Load required packages: (tidyverse; lme4; lmSupport; cowplot; performance; see)
Load dataframe: timescale 350; offset 5-30
setwd("C:/Users/pkmon/Desktop/TLCC_baseline_check")
d = read.csv('timescale_350_offset_5-30_bin_1.csv')
d = d[which(d$Date!='2'),] # remove 6 hr data
File formatting and DF cleaning
d$treatment = varRecode(d$Treatment, c('No Oxytocin','Oxytocin'), c('saline','oxytocin'))
d$treatment_num = varRecode(d$treatment, c('saline','oxytocin'), c(0,1))
d$treatment_C = varRecode(d$treatment_num, c(0,1), c(-.5,.5))
d$hr = varRecode(d$Date, c(1,3,4,5), c(0,24,48,168))
d$hr_C = d$hr - mean(d$hr)
d$correlation = d$Correlation
d = select(d, -MousePair_ZhiminLabel_Original, -Treatment, -Date, -Bin, - Correlation) # remove old columns
Curiosity - general summary statistics
grand_mean = mean(d$correlation)
print(grand_mean) # 'Baseline' synchrony is about 0.14
## [1] 0.1417341
hourly_mean = aggregate(correlation ~ hr, data=d, FUN=mean)
print(hourly_mean)
## hr correlation
## 1 0 0.1376716
## 2 24 0.1511825
## 3 48 0.1417210
## 4 168 0.1363612
treatment_mean = aggregate(correlation ~ treatment, data=d, FUN=mean)
print(treatment_mean)
## treatment correlation
## 1 oxytocin 0.1348256
## 2 saline 0.1486425
hourly_mean_by_treatment = aggregate(correlation ~ hr * treatment, data=d, FUN=mean)
print(hourly_mean_by_treatment)
## hr treatment correlation
## 1 0 oxytocin 0.1253660
## 2 24 oxytocin 0.1468504
## 3 48 oxytocin 0.1343879
## 4 168 oxytocin 0.1326982
## 5 0 saline 0.1499772
## 6 24 saline 0.1555146
## 7 48 saline 0.1490541
## 8 168 saline 0.1400242
Method 1: full repeated measures (though the random effects are a little confusing in this case, because it’s round-robin so not independent)
m1 = lmer(correlation ~ treatment_C * hr_C + (1|subject) + (1|shuffle) + (1|hr_C), data = d)
modelSummary(m1)
## lmer(formula = correlation ~ treatment_C * hr_C + (1 | subject) +
## (1 | shuffle) + (1 | hr_C), data = d)
## Observations: 576; Groups: subject, 18
##
## Observations: 576; Groups: shuffle, 18
##
## Observations: 576; Groups: hr_C, 4
##
## Linear mixed model fit by REML
##
## Fixed Effects:
## Estimate SE F error df Pr(>F)
## (Intercept) 1.417e-01 7.113e-03 396.994 18.14 8.81e-14 ***
## treatment_C -1.382e-02 1.246e-02 1.230 29.36 0.2765
## hr_C -4.050e-05 5.666e-05 0.511 2.00 0.5489
## treatment_C:hr_C 7.024e-05 3.932e-05 3.192 538.00 0.0746 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## NOTE: F, error df, and p-values from Kenward-Roger approximation
##
## Random Effects:
## Groups Name Std.Dev.
## subject (Intercept) 0.0178245
## shuffle (Intercept) 0.0187567
## hr_C (Intercept) 0.0068678
## Residual 0.0304878
## Warning in deviance.merMod(Model): deviance() is deprecated for REML fits; use
## REMLcrit for the REML criterion or deviance(.,REML=FALSE) for deviance
## calculated at the REML fit
##
## AIC: -2229.6; BIC: -2194.7; logLik: 1122.8; Deviance: -2245.6
# A repeated measures framework for the random shuffle doesn't show a significant difference between groups, time points, or their interactions
Version 2: aggregated baseline per pair (average all the measurements per pair per timepoint)
d_aggregate = d %>%
group_by(subject, hr) %>%
summarise(
average_correlation = mean(correlation, na.rm = TRUE),
hr = first(hr),
hr_C = first(hr_C),
treatment = first(treatment),
treatment_C = first(treatment_C),
.groups = 'drop'
)
m2 = lmer(average_correlation ~ treatment_C * hr_C + (1|subject) + (1|hr_C), data = d_aggregate)
modelSummary(m2)
## lmer(formula = average_correlation ~ treatment_C * hr_C + (1 |
## subject) + (1 | hr_C), data = d_aggregate)
## Observations: 72; Groups: subject, 18
##
## Observations: 72; Groups: hr_C, 4
##
## Linear mixed model fit by REML
##
## Fixed Effects:
## Estimate SE F error df Pr(>F)
## (Intercept) 1.417e-01 5.027e-03 794.849 6.044 1.21e-07 ***
## treatment_C -1.382e-02 7.941e-03 3.027 16.000 0.101
## hr_C -4.050e-05 5.666e-05 0.511 2.000 0.549
## treatment_C:hr_C 7.024e-05 6.110e-05 1.322 50.000 0.256
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## NOTE: F, error df, and p-values from Kenward-Roger approximation
##
## Random Effects:
## Groups Name Std.Dev.
## subject (Intercept) 0.0146161
## hr_C (Intercept) 0.0061669
## Residual 0.0167518
## Warning in deviance.merMod(Model): deviance() is deprecated for REML fits; use
## REMLcrit for the REML criterion or deviance(.,REML=FALSE) for deviance
## calculated at the REML fit
##
## AIC: -293.3; BIC: -277.4; logLik: 153.7; Deviance: -307.3
# A repeated measures framework for the aggregated random shuffle doesn't show a significant difference between groups, time points, or their interactions
Model assumptions/performance for m2
model_performance(m2)
check_model(m2)
Plotting the aggregate (m2)
plot =
ggplot(aes(x = hr, y = average_correlation, group = as.factor(treatment), fill = as.factor(treatment)), data = d_aggregate) +
geom_point(aes(colour = as.factor(treatment)), data = d_aggregate)+
stat_smooth(method = "lm", formula = y ~ x, geom = "smooth", aes(colour = as.factor(treatment)), linewidth = .5, linetype = 1, fullrange = TRUE)+
scale_y_continuous(expand = c(0,0), limits = c(0.05,.25), breaks = seq(from = 0.05, to = .25, by = .05))+
scale_x_continuous(expand = c(0,0), limits = c(-6,174), breaks = seq(from = 0, to = 168, by = 24))+
scale_colour_brewer(palette = "Dark2")+
scale_fill_brewer(palette = "Dark2") +
ylab("Correlation (Pearson's r)")+
xlab("Hours following pairing")+
theme_cowplot()+
theme(legend.title = element_blank())+
ggtitle("TLCC BASELINE RANDOM | TS=350s; OS=5-30s")
print(plot)
plot_MeanLine = plot +
geom_hline(yintercept = grand_mean, linetype = 2, linewidth = .75)
print(plot_MeanLine)
plot_Time_no_treatment =
ggplot(aes(x = hr, y = average_correlation), data = d_aggregate) +
geom_point()+
stat_smooth(method = "lm", formula = y ~ x, geom = "smooth", linewidth = 1, linetype = 1, fullrange = TRUE)+
scale_y_continuous(expand = c(0,0), limits = c(0.05,.25), breaks = seq(from = 0.05, to = .25, by = .05))+
scale_x_continuous(expand = c(0,0), limits = c(-6,174), breaks = seq(from = 0, to = 168, by = 24))+
geom_hline(yintercept = grand_mean, linetype = 2, linewidth = .75)+
scale_colour_brewer(palette = "Dark2")+
scale_fill_brewer(palette = "Dark2") +
ylab("Correlation (Pearson's r)")+
xlab("Hours following pairing")+
theme_cowplot()+
theme(legend.title = element_blank())+
ggtitle("TLCC BASELINE RANDOM | TS=350s; OS=5-30s")
print(plot_Time_no_treatment)
plot_Time_no_treatment_v2 =
ggplot(aes(x = hr, y = average_correlation), data = d_aggregate) +
geom_point(aes(colour = as.factor(treatment)), data = d_aggregate)+
stat_smooth(method = "lm", formula = y ~ x, geom = "smooth", linewidth = .5, linetype = 2, colour = "black", fullrange = TRUE)+
geom_line(aes(x = hr, y = average_correlation, colour = as.factor(treatment), group = subject), data = d_aggregate,linetype = 1, linewidth=.3, alpha = .2) +
scale_y_continuous(expand = c(0,0), limits = c(0.05,.25), breaks = seq(from = 0.05, to = .25, by = .05))+
scale_x_continuous(expand = c(0,0), limits = c(-6,174), breaks = seq(from = 0, to = 168, by = 24))+
geom_hline(yintercept = grand_mean, linetype = 5, linewidth = .5, colour = "red")+
scale_colour_brewer(palette = "Dark2")+
scale_fill_brewer(palette = "Dark2") +
ylab("Correlation (Pearson's r)")+
xlab("Hours following pairing")+
theme_cowplot()+
theme(legend.title = element_blank())+
ggtitle("TLCC BASELINE RANDOM | TS=350s; OS=5-30s")
print(plot_Time_no_treatment_v2)