD_B1M_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_PHQ_1M)##
## Call:
## lm(formula = GAD_B1M_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.3509 -0.3953 0.1163 0.3634 2.3634
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.17441 0.18391 -0.948 0.344
## GroupIntervention 0.06139 0.25487 0.241 0.810
## B_GM 0.01935 0.05359 0.361 0.718
## GroupIntervention:B_GM -0.07083 0.07752 -0.914 0.362
##
## Residual standard error: 0.7214 on 181 degrees of freedom
## (77 observations deleted due to missingness)
## Multiple R-squared: 0.01559, Adjusted R-squared: -0.0007304
## F-statistic: 0.9552 on 3 and 181 DF, p-value: 0.4152anova(moderation_GM_PHQ_1M)## Analysis of Variance Table
##
## Response: GAD_B1M_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 1 0.984 0.98388 1.8906 0.1708
## B_GM 1 0.073 0.07296 0.1402 0.7085
## Group:B_GM 1 0.434 0.43448 0.8349 0.3621
## Residuals 181 94.193 0.52041E1: Growth mindsets moderating the association between group and mood changes across time
# post
moderation_GM_mood_BP <- lm(Mood_BP_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_mood_BP)##
## Call:
## lm(formula = Mood_BP_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -72.57 -19.14 -3.97 15.23 171.32
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.2623 7.5685 3.074 0.00235 **
## GroupECs -31.6421 12.6179 -2.508 0.01278 *
## GroupIntervention 7.2041 10.6547 0.676 0.49957
## B_GM -1.0475 2.1943 -0.477 0.63353
## GroupECs:B_GM 4.0985 3.9542 1.036 0.30097
## GroupIntervention:B_GM 0.6891 3.2076 0.215 0.83007
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 32.17 on 252 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.1039, Adjusted R-squared: 0.08617
## F-statistic: 5.847 on 5 and 252 DF, p-value: 3.945e-05anova(moderation_GM_mood_BP)## Analysis of Variance Table
##
## Response: Mood_BP_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 2 29097 14548.3 14.0609 1.625e-06 ***
## B_GM 1 0 0.0 0.0000 0.9988
## Group:B_GM 2 1150 575.1 0.5558 0.5743
## Residuals 252 260736 1034.7
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# 1 week
moderation_GM_mood_1W <- lm(Mood_B1W_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_mood_1W)##
## Call:
## lm(formula = Mood_B1W_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -185.320 -23.963 2.028 25.016 185.316
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.3130 11.2877 0.028 0.978
## GroupECs -15.5416 18.8441 -0.825 0.410
## GroupIntervention 0.8914 16.0669 0.055 0.956
## B_GM -2.1258 3.2638 -0.651 0.515
## GroupECs:B_GM 2.3073 5.8749 0.393 0.695
## GroupIntervention:B_GM -0.2204 4.8097 -0.046 0.963
##
## Residual standard error: 47.61 on 244 degrees of freedom
## (12 observations deleted due to missingness)
## Multiple R-squared: 0.00881, Adjusted R-squared: -0.0115
## F-statistic: 0.4338 on 5 and 244 DF, p-value: 0.8248anova(moderation_GM_mood_1W)## Analysis of Variance Table
##
## Response: Mood_B1W_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 2 2952 1476.0 0.6511 0.5224
## B_GM 1 1516 1515.6 0.6686 0.4143
## Group:B_GM 2 449 224.5 0.0990 0.9057
## Residuals 244 553135 2266.9# 1 month
moderation_GM_mood_1W <- lm(Mood_B1M_change ~ Group*B_GM, data = changeinvariables)
summary(moderation_GM_mood_1W)##
## Call:
## lm(formula = Mood_B1M_change ~ Group * B_GM, data = changeinvariables)
##
## Residuals:
## Min 1Q Median 3Q Max
## -150.984 -27.840 3.612 26.586 183.538
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.407 12.840 -0.187 0.851
## GroupIntervention -14.301 17.795 -0.804 0.423
## B_GM -1.226 3.742 -0.328 0.744
## GroupIntervention:B_GM 4.774 5.413 0.882 0.379
##
## Residual standard error: 50.37 on 181 degrees of freedom
## (77 observations deleted due to missingness)
## Multiple R-squared: 0.005127, Adjusted R-squared: -0.01136
## F-statistic: 0.3109 on 3 and 181 DF, p-value: 0.8175anova(moderation_GM_mood_1W)## Analysis of Variance Table
##
## Response: Mood_B1M_change
## Df Sum Sq Mean Sq F value Pr(>F)
## Group 1 6 5.81 0.0023 0.9619
## B_GM 1 387 386.58 0.1524 0.6967
## Group:B_GM 1 1974 1973.85 0.7781 0.3789
## Residuals 181 459164 2536.82E2: Association between IUS and baseline functional impairment
# Total FI scale
PRE_IUS_FI_lm <- lm(PRE_IUS_mean ~ PRE_FI_mean, data = Full_data_all)
summary(PRE_IUS_FI_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ PRE_FI_mean, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.65716 -0.35317 0.03226 0.41609 1.29993
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.85416 0.14999 12.36 <2e-16 ***
## PRE_FI_mean 0.54292 0.04715 11.51 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.602 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.3403, Adjusted R-squared: 0.3377
## F-statistic: 132.6 on 1 and 257 DF, p-value: < 2.2e-16anova(PRE_IUS_FI_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## PRE_FI_mean 1 48.049 48.049 132.57 < 2.2e-16 ***
## Residuals 257 93.150 0.362
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Friends item
PRE_IUS_friends_lm <- lm(PRE_IUS_mean ~ B_FI_friends, data = Full_data_all)
summary(PRE_IUS_friends_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_FI_friends, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.23660 -0.41867 0.04736 0.49799 1.59674
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.7891 0.1163 23.983 < 2e-16 ***
## B_FI_friends 0.2654 0.0390 6.805 7.12e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6833 on 256 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.1532, Adjusted R-squared: 0.1499
## F-statistic: 46.31 on 1 and 256 DF, p-value: 7.115e-11anova(PRE_IUS_friends_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_FI_friends 1 21.623 21.6233 46.313 7.115e-11 ***
## Residuals 256 119.526 0.4669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Strangers item
PRE_IUS_strangers_lm <- lm(PRE_IUS_mean ~ B_FI_strangers, data = Full_data_all)
summary(PRE_IUS_strangers_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_FI_strangers, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.32537 -0.41938 0.08596 0.58062 1.67997
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.89268 0.14461 20.003 < 2e-16 ***
## B_FI_strangers 0.17201 0.03746 4.592 6.88e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7133 on 256 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.07611, Adjusted R-squared: 0.0725
## F-statistic: 21.09 on 1 and 256 DF, p-value: 6.881e-06anova(PRE_IUS_strangers_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_FI_strangers 1 10.729 10.7295 21.089 6.881e-06 ***
## Residuals 256 130.245 0.5088
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Work item
PRE_IUS_work_lm <- lm(PRE_IUS_mean ~ B_FI_work, data = Full_data_all)
summary(PRE_IUS_work_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_FI_work, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.75679 -0.36400 -0.00679 0.48724 1.57058
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.50081 0.12127 20.621 <2e-16 ***
## B_FI_work 0.33930 0.03772 8.996 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6443 on 243 degrees of freedom
## (17 observations deleted due to missingness)
## Multiple R-squared: 0.2498, Adjusted R-squared: 0.2468
## F-statistic: 80.93 on 1 and 243 DF, p-value: < 2.2e-16anova(PRE_IUS_work_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_FI_work 1 33.60 33.600 80.931 < 2.2e-16 ***
## Residuals 243 100.89 0.415
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Education item
PRE_IUS_education_lm <- lm(PRE_IUS_mean ~ B_FI_education, data = Full_data_all)
summary(PRE_IUS_education_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_FI_education, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.91386 -0.42064 -0.00397 0.49433 1.49942
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.74380 0.11511 23.836 < 2e-16 ***
## B_FI_education 0.25339 0.03499 7.241 5.53e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6806 on 249 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.1739, Adjusted R-squared: 0.1706
## F-statistic: 52.43 on 1 and 249 DF, p-value: 5.534e-12anova(PRE_IUS_education_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_FI_education 1 24.291 24.2910 52.432 5.534e-12 ***
## Residuals 249 115.358 0.4633
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Hobbies item
PRE_IUS_hobbies_lm <- lm(PRE_IUS_mean ~ B_FI_hobbies, data = Full_data_all)
summary(PRE_IUS_hobbies_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_FI_hobbies, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.95109 -0.46329 0.00824 0.44931 1.46558
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.76816 0.10692 25.889 < 2e-16 ***
## B_FI_hobbies 0.26627 0.03461 7.693 3.12e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6692 on 256 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.1878, Adjusted R-squared: 0.1846
## F-statistic: 59.18 on 1 and 256 DF, p-value: 3.115e-13anova(PRE_IUS_hobbies_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_FI_hobbies 1 26.502 26.5015 59.176 3.115e-13 ***
## Residuals 256 114.647 0.4478
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1E2: Change in functional impairment over time across groups
# Merging across timepoints
FI_alltimepoints <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_FI_mean", "W1_FI_mean", "M1_FI_mean")## Formatting table as needed
FI_alltimepoints_long <- FI_alltimepoints %>%
pivot_longer(cols = c(PRE_FI_mean, W1_FI_mean, M1_FI_mean),
names_to = "Time",
values_to = "FI_Score")FI_MEM <- lmer(FI_Score ~ Group * Time + (1|ID), data = FI_alltimepoints_long, REML = TRUE)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientsummary(FI_MEM)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: FI_Score ~ Group * Time + (1 | ID)
## Data: FI_alltimepoints_long
##
## REML criterion at convergence: 1462.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1207 -0.5483 -0.0128 0.4985 3.6880
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4039 0.6355
## Residual 0.2515 0.5015
## Number of obs: 696, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.900304 0.081284 455.421328 35.681
## GroupECs -0.005739 0.140467 429.427211 -0.041
## GroupIntervention 0.001562 0.115645 454.287081 0.014
## TimePRE_FI_mean 0.144980 0.071898 441.298219 2.016
## TimeW1_FI_mean 0.096852 0.072443 441.328529 1.337
## GroupECs:TimePRE_FI_mean -0.067544 0.123472 439.067166 -0.547
## GroupIntervention:TimePRE_FI_mean 0.122249 0.102257 440.789575 1.196
## GroupIntervention:TimeW1_FI_mean -0.047668 0.103177 441.702755 -0.462
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.9674
## GroupIntervention 0.9892
## TimePRE_FI_mean 0.0444 *
## TimeW1_FI_mean 0.1819
## GroupECs:TimePRE_FI_mean 0.5846
## GroupIntervention:TimePRE_FI_mean 0.2325
## GroupIntervention:TimeW1_FI_mean 0.6443
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TPRE_F TW1_FI GEC:TP GI:TPR
## GroupECs -0.335
## GrpIntrvntn -0.703 0.235
## TmPRE_FI_mn -0.479 0.001 0.336
## TimW1_FI_mn -0.473 -0.242 0.332 0.535
## GEC:TPRE_FI 0.001 -0.452 -0.001 -0.269 0.275
## GI:TPRE_FI_ 0.336 -0.001 -0.477 -0.703 -0.376 0.189
## GrI:TW1_FI_ 0.332 0.170 -0.472 -0.375 -0.702 -0.193 0.534
## fit warnings:
## fixed-effect model matrix is rank deficient so dropping 1 column / coefficientanova (FI_MEM)## Missing cells for: GroupECs:TimeM1_FI_mean.
## Interpret type III hypotheses with care.## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.0842 0.04211 2 270.90 0.1674 0.845917
## Time 3.1983 1.59915 2 440.51 6.3583 0.001896 **
## Group:Time 1.2338 0.41126 3 439.56 1.6352 0.180500
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(FI_MEM)| Â | FI Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.90 | 2.74 – 3.06 | <0.001 |
| Group [ECs] | -0.01 | -0.28 – 0.27 | 0.967 |
| Group [Intervention] | 0.00 | -0.23 – 0.23 | 0.989 |
| Time [PRE_FI_mean] | 0.14 | 0.00 – 0.29 | 0.044 |
| Time [W1_FI_mean] | 0.10 | -0.05 – 0.24 | 0.182 |
|
Group [ECs] × Time [PRE_FI_mean] |
-0.07 | -0.31 – 0.17 | 0.585 |
|
Group [Intervention] × Time [PRE_FI_mean] |
0.12 | -0.08 – 0.32 | 0.232 |
|
Group [Intervention] × Time [W1_FI_mean] |
-0.05 | -0.25 – 0.15 | 0.644 |
| Random Effects | |||
| σ2 | 0.25 | ||
| Ï„00 ID | 0.40 | ||
| ICC | 0.62 | ||
| N ID | 259 | ||
| Observations | 696 | ||
| Marginal R2 / Conditional R2 | 0.011 / 0.621 | ||
parameters::standardise_parameters(FI_MEM)## fixed-effect model matrix is rank deficient so dropping 1 column / coefficient## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## --------------------------------------------------------------
## (Intercept) | -0.12 | [-0.31, 0.08]
## GroupECs | -7.05e-03 | [-0.35, 0.33]
## GroupIntervention | 1.92e-03 | [-0.28, 0.28]
## TimePRE_FI_mean | 0.18 | [ 0.00, 0.35]
## TimeW1_FI_mean | 0.12 | [-0.06, 0.29]
## GroupECs:TimePRE_FI_mean | -0.08 | [-0.38, 0.21]
## GroupIntervention:TimePRE_FI_mean | 0.15 | [-0.10, 0.40]
## GroupIntervention:TimeW1_FI_mean | -0.06 | [-0.31, 0.19]Baseline to 1W
# Merging across timepoints
FI_B1W <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_FI_mean", "W1_FI_mean")## Formatting table as needed
FI_B1W_long <- FI_B1W %>%
pivot_longer(cols = c(PRE_FI_mean, W1_FI_mean),
names_to = "Time",
values_to = "FI_Score")FI_MEM_B1W <- lmer(FI_Score ~ Group * Time + (1|ID), data = FI_B1W_long, REML = TRUE)
summary(FI_MEM_B1W)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: FI_Score ~ Group * Time + (1 | ID)
## Data: FI_B1W_long
##
## REML criterion at convergence: 1123
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.8980 -0.5129 0.0173 0.4814 2.6754
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.3742 0.6117
## Residual 0.2617 0.5115
## Number of obs: 510, groups: ID, 259
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.04528 0.07745 376.89895 39.319
## GroupECs -0.07328 0.13681 376.89895 -0.536
## GroupIntervention 0.12381 0.11033 376.89895 1.122
## TimeW1_FI_mean -0.05100 0.07107 251.29934 -0.718
## GroupECs:TimeW1_FI_mean 0.07062 0.12596 251.96627 0.561
## GroupIntervention:TimeW1_FI_mean -0.16399 0.10126 251.33420 -1.620
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupECs 0.592
## GroupIntervention 0.262
## TimeW1_FI_mean 0.474
## GroupECs:TimeW1_FI_mean 0.576
## GroupIntervention:TimeW1_FI_mean 0.107
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpECs GrpInt TW1_FI GEC:TW
## GroupECs -0.566
## GrpIntrvntn -0.702 0.397
## TimW1_FI_mn -0.448 0.254 0.315
## GEC:TW1_FI_ 0.253 -0.447 -0.178 -0.564
## GrI:TW1_FI_ 0.315 -0.178 -0.448 -0.702 0.396anova (FI_MEM_B1W)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.11820 0.05910 2 256.53 0.2259 0.79799
## Time 0.75402 0.75402 1 251.82 2.8815 0.09084 .
## Group:Time 1.13482 0.56741 2 251.72 2.1684 0.11650
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(FI_MEM_B1W)| Â | FI Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 3.05 | 2.89 – 3.20 | <0.001 |
| Group [ECs] | -0.07 | -0.34 – 0.20 | 0.592 |
| Group [Intervention] | 0.12 | -0.09 – 0.34 | 0.262 |
| Time [W1_FI_mean] | -0.05 | -0.19 – 0.09 | 0.473 |
|
Group [ECs] × Time [W1_FI_mean] |
0.07 | -0.18 – 0.32 | 0.575 |
|
Group [Intervention] × Time [W1_FI_mean] |
-0.16 | -0.36 – 0.03 | 0.106 |
| Random Effects | |||
| σ2 | 0.26 | ||
| Ï„00 ID | 0.37 | ||
| ICC | 0.59 | ||
| N ID | 259 | ||
| Observations | 510 | ||
| Marginal R2 / Conditional R2 | 0.009 / 0.592 | ||
parameters::standardise_parameters(FI_MEM_B1W)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## -------------------------------------------------------------
## (Intercept) | 0.02 | [-0.17, 0.21]
## GroupECs | -0.09 | [-0.43, 0.25]
## GroupIntervention | 0.16 | [-0.12, 0.43]
## TimeW1_FI_mean | -0.06 | [-0.24, 0.11]
## GroupECs:TimeW1_FI_mean | 0.09 | [-0.22, 0.40]
## GroupIntervention:TimeW1_FI_mean | -0.21 | [-0.45, 0.04]plot_model(FI_MEM_B1W, type = "int")
Baseline to 1M
# Merging across timepoints
FI_B1M <- Full_data_all %>%
dplyr::select("ID", "Group", "PRE_FI_mean", "M1_FI_mean") %>%
filter(Group != "ECs")## Formatting table as needed
FI_B1M_long <- FI_B1M %>%
pivot_longer(cols = c(PRE_FI_mean, M1_FI_mean),
names_to = "Time",
values_to = "FI_Score")FI_MEM_B1M <- lmer(FI_Score ~ Group * Time + (1|ID), data = FI_B1M_long, REML = TRUE)
summary(FI_MEM_B1M)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: FI_Score ~ Group * Time + (1 | ID)
## Data: FI_B1M_long
##
## REML criterion at convergence: 883.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.32969 -0.49758 -0.02208 0.50334 2.38286
##
## Random effects:
## Groups Name Variance Std.Dev.
## ID (Intercept) 0.4394 0.6629
## Residual 0.2468 0.4968
## Number of obs: 395, groups: ID, 209
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.89481 0.08344 308.07801 34.695
## GroupIntervention 0.01564 0.11872 307.39282 0.132
## TimePRE_FI_mean 0.15048 0.07173 192.57954 2.098
## GroupIntervention:TimePRE_FI_mean 0.10817 0.10202 192.38577 1.060
## Pr(>|t|)
## (Intercept) <2e-16 ***
## GroupIntervention 0.8953
## TimePRE_FI_mean 0.0372 *
## GroupIntervention:TimePRE_FI_mean 0.2903
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) GrpInt TPRE_F
## GrpIntrvntn -0.703
## TmPRE_FI_mn -0.471 0.331
## GI:TPRE_FI_ 0.331 -0.469 -0.703anova (FI_MEM_B1M)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## Group 0.1090 0.1090 1 208.15 0.4414 0.5072
## Time 3.9698 3.9698 1 192.39 16.0821 8.674e-05 ***
## Group:Time 0.2775 0.2775 1 192.39 1.1242 0.2903
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1sjPlot::tab_model(FI_MEM_B1M)| Â | FI Score | ||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 2.89 | 2.73 – 3.06 | <0.001 |
| Group [Intervention] | 0.02 | -0.22 – 0.25 | 0.895 |
| Time [PRE_FI_mean] | 0.15 | 0.01 – 0.29 | 0.037 |
|
Group [Intervention] × Time [PRE_FI_mean] |
0.11 | -0.09 – 0.31 | 0.290 |
| Random Effects | |||
| σ2 | 0.25 | ||
| Ï„00 ID | 0.44 | ||
| ICC | 0.64 | ||
| N ID | 209 | ||
| Observations | 395 | ||
| Marginal R2 / Conditional R2 | 0.018 / 0.647 | ||
parameters::standardise_parameters(FI_MEM_B1M)## # Standardization method: refit
##
## Parameter | Std. Coef. | 95% CI
## --------------------------------------------------------------
## (Intercept) | -0.14 | [-0.33, 0.06]
## GroupIntervention | 0.02 | [-0.26, 0.30]
## TimePRE_FI_mean | 0.18 | [ 0.01, 0.35]
## GroupIntervention:TimePRE_FI_mean | 0.13 | [-0.11, 0.37]plot_model(FI_MEM_B1M, type = "int")
Extra exploratory: IUS and GM association at PRE
PRE_IUS_GM_lm <- lm(PRE_IUS_mean ~ B_GM, data = Full_data_all)
summary(PRE_IUS_GM_lm)##
## Call:
## lm(formula = PRE_IUS_mean ~ B_GM, data = Full_data_all)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.74527 -0.49697 0.07004 0.52106 1.50303
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.23064 0.10622 30.416 <2e-16 ***
## B_GM 0.09966 0.03237 3.079 0.0023 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7279 on 257 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.03558, Adjusted R-squared: 0.03182
## F-statistic: 9.48 on 1 and 257 DF, p-value: 0.002302anova(PRE_IUS_GM_lm)## Analysis of Variance Table
##
## Response: PRE_IUS_mean
## Df Sum Sq Mean Sq F value Pr(>F)
## B_GM 1 5.023 5.0232 9.4801 0.002302 **
## Residuals 257 136.176 0.5299
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1