setwd("~/My Drive (okara004@ucr.edu)/classes/fall 2022 quarter/PSYC 211 -- stats/final project")
i’ll be using a data file given to me by my advisor (same one i used for all the problem sets).
## load the data file.
patience_data <- read.csv("patience22ucr_copy.csv")
## then load the libraries you'll need.
library(psych)
library(report)
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ ggplot2::%+%() masks psych::%+%()
## ✖ ggplot2::alpha() masks psych::alpha()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(ggplot2)
i am interested in data from the 3-factor patience scale (3-FPS) and the emotion regulation questionnaire (ERQ). i will also be selecting the participant demographic information.
patience_ERQ_gender <- subset(patience_data, select = c("sn", "patience_ss1", "patience_ss2",
"patience_ss3", "patience_ss4", "patience_ss5",
"patience_ss6", "patience_ss7", "patience_ss8",
"patience_ss9", "patience_ss10", "patience_ss11",
"erq1", "erq2", "erq3", "erq4", "erq5", "erq6",
"erq7", "erq8", "erq9", "erq10", "sex", "age",
"eth", "eth_7_TEXT"))
i will be averaging all the 3-FPS, ERQ–reappraisal, and ERQ–suppression items to get average patience, reappraisal, and suppression scores.
## first average all of the patience items and put these averages in a new column.
patience_ERQ_gender$patience_avg <- rowMeans(patience_ERQ_gender[ , c("patience_ss1", "patience_ss2", "patience_ss3", "patience_ss4", "patience_ss5", "patience_ss6",
"patience_ss7", "patience_ss8", "patience_ss9", "patience_ss10", "patience_ss11")],
na.rm = TRUE)
## now average all of the ERQ reappraisal items and put these averages in a new column.
patience_ERQ_gender$reappraisal_avg <- rowMeans(patience_ERQ_gender[ , c("erq1", "erq3", "erq5", "erq7", "erq8", "erq10")], na.rm = TRUE)
## lastly average the ERQ suppression items and put these averages in a new column.
patience_ERQ_gender$suppression_avg <- rowMeans(patience_ERQ_gender[ , c("erq2", "erq4", "erq6", "erq9")], na.rm = TRUE)
anyone who has missing data for all scale items (for any scale) will be removed. additionally, anyone who did not report being either male or female will be removed.
## these 2 participants did not have any data for the 3_FPS so i am removing them.
patience_ERQ_gender_2 <- patience_ERQ_gender[ -c(208, 216), ]
## now take a look at the different reported genders.
table(patience_ERQ_gender_2$sex)
##
## 1 2 3 4
## 92 115 3 4
## remove anyone who reported a gender other than male/female.
gender_TABLE <- table(patience_ERQ_gender_2$sex <= 2, patience_ERQ_gender_2$sn)
gender_TABLE
##
## 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
## FALSE 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 0 1 1 1 1 1 1 1
##
## 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069
## FALSE 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 0 1 1 1 1 1 1
##
## 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 0 1
##
## 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
## FALSE 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 0 1 1 1 1 1 1 1
##
## 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
## FALSE 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 0 1 1 1 1 1 1
##
## 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##
## 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195
## FALSE 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## TRUE 1 1 1 1 1 1 1 1 1 1 1 1 0 1
##
## 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1208 1209 1210
## FALSE 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## TRUE 1 1 1 1 1 1 1 0 1 1 1 1 1 1
##
## 1211 1212 1213 1214
## FALSE 0 0 0 0
## TRUE 1 1 1 1
genderMF_LIST <- which(gender_TABLE[2 , ] == 1)
length(genderMF_LIST) ### we're left with 207 subjects, which is the total of male + female found above in the table
## [1] 207
patience_ERQ_gender_3 <- patience_ERQ_gender_2[patience_ERQ_gender_2$sn %in% names(genderMF_LIST), ]
## first look at the information on participant sex.
table(patience_ERQ_gender_3$sex) ### 1 is male, 2 is female
##
## 1 2
## 92 115
115/207 # 55.56% women
## [1] 0.5555556
## then look at the descriptive stats on participant age.
describe(patience_ERQ_gender_3$age)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 207 20.5 2.2 20 20.23 1.48 18 34 16 2.73 12.72 0.15
## lastly look at the information on participant race/ethnicity.
table(patience_ERQ_gender_3$eth) # 1 is white, 2 is black/african diaspora, 3 is native american/other native person, 4 is asian, 5 is native hawaiian/pacific islander, 6 is latino/a/x, 7 and 8 are other
##
## 1 2 3 4 6 7 8
## 18 6 1 88 73 9 12
18/207 # 8.7% white
## [1] 0.08695652
6/207 # 2.9% black
## [1] 0.02898551
1/207 # 0.48% native american
## [1] 0.004830918
88/207 # 42.51% asian
## [1] 0.4251208
73/207 # 35.27% latinx
## [1] 0.352657
(9+12)/207 # 10.14% other
## [1] 0.1014493
## first you'll need to split your sex variable into 2 factors -- male & female.
patience_ERQ_gender_3$sex <- as.factor(patience_ERQ_gender_3$sex)
patience_ERQ_gender_4 <- patience_ERQ_gender_3
levels(patience_ERQ_gender_4$sex) <- list("male" = "1", "female" = "2")
## create female/male reappraisal variables.
female_reapp <- patience_ERQ_gender_4$reappraisal_avg[patience_ERQ_gender_4$sex == "female"]
male_reapp <- patience_ERQ_gender_4$reappraisal_avg[patience_ERQ_gender_4$sex == "male"]
## test for homoscedasticity.
var.test(female_reapp, male_reapp)
##
## F test to compare two variances
##
## data: female_reapp and male_reapp
## F = 1.2093, num df = 114, denom df = 91, p-value = 0.3463
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.813651 1.781595
## sample estimates:
## ratio of variances
## 1.209252
## awesome!! variances are equal. let's continue.
## run an independent-samples t-test to test the difference in means between male reappraisal & female reappraisal.
MF_reapp_test <- t.test(female_reapp, male_reapp,
var.equal = TRUE)
MF_reapp_test
##
## Two Sample t-test
##
## data: female_reapp and male_reapp
## t = 1.2856, df = 205, p-value = 0.2
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.07057077 0.33506352
## sample estimates:
## mean of x mean of y
## 3.607246 3.475000
report(MF_reapp_test)
## Warning: Missing values detected. NAs dropped.
## Effect sizes were labelled following Cohen's (1988) recommendations.
##
## The Two Sample t-test testing the difference between female_reapp and
## male_reapp (mean of x = 3.61, mean of y = 3.48) suggests that the effect is
## positive, statistically not significant, and very small (difference = 0.13, 95%
## CI [-0.07, 0.34], t(205) = 1.29, p = 0.200; Cohen's d = 0.18, 95% CI [-0.10,
## 0.45])
## get the descriptives of the male/female reappraisal variables.
describe(female_reapp)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 115 3.61 0.77 3.67 3.6 0.74 1.67 6.67 5 0.28 1.35 0.07
describe(male_reapp)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 92 3.48 0.7 3.5 3.52 0.74 1.5 5 3.5 -0.5 0.06 0.07
## create female/male suppression variables.
female_supp <- patience_ERQ_gender_4$suppression_avg[patience_ERQ_gender_4$sex == "female"]
male_supp <- patience_ERQ_gender_4$suppression_avg[patience_ERQ_gender_4$sex == "male"]
## test for homoscedasticity.
var.test(female_supp, male_supp)
##
## F test to compare two variances
##
## data: female_supp and male_supp
## F = 1.083, num df = 114, denom df = 91, p-value = 0.6952
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.7286791 1.5955384
## sample estimates:
## ratio of variances
## 1.082966
## awesome!! variances are equal. let's continue.
## run an independent-samples t-test to test the difference in means between male suppression & female suppression.
MF_supp_test <- t.test(female_supp, male_supp,
var.equal = TRUE)
MF_supp_test
##
## Two Sample t-test
##
## data: female_supp and male_supp
## t = -1.2956, df = 205, p-value = 0.1966
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.37688683 0.07797378
## sample estimates:
## mean of x mean of y
## 3.184783 3.334239
report(MF_supp_test)
## Warning: Missing values detected. NAs dropped.
## Effect sizes were labelled following Cohen's (1988) recommendations.
##
## The Two Sample t-test testing the difference between female_supp and male_supp
## (mean of x = 3.18, mean of y = 3.33) suggests that the effect is negative,
## statistically not significant, and very small (difference = -0.15, 95% CI
## [-0.38, 0.08], t(205) = -1.30, p = 0.197; Cohen's d = -0.18, 95% CI [-0.46,
## 0.09])
## get the descriptives of the male/female suppression variables.
describe(female_supp)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 115 3.18 0.84 3 3.18 1.11 1.25 5 3.75 0.05 -0.51 0.08
describe(male_supp)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 92 3.33 0.81 3.25 3.33 0.74 1.5 5 3.5 0.03 -0.55 0.08
## create male/female patience variables.
female_patience <- patience_ERQ_gender_4$patience_avg[patience_ERQ_gender_4$sex == "female"]
male_patience <- patience_ERQ_gender_4$patience_avg[patience_ERQ_gender_4$sex == "male"]
## test for homoscedasticity.
var.test(female_patience, male_patience)
##
## F test to compare two variances
##
## data: female_patience and male_patience
## F = 1.3491, num df = 114, denom df = 91, p-value = 0.1378
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.9077202 1.9875724
## sample estimates:
## ratio of variances
## 1.349058
## awesome!! variances are equal. let's continue.
## run an independent-samples t-test to test the difference in means between male patience & female patience.
MF_patience_test <- t.test(female_patience, male_patience,
var.equal = TRUE)
MF_patience_test
##
## Two Sample t-test
##
## data: female_patience and male_patience
## t = -0.56972, df = 205, p-value = 0.5695
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.1829218 0.1009060
## sample estimates:
## mean of x mean of y
## 3.316206 3.357213
report(MF_patience_test)
## Warning: Missing values detected. NAs dropped.
## Effect sizes were labelled following Cohen's (1988) recommendations.
##
## The Two Sample t-test testing the difference between female_patience and
## male_patience (mean of x = 3.32, mean of y = 3.36) suggests that the effect is
## negative, statistically not significant, and very small (difference = -0.04,
## 95% CI [-0.18, 0.10], t(205) = -0.57, p = 0.569; Cohen's d = -0.08, 95% CI
## [-0.35, 0.19])
## get the descriptives of the male/female patience variables.
describe(female_patience)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 115 3.32 0.55 3.27 3.31 0.54 1.36 4.64 3.27 -0.16 0.79 0.05
describe(male_patience)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 92 3.36 0.47 3.36 3.35 0.54 2.45 4.45 2 0.09 -0.67 0.05
## create a graph for the reappraisal results (after calculating 95% CIs).
reapp_info <- patience_ERQ_gender_4 %>%
group_by(sex) %>%
summarise(
n = n(),
sd = sd(reappraisal_avg, na.rm = TRUE),
reappraisal_avg = mean(reappraisal_avg, na.rm = TRUE)
) %>%
mutate(se = sd/sqrt(n)) %>%
mutate(ci = se * 1.96)
ggplot(reapp_info, aes(sex, reappraisal_avg)) +
geom_col(fill = c("blue", "pink")) +
geom_errorbar(aes(ymin = reappraisal_avg - ci, ymax = reappraisal_avg + ci), width = 0.3) +
xlab("Gender") +
ylab("Reappraisal Tendency")
## create a graph for the suppression results (after calcualting 95% CIs).
supp_info <- patience_ERQ_gender_4 %>%
group_by(sex) %>%
summarise(
n = n(),
sd = sd(suppression_avg, na.rm = TRUE),
suppression_avg = mean(suppression_avg, na.rm = TRUE)
) %>%
mutate(se = sd/sqrt(n)) %>%
mutate(ci = se * 1.96)
ggplot(supp_info, aes(sex, suppression_avg)) +
geom_col(fill = c("blue", "pink")) +
geom_errorbar(aes(ymin = suppression_avg - ci, ymax = suppression_avg + ci), width = 0.3) +
xlab("Gender") +
ylab("Suppression Tendency")
## create a graph for the patience results (after calcualting 95% CIs).
patience_info <- patience_ERQ_gender_4 %>%
group_by(sex) %>%
summarise(
n = n(),
sd = sd(patience_avg, na.rm = TRUE),
patience_avg = mean(patience_avg, na.rm = TRUE)
) %>%
mutate(se = sd/sqrt(n)) %>%
mutate(ci = se * 1.96)
ggplot(patience_info, aes(sex, patience_avg)) +
geom_col(fill = c("blue", "pink")) +
geom_errorbar(aes(ymin = patience_avg - ci, ymax = patience_avg + ci), width = 0.3) +
xlab("Gender") +
ylab("Patience")