Stress and Personality Pilot Studies
Samantha Grayson
2024-03-07
Pilot 1
In pilot 1, we recruited 100 participants on Prolific. Approximately half were assigned to a stress manipulation and the others were assigned to the nonstress condition. We ran a design where personality states were measured once after the manipulation.
Load Packages
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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 errorsLoad Data
pilot1 <- read.csv("~/Downloads/Stress and Personality_March 7, 2024_12.08.csv") %>%
slice(-c(1:2)) %>%
rename(Condition = FL_7_DO) %>%
mutate(Condition = ifelse(Condition == "FL_11", "stress", "nonstress")) %>%
filter(attn == 24)How many participants were assigned to each condition by Qualtrics?
table(pilot1$Condition)##
## nonstress stress
## 55 47There doesn’t seem to be severe differential drop out.
Manipulation Check
# Manipulation check
pilot1 %>%
lm(momentary_stress ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = momentary_stress ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.97872 -0.63636 0.02128 0.36364 2.36364
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.6364 0.1346 12.153 < 2e-16 ***
## Conditionstress 1.3424 0.1983 6.768 9.02e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9985 on 100 degrees of freedom
## Multiple R-squared: 0.3141, Adjusted R-squared: 0.3073
## F-statistic: 45.8 on 1 and 100 DF, p-value: 9.024e-10library(see)
library(ggpubr)
my_comparisons <- list( c("stress", "nonstress"))
ggplot(data = pilot1,
mapping = aes(x = Condition,
y = as.numeric(momentary_stress),
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Stress and personality states results
# Recode reverse scored items
pilot1 <- pilot1 %>%
mutate(across(starts_with("extra"), as.numeric)) %>%
mutate(across(starts_with("neuro"), as.numeric)) %>%
mutate(across(starts_with("con_"), as.numeric)) %>%
mutate(across(starts_with("agree"), as.numeric)) %>%
mutate(across(starts_with("open"), as.numeric)) %>%
rowwise() %>%
mutate(extra_2_R = 8 - extra_2_1) %>%
mutate(extra_3_R = 8 - extra_3_1) %>%
mutate(neuro_1_R = 8 - neuro_1_1) %>%
mutate(neuro_3_R = 8 - neuro_3_1) %>%
mutate(con_2_R = 8 - con_2_1) %>%
mutate(con_3_R = 8 - con_3_1) %>%
mutate(agree_3_R = 8 - agree_3_1) %>%
ungroup()
# Create means for personality states
pilot1 <- pilot1 %>%
rowwise() %>%
mutate(extra_avg = mean(c(extra_1_1, extra_2_R, extra_3_R, extra_4_1), na.rm = T))%>%
mutate(neuro_avg = mean(c(neuro_1_R, neuro_2_1, neuro_3_R, neuro_4_1), na.rm = T))%>%
mutate(con_avg = mean(c(con_1_1, con_2_R, con_3_R, con_4_1), na.rm = T)) %>%
mutate(agree_avg = mean(c(agree_1_1, agree_2_1, agree_3_R, agree_4_1), na.rm = T))%>%
ungroup() %>%
mutate(open_avg = rowMeans(select(., starts_with("open")), na.rm = T)) Analyses
Extraversion
pilot1 %>%
lm(extra_avg ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = extra_avg ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.53723 -0.78723 -0.03723 0.53636 2.71277
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.9636 0.1627 24.365 <2e-16 ***
## Conditionstress 0.0736 0.2397 0.307 0.759
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.206 on 100 degrees of freedom
## Multiple R-squared: 0.0009423, Adjusted R-squared: -0.009048
## F-statistic: 0.09431 on 1 and 100 DF, p-value: 0.7594ggplot(data = pilot1,
mapping = aes(x = Condition,
y = extra_avg,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Neuroticism
pilot1 %>%
lm(neuro_avg ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = neuro_avg ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.0319 -0.7182 -0.2182 0.7818 2.2818
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.96818 0.13937 28.47 <2e-16 ***
## Conditionstress 0.06373 0.20532 0.31 0.757
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.034 on 100 degrees of freedom
## Multiple R-squared: 0.0009626, Adjusted R-squared: -0.009028
## F-statistic: 0.09636 on 1 and 100 DF, p-value: 0.7569ggplot(data = pilot1,
mapping = aes(x = Condition,
y = neuro_avg,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Conscientiousness
pilot1 %>%
lm(con_avg ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = con_avg ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4255 -0.6973 0.0455 0.7402 1.8245
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.2045 0.1370 37.985 <2e-16 ***
## Conditionstress -0.2790 0.2018 -1.382 0.17
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.016 on 100 degrees of freedom
## Multiple R-squared: 0.01875, Adjusted R-squared: 0.008937
## F-statistic: 1.911 on 1 and 100 DF, p-value: 0.17ggplot(data = pilot1,
mapping = aes(x = Condition,
y = con_avg,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Agreeableness
pilot1 %>%
lm(agree_avg ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = agree_avg ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0227 -0.7138 0.2273 0.7273 2.2128
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.0227 0.1499 33.514 <2e-16 ***
## Conditionstress -0.2355 0.2208 -1.067 0.289
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.111 on 100 degrees of freedom
## Multiple R-squared: 0.01125, Adjusted R-squared: 0.001362
## F-statistic: 1.138 on 1 and 100 DF, p-value: 0.2887ggplot(data = pilot1,
mapping = aes(x = Condition,
y = agree_avg,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Openness to Experience
pilot1 %>%
lm(open_avg ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = open_avg ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.01596 -0.71818 -0.01596 0.76987 2.23404
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.2182 0.1511 34.537 <2e-16 ***
## Conditionstress -0.4522 0.2226 -2.032 0.0448 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.121 on 100 degrees of freedom
## Multiple R-squared: 0.03964, Adjusted R-squared: 0.03004
## F-statistic: 4.128 on 1 and 100 DF, p-value: 0.04483ggplot(data = pilot1,
mapping = aes(x = Condition,
y = open_avg,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Pilot 2
In pilot 1, we observed that there was a lot of within person variation on personality states that might have washed out the effects of stress on personality states. So, in pilot 2, we tried to account for within person variation by measuring personality states pre- and post- intervention. We recruited a sample of 100 participants on Prolific. Approximately half were assigned to a stress manipulation and the others were assigned to the non stress condition.
Load Data
pilot2 <- read.csv("~/Downloads/Stress and Personality (Pilot 2)_March 10, 2024_21.40.csv") %>%
slice(-c(1:2)) %>%
rename(Condition = FL_7_DO) %>%
mutate(Condition = ifelse(Condition == "FL_11", "stress", "nonstress"))%>%
filter(attn == 24)How many participants were assigned to each condition by Qualtrics?
table(pilot2$Condition)##
## nonstress stress
## 54 46There doesn’t seem to be severe differential drop out.
Manipulation Check
# Manipulation check
pilot2 %>%
lm(momentary_stress ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = momentary_stress ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.0435 -0.6296 -0.0435 0.3704 3.3704
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.6296 0.1606 10.147 < 2e-16 ***
## Conditionstress 1.4138 0.2368 5.971 3.79e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.18 on 98 degrees of freedom
## Multiple R-squared: 0.2667, Adjusted R-squared: 0.2592
## F-statistic: 35.65 on 1 and 98 DF, p-value: 3.792e-08my_comparisons <- list( c("stress", "nonstress"))
ggplot(data = pilot2,
mapping = aes(x = Condition,
y = as.numeric(momentary_stress),
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
Stress and personality states results
# Recode reverse scored items
pilot2 <- pilot2 %>%
mutate(across(starts_with("extra"), as.numeric)) %>%
mutate(across(starts_with("neuro"), as.numeric)) %>%
mutate(across(starts_with("con_"), as.numeric)) %>%
mutate(across(starts_with("agree"), as.numeric)) %>%
mutate(across(starts_with("open"), as.numeric)) %>%
rowwise() %>%
mutate(extra_2_T1_R = 8 - extra_2_T1_1) %>%
mutate(neuro_1_T1_R = 8 - neuro_1_T1_1) %>%
mutate(con_2_T1_R = 8 - con_2_T1_1) %>%
mutate(extra_2_T2_R = 8 - extra_2_T2_1) %>%
mutate(neuro_1_T2_R = 8 - neuro_1_T2_1) %>%
mutate(con_2_T2_R = 8 - con_2_T2_1) %>%
ungroup()
# Create means and difference scores for personality states
pilot2 <- pilot2 %>%
rowwise() %>%
mutate(extra_avg_T1 = mean(c(extra_1_T1_1, extra_2_T1_R), na.rm = T))%>%
mutate(neuro_avg_T1 = mean(c(neuro_1_T1_R, neuro_2_T1_1), na.rm = T))%>%
mutate(con_avg_T1 = mean(c(con_1_T1_1, con_2_T1_1), na.rm = T)) %>%
mutate(agree_avg_T1 = mean(c(agree_1_T1_1, agree_2_T1_1), na.rm = T))%>%
mutate(open_avg_T1 = mean(c(open_1_T1_1, open_2_T1_1), na.rm = T))%>%
mutate(extra_avg_T2 = mean(c(extra_1_T2_1, extra_2_T2_R), na.rm = T))%>%
mutate(neuro_avg_T2 = mean(c(neuro_1_T2_R, neuro_2_T2_1), na.rm = T))%>%
mutate(con_avg_T2 = mean(c(con_1_T2_1, con_2_T2_1), na.rm = T)) %>%
mutate(agree_avg_T2 = mean(c(agree_1_T2_1, agree_2_T2_1), na.rm = T))%>%
mutate(open_avg_T2 = mean(c(open_1_T2_1, open_2_T2_1), na.rm = T))%>%
mutate(extra_diffScore = extra_avg_T1 - extra_avg_T2) %>%
mutate(neuro_diffScore = neuro_avg_T1 - neuro_avg_T2) %>%
mutate(con_diffScore = con_avg_T1 - con_avg_T2) %>%
mutate(agree_diffScore = agree_avg_T1 - agree_avg_T2) %>%
mutate(open_diffScore = open_avg_T1 - open_avg_T2) %>%
ungroup() Analyses
Extraversion
pilot2 %>%
lm(extra_diffScore ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = extra_diffScore ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3982 -0.3982 0.1018 0.1018 2.8587
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.10185 0.08696 -1.171 0.2444
## Conditionstress 0.24316 0.12822 1.896 0.0609 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.639 on 98 degrees of freedom
## Multiple R-squared: 0.0354, Adjusted R-squared: 0.02556
## F-statistic: 3.596 on 1 and 98 DF, p-value: 0.06085ggplot(data = pilot2,
mapping = aes(x = Condition,
y = extra_diffScore,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
A positive difference score means their T2 extraversion score was smaller than their T1 extraversion score – in line with our hypothesis that participants would be less extraverted when under stress. The effect is marginally significant.
Neuroticism
pilot2 %>%
lm(neuro_diffScore ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = neuro_diffScore ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9891 -0.1574 -0.1574 0.5109 3.8426
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1574 0.1215 1.295 0.198278
## Conditionstress -0.6683 0.1792 -3.730 0.000321 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.893 on 98 degrees of freedom
## Multiple R-squared: 0.1243, Adjusted R-squared: 0.1154
## F-statistic: 13.91 on 1 and 98 DF, p-value: 0.0003213ggplot(data = pilot2,
mapping = aes(x = Condition,
y = neuro_diffScore,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
A negative difference score means their T2 neuroticism score was higher than their T1 neuroticism score – in line with our hypothesis that participants would be more neurotic when under stress. The effect is significant.
Conscientiousness
pilot2 %>%
lm(con_diffScore ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = con_diffScore ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.49074 -0.16345 0.00926 0.44565 2.00926
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.009259 0.088405 -0.105 0.917
## Conditionstress 0.063607 0.130346 0.488 0.627
##
## Residual standard error: 0.6496 on 98 degrees of freedom
## Multiple R-squared: 0.002424, Adjusted R-squared: -0.007755
## F-statistic: 0.2381 on 1 and 98 DF, p-value: 0.6267ggplot(data = pilot2,
mapping = aes(x = Condition,
y = con_diffScore,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
We also did not see an affect of stress on conscientiousness in our EMA data.
Agreeableness
pilot2 %>%
lm(agree_diffScore ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = agree_diffScore ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7391 -0.3241 0.1759 0.1759 2.2609
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.17593 0.08743 -2.012 0.04693 *
## Conditionstress 0.41506 0.12890 3.220 0.00174 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6424 on 98 degrees of freedom
## Multiple R-squared: 0.09567, Adjusted R-squared: 0.08645
## F-statistic: 10.37 on 1 and 98 DF, p-value: 0.00174ggplot(data = pilot2,
mapping = aes(x = Condition,
y = agree_diffScore,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
A positive difference score means their T2 agreeableness score was lower than their T1 agreeableness score – in line with our hypothesis that participants would be less agreeable when under stress. The effect is significant.
Openness to Experience
pilot2 %>%
lm(open_diffScore ~ Condition, .)%>%
summary()##
## Call:
## lm(formula = open_diffScore ~ Condition, data = .)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1957 -0.1957 -0.0556 -0.0556 2.9444
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.05556 0.10699 0.519 0.605
## Conditionstress 0.14010 0.15774 0.888 0.377
##
## Residual standard error: 0.7862 on 98 degrees of freedom
## Multiple R-squared: 0.007985, Adjusted R-squared: -0.002138
## F-statistic: 0.7888 on 1 and 98 DF, p-value: 0.3766ggplot(data = pilot2,
mapping = aes(x = Condition,
y = open_diffScore,
color = Condition)) +
# means with confidence intervals
geom_violinhalf(position = position_nudge(0.1),
#fill = "gray23",
alpha = 0.4) +
geom_point(alpha = 0.3,
size = 2,
position = position_jitter(0.1)) +
stat_summary(fun.data = "mean_cl_boot",
size = 1,
geom = "linerange",
color = "grey50",
position = position_nudge(x = 0.2)) +
stat_summary(fun = "mean",
size = 0.3,
position = position_nudge(x = 0.2))+
# individual data points (jittered horizontally)
theme_bw()+
theme(legend.position="none")+
stat_compare_means(comparisons = my_comparisons, label = "p.signif", method = "t.test")## Warning: Removed 2 rows containing missing values (`geom_segment()`).
The EMA models showed that people were a little more open when under stress. This trend is in the right direction here, but not significant. Maybe it will be when we power the study up?