Load Data
Notes
- issue with s23_pre – multiple select for Q5, Q6, & Q7 not
enabled
f22_post <- read.csv(file="data/FA22 Post_September 21, 2023_18.07.csv", header = F, na.strings = c(""," "))
list <- data.frame(subset(t(f22_post), select=c(1:2)))
f22_post <- f22_post[-c(1,2,3),]
colnames(f22_post) <- list[[1]]
f22_post <- subset(f22_post, Progress == 100)
s23_pre <- read.csv(file="data/SP 23 Pre_January 27, 2023_10.06.csv", header = F, na.strings = c(""," "))
list <- data.frame(subset(t(s23_pre), select=c(1:2)))
s23_pre <- s23_pre[-c(1,2,3),]
colnames(s23_pre) <- list[[1]]
s23_pre <- subset(s23_pre, Progress == 100)
s23_post <- read.csv(file="data/SP 23 Post_May 3, 2023_19.10.csv", header = F, na.strings = c(""," "))
list <- data.frame(subset(t(s23_post), select=c(1:2)))
s23_post <- s23_post[-c(1,2,3),]
colnames(s23_post) <- list[[1]]
s23_post <- subset(s23_post, Progress == 100)
Create IDs
f22_post$Q28 <- tolower(f22_post$Q28)
f22_post$UID <- as.vector(sapply(f22_post$Q28, digest, algo="md5"))
f22_post <- subset(f22_post, select=-c(3:4, 7:17, Q28))
s23_pre$Q28 <- tolower(s23_pre$Q28)
s23_pre$UID <- as.vector(sapply(s23_pre$Q28, digest, algo="md5"))
s23_pre <- subset(s23_pre, select=-c(3:4, 7:17, Q28))
s23_post$Q28 <- tolower(s23_post$Q28)
s23_post$UID <- as.vector(sapply(s23_post$Q28, digest, algo="md5"))
s23_post <- subset(s23_post, select=-c(3:4, 7:17, Q28))
Variable Names
pre_vars <- c("start","end","progress","time",
"major","classes","classestxt","gender","gendertxt","sexuality","sexualitytxt","race","racetxt","ethnicity","parented1","parented2","immi1","immi2","immi3",
"pre_int1","pre_int2","pre_int3","pre_int4","pre_int5","pre_int6","pre_int7","pre_int8","pre_int9","pre_int10",
"pre_ase1","pre_ase2","pre_ase3","pre_ase4","pre_ase5",
"pre_id1","pre_id2","pre_id3","pre_id4","pre_id5","pre_id6","pre_id7","pre_id8","pre_id9","pre_id10",
"pre_ar1","pre_ar2","pre_ar3","pre_ar4","pre_ar5","pre_ar6","pre_ar7","pre_ar8","pre_ar9","pre_ar10","pre_ar11","pre_ar12","pre_ar13",
"UID")
post_vars <- c("start","end","progress","time",
"post_int1","post_int2","post_int3","post_int4","post_int5","post_int6","post_int7","post_int8","post_int9","post_int10",
"post_ase1","post_ase2","post_ase3","post_ase4","post_ase5",
"post_id1","post_id2","post_id3","post_id4","post_id5","post_id6","post_id7","post_id8","post_id9","post_id10",
"post_ar1","post_ar2","post_ar3","post_ar4","post_ar5","post_ar6","post_ar7","post_ar8","post_ar9","post_ar10","post_ar11","post_ar12","post_ar13",
"UID")
colnames(f22_post) <- pre_vars
colnames(s23_pre) <- pre_vars
colnames(s23_post) <- post_vars
Clean Data
Recode Function
# Function to recode selected columns by position as numeric
recode_to_numeric <- function(data, columns_to_recode) {
recoded_data <- data %>%
mutate(across(
.cols = columns_to_recode,
.fns = as.numeric
))
return(recoded_data)
}
columns_to_recode <- c(5,8,10,12,15:57)
f22_post <- recode_to_numeric(f22_post, columns_to_recode)
s23_pre <- recode_to_numeric(s23_pre, columns_to_recode)
columns_to_recode <- c(5:42)
s23_post <- recode_to_numeric(s23_post, columns_to_recode)
Recode Major
f22_post <- f22_post %>%
mutate(major = recode(major,
`1` = "Current major",
`2` = "Current minor",
`3` = "Planning to major",
`4` = "Planning to minor",
`5` = "Considering a major or minor",
`6` = "No, my studies are in a different area"))
table(f22_post$major)
##
## Current major Current minor Planning to major Planning to minor
## 106 14 4 3
s23_pre <- s23_pre %>%
mutate(major = recode(major,
`1` = "Current major",
`2` = "Current minor",
`3` = "Planning to major",
`4` = "Planning to minor",
`5` = "Considering a major or minor",
`6` = "No, my studies are in a different area"))
table(s23_pre$major)
##
## Current major Current minor
## 60 13
## No, my studies are in a different area Planning to major
## 2 1
## Planning to minor
## 1
Recode Gender
f22_post <- f22_post %>%
mutate(gender = recode(gender,
`1` = "Woman",
`2` = "Man",
`3` = "Agender",
`4` = "Genderqueer",
`5` = "Non-binary",
`6` = "Cisgender",
`7` = "Transgender",
`8` = "Not listed",
`9` = "Prefer not to say"))
table(f22_post$gender)
##
## Agender Man Non-binary Transgender Woman
## 1 36 4 1 84
s23_pre <- s23_pre %>%
mutate(gender = recode(gender,
`1` = "Woman",
`2` = "Man",
`3` = "Agender",
`4` = "Genderqueer",
`5` = "Non-binary",
`6` = "Cisgender",
`7` = "Transgender",
`8` = "Not listed",
`9` = "Prefer not to say"))
table(s23_pre$gender)
##
## Genderqueer Man Non-binary Prefer not to say
## 1 10 1 1
## Woman
## 64
Recode Sexuality
f22_post <- f22_post %>%
mutate(sexuality = recode(sexuality,
`1` = "Heterosexual/straight",
`2` = "Homosexual/gay/lesbian",
`3` = "Bisexual",
`4` = "Pansexual",
`5` = "Asexual",
`6` = "Not listed",
`7` = "Prefer not to say"))
table(f22_post$sexuality)
##
## Asexual Bisexual Heterosexual/straight
## 3 13 99
## Homosexual/gay/lesbian Not listed Pansexual
## 5 3 3
## Prefer not to say
## 1
s23_pre <- s23_pre %>%
mutate(sexuality = recode(sexuality,
`1` = "Heterosexual/straight",
`2` = "Homosexual/gay/lesbian",
`3` = "Bisexual",
`4` = "Pansexual",
`5` = "Asexual",
`6` = "Not listed",
`7` = "Prefer not to say"))
table(s23_pre$sexuality)
##
## Bisexual Heterosexual/straight Homosexual/gay/lesbian
## 11 60 2
## Not listed Pansexual
## 1 3
Recode Race
f22_post <- f22_post %>%
mutate(race = recode(race,
`1` = "AIAN",
`2` = "Asian",
`3` = "Black/Afam",
`4` = "Latine",
`5` = "MENA",
`6` = "NHPI",
`7` = "White",
`8` = "Not listed",
`9` = "Prefer not to say"))
table(f22_post$race)
##
## Asian Black/Afam Latine MENA Not listed White
## 20 9 6 2 6 84
s23_pre <- s23_pre %>%
mutate(race = recode(race,
`1` = "AIAN",
`2` = "Asian",
`3` = "Black/Afam",
`4` = "Latine",
`5` = "MENA",
`6` = "NHPI",
`7` = "White",
`8` = "Not listed",
`9` = "Prefer not to say"))
table(s23_pre$race)
##
## Asian Black/Afam Latine MENA
## 7 4 2 1
## Not listed Prefer not to say White
## 1 1 61
Recode First Gen
f22_post <- f22_post %>%
mutate(firstgen = ifelse(parented1 >= 4 | parented2 >= 4, "congen", "firstgen"))
s23_pre <- s23_pre %>%
mutate(firstgen = ifelse(parented1 >= 4 | parented2 >= 4, "congen", "firstgen"))
table(f22_post$firstgen)
##
## congen firstgen
## 94 33
table(s23_pre$firstgen)
##
## congen firstgen
## 54 23
Recode Immigration
Background
f22_post <- f22_post %>%
mutate(immi = case_when(
immi1 == 1 & (immi2 == 2 | immi3 == 2) ~ "secondgen",
immi1 == 2 ~ "firstgen",
TRUE ~ "thirdgen"
))
s23_pre <- s23_pre %>%
mutate(immi = case_when(
immi1 == 1 & (immi2 == 2 | immi3 == 2) ~ "secondgen",
immi1 == 2 ~ "firstgen",
TRUE ~ "thirdgen"
))
table(f22_post$immi)
##
## firstgen secondgen thirdgen
## 14 24 89
table(s23_pre$immi)
##
## firstgen secondgen thirdgen
## 3 8 66
Reverse Code
f22_post$pre_int3 <- abs(f22_post$pre_int3 - 5)
s23_pre$pre_int3 <- abs(s23_pre$pre_int3 - 5)
s23_post$post_int3 <- abs(s23_post$post_int3 - 5)
f22_post$pre_ase3 <- abs(f22_post$pre_ase3 - 5)
s23_pre$pre_ase3 <- abs(s23_pre$pre_ase3 - 5)
s23_post$post_ase3 <- abs(s23_post$post_ase3 - 5)
f22_post$pre_ase5 <- abs(f22_post$pre_ase5 - 5)
s23_pre$pre_ase5 <- abs(s23_pre$pre_ase5 - 5)
s23_post$post_ase5 <- abs(s23_post$post_ase5 - 5)
Factor Analysis
Histogram
Function
plot_all_histograms <- function(data) {
# Gather the data into long format for easier plotting
data_long <- data %>%
gather(variable, value)
# Create the histogram plot
ggplot(data_long, aes(x = value)) +
geom_histogram(binwidth = 1, fill = "blue", color = "black") +
labs(title = "Histograms of Variables",
x = "Value", y = "Frequency") +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5)) +
facet_wrap(~ variable, scales = "free")
}
Fascination &
Value
- Interest = int2, int4, int6
- Value = int8, int9, int10
temp1 <- subset(f22_post, select=c(grep("int",colnames(f22_post))))
temp2 <- subset(s23_pre, select=c(grep("int",colnames(s23_pre))))
d <- rbind.data.frame(temp1, temp2)
d <- subset(d, select=-c(pre_int1))
plot_all_histograms(d)
colnames(d) <- c("I look forward to my psychology classes.",
"I don't care about learning psychology.",
"I am curious about recent discoveries in psychology.",
"Psychology makes the world a better place to live.",
"In general, I find psychology ________",
"I wonder why people think, feel, and behave the way they do.",
"Knowing psychology is important for:",
"Knowing psychology helps me understand how the world works.",
"Thinking like a psychologist will help me do well in:")
ev <- eigen(cor(na.omit(d))) # get eigenvalues
ap <- parallel(subject = nrow(na.omit(d)), var = ncol(na.omit(d)),
rep = 100,cent = .05)
nS <- nScree(x = ev$values, aparallel = ap$eigen$qevpea)
plotnScree(nS)
fit <- factanal(na.omit(d), 2, rotation="promax")
print(fit, digits = 3, cutoff = 0.2, sort = TRUE)
##
## Call:
## factanal(x = na.omit(d), factors = 2, rotation = "promax")
##
## Uniquenesses:
## I look forward to my psychology classes.
## 0.587
## I don't care about learning psychology.
## 0.663
## I am curious about recent discoveries in psychology.
## 0.359
## Psychology makes the world a better place to live.
## 0.548
## In general, I find psychology ________
## 0.608
## I wonder why people think, feel, and behave the way they do.
## 0.807
## Knowing psychology is important for:
## 0.625
## Knowing psychology helps me understand how the world works.
## 0.548
## Thinking like a psychologist will help me do well in:
## 0.672
##
## Loadings:
## Factor1 Factor2
## Knowing psychology is important for: 0.702
## Knowing psychology helps me understand how the world works. 0.672
## Thinking like a psychologist will help me do well in: 0.591
## I look forward to my psychology classes. 0.607
## I am curious about recent discoveries in psychology. 0.842
## Psychology makes the world a better place to live. 0.708
## I don't care about learning psychology. 0.409 0.238
## In general, I find psychology ________ 0.410 0.291
## I wonder why people think, feel, and behave the way they do. 0.469
##
## Factor1 Factor2
## SS loadings 1.862 1.758
## Proportion Var 0.207 0.195
## Cumulative Var 0.207 0.402
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.000 -0.582
## Factor2 -0.582 1.000
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 73.98 on 19 degrees of freedom.
## The p-value is 1.98e-08
Academic
Self-Efficacy
temp1 <- subset(f22_post, select=c(grep("ase",colnames(f22_post))))
temp2 <- subset(s23_pre, select=c(grep("ase",colnames(s23_pre))))
d <- rbind.data.frame(temp1, temp2)
plot_all_histograms(d)
ev <- eigen(cor(na.omit(d))) # get eigenvalues
ap <- parallel(subject = nrow(na.omit(d)), var = ncol(na.omit(d)),
rep = 100,cent = .05)
nS <- nScree(x = ev$values, aparallel = ap$eigen$qevpea)
plotnScree(nS)
fit <- factanal(na.omit(d), 1, rotation="promax")
print(fit, digits = 3, cutoff = 0.3, sort = F)
##
## Call:
## factanal(x = na.omit(d), factors = 1, rotation = "promax")
##
## Uniquenesses:
## pre_ase1 pre_ase2 pre_ase3 pre_ase4 pre_ase5
## 0.751 0.663 0.714 0.760 0.627
##
## Loadings:
## Factor1
## pre_ase1 0.499
## pre_ase2 0.581
## pre_ase3 0.534
## pre_ase4 0.490
## pre_ase5 0.611
##
## Factor1
## SS loadings 1.485
## Proportion Var 0.297
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 2.83 on 5 degrees of freedom.
## The p-value is 0.726
Identity
- Recognition = id2, id3, id4, id5
- Belonging = id7, id8, id9, id10
temp1 <- subset(f22_post, select=c(grep("id",colnames(f22_post))))
temp2 <- subset(s23_pre, select=c(grep("id",colnames(s23_pre))))
d <- rbind.data.frame(temp1, temp2)
d <- subset(d, select=-c(pre_id1))
plot_all_histograms(d)
colnames(d) <- c("My parents see me as a psychology kind of person.",
"My instructors see me as a psychology kind of person.",
"My friends see me as a psychology kind of person.",
"My peers see me as a psychology kind of person.",
"I have had experiences in which I was recognized as a psychology kind of person.",
"I feel comfortable in psychology.",
"I feel I belong in psychology.",
"I enjoy being in psychology.",
"I feel comfortable in my psychology classes.")
ev <- eigen(cor(na.omit(d))) # get eigenvalues
ap <- parallel(subject = nrow(na.omit(d)), var = ncol(na.omit(d)),
rep = 100,cent = .05)
nS <- nScree(x = ev$values, aparallel = ap$eigen$qevpea)
plotnScree(nS)
fit <- factanal(na.omit(d), 1, rotation="promax")
print(fit, digits = 3, cutoff = 0.3, sort = F)
##
## Call:
## factanal(x = na.omit(d), factors = 1, rotation = "promax")
##
## Uniquenesses:
## My parents see me as a psychology kind of person.
## 0.590
## My instructors see me as a psychology kind of person.
## 0.656
## My friends see me as a psychology kind of person.
## 0.422
## My peers see me as a psychology kind of person.
## 0.468
## I have had experiences in which I was recognized as a psychology kind of person.
## 0.622
## I feel comfortable in psychology.
## 0.297
## I feel I belong in psychology.
## 0.243
## I enjoy being in psychology.
## 0.400
## I feel comfortable in my psychology classes.
## 0.447
##
## Loadings:
## Factor1
## My parents see me as a psychology kind of person. 0.640
## My instructors see me as a psychology kind of person. 0.586
## My friends see me as a psychology kind of person. 0.761
## My peers see me as a psychology kind of person. 0.729
## I have had experiences in which I was recognized as a psychology kind of person. 0.615
## I feel comfortable in psychology. 0.838
## I feel I belong in psychology. 0.870
## I enjoy being in psychology. 0.775
## I feel comfortable in my psychology classes. 0.744
##
## Factor1
## SS loadings 4.855
## Proportion Var 0.539
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 196.27 on 27 degrees of freedom.
## The p-value is 1.27e-27
fit <- factanal(na.omit(d), 2, rotation="promax")
print(fit, digits = 3, cutoff = 0.3, sort = F)
##
## Call:
## factanal(x = na.omit(d), factors = 2, rotation = "promax")
##
## Uniquenesses:
## My parents see me as a psychology kind of person.
## 0.485
## My instructors see me as a psychology kind of person.
## 0.630
## My friends see me as a psychology kind of person.
## 0.194
## My peers see me as a psychology kind of person.
## 0.242
## I have had experiences in which I was recognized as a psychology kind of person.
## 0.615
## I feel comfortable in psychology.
## 0.284
## I feel I belong in psychology.
## 0.180
## I enjoy being in psychology.
## 0.286
## I feel comfortable in my psychology classes.
## 0.419
##
## Loadings:
## Factor1
## My parents see me as a psychology kind of person.
## My instructors see me as a psychology kind of person.
## My friends see me as a psychology kind of person.
## My peers see me as a psychology kind of person.
## I have had experiences in which I was recognized as a psychology kind of person.
## I feel comfortable in psychology. 0.761
## I feel I belong in psychology. 0.882
## I enjoy being in psychology. 0.945
## I feel comfortable in my psychology classes. 0.753
## Factor2
## My parents see me as a psychology kind of person. 0.700
## My instructors see me as a psychology kind of person. 0.467
## My friends see me as a psychology kind of person. 0.927
## My peers see me as a psychology kind of person. 0.929
## I have had experiences in which I was recognized as a psychology kind of person. 0.419
## I feel comfortable in psychology.
## I feel I belong in psychology.
## I enjoy being in psychology.
## I feel comfortable in my psychology classes.
##
## Factor1 Factor2
## SS loadings 2.914 2.640
## Proportion Var 0.324 0.293
## Cumulative Var 0.324 0.617
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.000 0.743
## Factor2 0.743 1.000
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 40.72 on 19 degrees of freedom.
## The p-value is 0.00263
Anti-Racism in
Psychology
- Anti-racist self-efficacy = ar1 - ar9
- Vigilance = ar10 - ar13
temp1 <- subset(f22_post, select=c(grep("pre_ar",colnames(f22_post))))
temp2 <- subset(s23_pre, select=c(grep("pre_ar",colnames(s23_pre))))
d <- rbind.data.frame(temp1, temp2)
plot_all_histograms(d)
colnames(d) <- c("Analyzing the social construction of race and racism in psychology",
"Examining the influence of whiteness in the information about psychology that you encounter",
"Answering questions or addressing others' anxiety about controversial racial issues in psychology",
"Using your knowledge of psychology to challenge racial bias",
"Discussing current findings in psychology within their historical and racial contexts",
"Encouraging others to explore their racial identity",
"Examining information you encounter as a psychology student for negative cultural stereotypes",
"Serve as the expert when talking about race and racism in psychology",
"Engage in cross race dialogue with fellow psychology students",
"I think about why racial minorities are treated stereotypically.",
"I think about whether people act in a prejudiced or discriminatory manner.",
"I consider whether people's actions are prejudiced or discriminatory.",
"I am on the lookout for instances of prejudice or discrimination.")
ev <- eigen(cor(na.omit(d))) # get eigenvalues
ap <- parallel(subject = nrow(na.omit(d)), var = ncol(na.omit(d)),
rep = 100,cent = .05)
nS <- nScree(x = ev$values, aparallel = ap$eigen$qevpea)
plotnScree(nS)
fit <- factanal(na.omit(d), 2, rotation="promax")
print(fit, digits = 3, cutoff = 0.3, sort = F)
##
## Call:
## factanal(x = na.omit(d), factors = 2, rotation = "promax")
##
## Uniquenesses:
## Analyzing the social construction of race and racism in psychology
## 0.506
## Examining the influence of whiteness in the information about psychology that you encounter
## 0.494
## Answering questions or addressing others' anxiety about controversial racial issues in psychology
## 0.424
## Using your knowledge of psychology to challenge racial bias
## 0.349
## Discussing current findings in psychology within their historical and racial contexts
## 0.493
## Encouraging others to explore their racial identity
## 0.554
## Examining information you encounter as a psychology student for negative cultural stereotypes
## 0.448
## Serve as the expert when talking about race and racism in psychology
## 0.658
## Engage in cross race dialogue with fellow psychology students
## 0.531
## I think about why racial minorities are treated stereotypically.
## 0.451
## I think about whether people act in a prejudiced or discriminatory manner.
## 0.228
## I consider whether people's actions are prejudiced or discriminatory.
## 0.253
## I am on the lookout for instances of prejudice or discrimination.
## 0.411
##
## Loadings:
## Factor1
## Analyzing the social construction of race and racism in psychology 0.645
## Examining the influence of whiteness in the information about psychology that you encounter 0.675
## Answering questions or addressing others' anxiety about controversial racial issues in psychology 0.830
## Using your knowledge of psychology to challenge racial bias 0.829
## Discussing current findings in psychology within their historical and racial contexts 0.714
## Encouraging others to explore their racial identity 0.625
## Examining information you encounter as a psychology student for negative cultural stereotypes 0.746
## Serve as the expert when talking about race and racism in psychology 0.560
## Engage in cross race dialogue with fellow psychology students 0.698
## I think about why racial minorities are treated stereotypically.
## I think about whether people act in a prejudiced or discriminatory manner.
## I consider whether people's actions are prejudiced or discriminatory.
## I am on the lookout for instances of prejudice or discrimination.
## Factor2
## Analyzing the social construction of race and racism in psychology
## Examining the influence of whiteness in the information about psychology that you encounter
## Answering questions or addressing others' anxiety about controversial racial issues in psychology
## Using your knowledge of psychology to challenge racial bias
## Discussing current findings in psychology within their historical and racial contexts
## Encouraging others to explore their racial identity
## Examining information you encounter as a psychology student for negative cultural stereotypes
## Serve as the expert when talking about race and racism in psychology
## Engage in cross race dialogue with fellow psychology students
## I think about why racial minorities are treated stereotypically. 0.728
## I think about whether people act in a prejudiced or discriminatory manner. 0.913
## I consider whether people's actions are prejudiced or discriminatory. 0.895
## I am on the lookout for instances of prejudice or discrimination. 0.723
##
## Factor1 Factor2
## SS loadings 4.516 2.726
## Proportion Var 0.347 0.210
## Cumulative Var 0.347 0.557
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.000 -0.579
## Factor2 -0.579 1.000
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 137.92 on 53 degrees of freedom.
## The p-value is 1.72e-09
Create Composite
Variables
- Interest = int2, int4, int5
- Value = int8, int9, int10
- Self-efficacy = ase1 - ase5
- Recognition = id2, id3, id4, id5
- Belonging = id7, id8, id9, id10
- Anti-racist self-efficacy = ar1 - ar9
- Vigilance = ar10 - ar13
attach(f22_post)
f22_post$pre_int <- (pre_int2 + pre_int4 + pre_int6)/3
f22_post$pre_val <- (pre_int8 + pre_int9 + pre_int10)/3
f22_post$pre_se <- (pre_ase1 + pre_ase2 + pre_ase3 + pre_ase4 + pre_ase5)/5
f22_post$pre_rec <- (pre_id2 + pre_id3 + pre_id4 + pre_id5)/4
f22_post$pre_bel <- (pre_id7 + pre_id8 + pre_id9 + pre_id10)/4
f22_post$pre_are <- (pre_ar1 + pre_ar2 + pre_ar3 + pre_ar4 + pre_ar5 + pre_ar6 + pre_ar7 + pre_ar8 + pre_ar9)/9
f22_post$pre_vig <- (pre_ar10 + pre_ar11 + pre_ar12 + pre_ar13)/4
detach(f22_post)
attach(s23_pre)
s23_pre$pre_int <- (pre_int2 + pre_int4 + pre_int6)/3
s23_pre$pre_val <- (pre_int8 + pre_int9 + pre_int10)/3
s23_pre$pre_se <- (pre_ase1 + pre_ase2 + pre_ase3 + pre_ase4 + pre_ase5)/5
s23_pre$pre_rec <- (pre_id2 + pre_id3 + pre_id4 + pre_id5)/4
s23_pre$pre_bel <- (pre_id7 + pre_id8 + pre_id9 + pre_id10)/4
s23_pre$pre_are <- (pre_ar1 + pre_ar2 + pre_ar3 + pre_ar4 + pre_ar5 + pre_ar6 + pre_ar7 + pre_ar8 + pre_ar9)/9
s23_pre$pre_vig <- (pre_ar10 + pre_ar11 + pre_ar12 + pre_ar13)/4
detach(s23_pre)
attach(s23_post)
s23_post$post_int <- (post_int2 + post_int4 + post_int6)/3
s23_post$post_val <- (post_int8 + post_int9 + post_int10)/3
s23_post$post_se <- (post_ase1 + post_ase2 + post_ase3 + post_ase4 + post_ase5)/5
s23_post$post_rec <- (post_id2 + post_id3 + post_id4 + post_id5)/4
s23_post$post_bel <- (post_id7 + post_id8 + post_id9 + post_id10)/4
s23_post$post_are <- (post_ar1 + post_ar2 + post_ar3 + post_ar4 + post_ar5 + post_ar6 + post_ar7 + post_ar8 + post_ar9)/9
s23_post$post_vig <- (post_ar10 + post_ar11 + post_ar12 + post_ar13)/4
detach(s23_post)
names(f22_post)
## [1] "start" "end" "progress" "time" "major"
## [6] "classes" "classestxt" "gender" "gendertxt" "sexuality"
## [11] "sexualitytxt" "race" "racetxt" "ethnicity" "parented1"
## [16] "parented2" "immi1" "immi2" "immi3" "pre_int1"
## [21] "pre_int2" "pre_int3" "pre_int4" "pre_int5" "pre_int6"
## [26] "pre_int7" "pre_int8" "pre_int9" "pre_int10" "pre_ase1"
## [31] "pre_ase2" "pre_ase3" "pre_ase4" "pre_ase5" "pre_id1"
## [36] "pre_id2" "pre_id3" "pre_id4" "pre_id5" "pre_id6"
## [41] "pre_id7" "pre_id8" "pre_id9" "pre_id10" "pre_ar1"
## [46] "pre_ar2" "pre_ar3" "pre_ar4" "pre_ar5" "pre_ar6"
## [51] "pre_ar7" "pre_ar8" "pre_ar9" "pre_ar10" "pre_ar11"
## [56] "pre_ar12" "pre_ar13" "UID" "firstgen" "immi"
## [61] "pre_int" "pre_val" "pre_se" "pre_rec" "pre_bel"
## [66] "pre_are" "pre_vig"
temp1 <- subset(f22_post, select=c(61:67))
temp2 <- subset(s23_pre, select=c(61:67))
temp3 <- subset(s23_post, select=c(44:50))
colnames(temp3) <- colnames(temp2)
temp <- rbind.data.frame(temp1, temp2, temp3)
desc <- describe(temp)
kable(round(desc, digits = 2)) %>%
kable_styling() %>%
row_spec(which(desc$kurtosis > 2), bold = T) %>%
row_spec(which(desc$kurtosis < -2), bold = T) %>%
row_spec(which(desc$skew > 2), italic = T) %>%
row_spec(which(desc$skew < -2), italic = T)
|
|
vars
|
n
|
mean
|
sd
|
median
|
trimmed
|
mad
|
min
|
max
|
range
|
skew
|
kurtosis
|
se
|
|
pre_int
|
1
|
272
|
3.51
|
0.45
|
3.67
|
3.55
|
0.49
|
1.67
|
4
|
2.33
|
-1.04
|
1.74
|
0.03
|
|
pre_val
|
2
|
271
|
3.34
|
0.49
|
3.33
|
3.37
|
0.49
|
1.67
|
4
|
2.33
|
-0.54
|
-0.03
|
0.03
|
|
pre_se
|
3
|
269
|
2.98
|
0.42
|
3.00
|
2.97
|
0.59
|
1.60
|
4
|
2.40
|
0.08
|
-0.19
|
0.03
|
|
pre_rec
|
4
|
268
|
3.19
|
0.52
|
3.00
|
3.21
|
0.37
|
1.50
|
4
|
2.50
|
-0.25
|
-0.15
|
0.03
|
|
pre_bel
|
5
|
269
|
3.40
|
0.52
|
3.25
|
3.43
|
0.74
|
1.50
|
4
|
2.50
|
-0.29
|
-0.66
|
0.03
|
|
pre_are
|
6
|
262
|
2.99
|
0.62
|
3.00
|
3.01
|
0.66
|
1.00
|
4
|
3.00
|
-0.21
|
-0.48
|
0.04
|
|
pre_vig
|
7
|
269
|
2.97
|
0.66
|
3.00
|
2.99
|
0.74
|
1.25
|
4
|
2.75
|
-0.12
|
-0.68
|
0.04
|
Write Clean Files
f22_post_fin <- subset(f22_post, select=c(58,1:5,8,10,12,59:67))
s23_pre_fin <- subset(s23_pre, select=c(58,1:5,8,10,12,59:67))
names(s23_post)
## [1] "start" "end" "progress" "time" "post_int1"
## [6] "post_int2" "post_int3" "post_int4" "post_int5" "post_int6"
## [11] "post_int7" "post_int8" "post_int9" "post_int10" "post_ase1"
## [16] "post_ase2" "post_ase3" "post_ase4" "post_ase5" "post_id1"
## [21] "post_id2" "post_id3" "post_id4" "post_id5" "post_id6"
## [26] "post_id7" "post_id8" "post_id9" "post_id10" "post_ar1"
## [31] "post_ar2" "post_ar3" "post_ar4" "post_ar5" "post_ar6"
## [36] "post_ar7" "post_ar8" "post_ar9" "post_ar10" "post_ar11"
## [41] "post_ar12" "post_ar13" "UID" "post_int" "post_val"
## [46] "post_se" "post_rec" "post_bel" "post_are" "post_vig"
s23_post_fin <- subset(s23_post, select=c(43,1:4,44:50))
s23 <- merge(s23_pre_fin, s23_post_fin, by="UID")
# write.csv(f22_post_fin, file="clean/f22_post.csv", row.names = F)
# write.csv(s23_pre_fin, file="clean/s23_pre.csv", row.names = F)
# write.csv(s23_post_fin, file="clean/s23_post.csv", row.names = F)
# write.csv(s23, file="clean/s23_merged.csv", row.names = F)