1. Pre-processing (for semesters 1 and 2)
# install.packages("devtools")
# devtools::install_github("jrosen48/jmRtools")
Sys.setenv(TZ='America/Detroit')
library(jmRtools)
library(readxl)
library(tidyverse)
library(lubridate)
RR_Course_Data <- read_csv("RR_Course_Data.csv")
CS1 <- read_csv("data/CS1.csv") # this is the pre-survey for the Fall, 2015 and Spring, 2016 semesters
CS1_ss <- dplyr::filter(CS1,
!is.na(Q1MaincellgroupRow1),
opdata_username != "_49147_1",
opdata_username != "_93993_1",
opdata_username != "@X@user.pk_string@X@",
opdata_username != "_80624_1",
opdata_CourseID != "@X@course.course_id@X@",
opdata_username != "") # must revisit
ps12 <- dplyr::arrange(CS1_ss, opdata_username, opdata_CourseID, StartDate)
# ps12$Q1MaincellgroupRow4_rc <- car::recode(ps12$Q1MaincellgroupRow4, "1=5; 2=4; 5=1; 4=2")
ps12$Q1MaincellgroupRow7_rc <- car::recode(ps12$Q1MaincellgroupRow7, "1=5; 2=4; 5=1; 4=2")
ps12$int <- (ps12$Q1MaincellgroupRow1 + ps12$Q1MaincellgroupRow8 + ps12$Q1MaincellgroupRow10+ ps12$Q1MaincellgroupRow5) / 4
ps12$uv <- (ps12$Q1MaincellgroupRow2 + ps12$Q1MaincellgroupRow6+ ps12$Q1MaincellgroupRow9) / 3 # dropped 7 (is this supposed to be dropped 4?)
ps12$percomp <- (ps12$Q1MaincellgroupRow3 + ps12$Q1MaincellgroupRow7_rc) / 2
x <- str_split(ps12$opdata_CourseID, "-")
ps12_f <- mutate(ps12,
subject = map_chr(x, ~ .[1]),
semester = map_chr(x, ~ .[2]),
section = map_chr(x, ~ .[3]))
ps12_f <- select(ps12_f,
student_ID = opdata_username,
course_ID = opdata_CourseID,
subject, semester, section,
int, uv, percomp)
ps12_f <- mutate(ps12_f, student_ID = str_sub(student_ID, start = 2L, end = -3L))
ps12_f <- arrange(ps12_f, student_ID)
CS2 <- read_csv("data/CS2.csv") # this is the pre-survey for the Fall, 2015 and Spring, 2016 semesters
CS2$Q1MaincellgroupRow7_rc <- car::recode(CS2$Q1MaincellgroupRow7, "1=5; 2=4; 5=1; 4=2")
CS2$post_int <- (CS2$Q1MaincellgroupRow1 + CS2$Q1MaincellgroupRow8 + CS2$Q1MaincellgroupRow10+ CS2$Q1MaincellgroupRow5) / 4
CS2$post_uv <- (CS2$Q1MaincellgroupRow2 + CS2$Q1MaincellgroupRow6+ CS2$Q1MaincellgroupRow9) / 3 # dropped 7 (is this supposed to be dropped 4?)
CS2$post_percomp <- (CS2$Q1MaincellgroupRow3 + CS2$Q1MaincellgroupRow7_rc) / 2
CS2$date <- lubridate::ymd_hm(CS2$CompletedDate, tz = "America/Detroit")
CS2 <- arrange(CS2, date)
CS2 <- CS2 %>%
mutate(student_ID = str_sub(opdata_username, start = 2L, end = -3L)) %>%
select(student_ID, contains("post"), date)
CS2 <- CS2[complete.cases(CS2), ]
CS2 <- filter(CS2,
student_ID != "49147",
student_ID != "93993",
student_ID != "80624",
student_ID != "@X@user.pk_string@X@",
student_ID != "@X@course.course_id@X@",
student_ID != "")
CS2 <- distinct(CS2, student_ID, .keep_all = T)
CS2 <- select(CS2, -date)
CS2 <- arrange(CS2, student_ID)
ps12_f <- left_join(ps12_f, CS2, by = "student_ID")
2. Pre-processing (for semester 3)
ps3 <- read_excel("~/Dropbox/1_Research/utility_value_intervention_online_science/CS_1_7_13_17.xls")
ps3$Q1MaincellgroupRow61_rc <- car::recode(ps3$Q1MaincellgroupRow61, "1=5; 2=4; 5=1; 4=2")
# ps3$int <- (ps3$Q1MaincellgroupRow01 + ps3$Q1MaincellgroupRow71 + ps3$Q1MaincellgroupRow91+ ps3$Q1MaincellgroupRow41) / 4
# ps3$uv <- (ps3$Q1MaincellgroupRow11 + ps3$Q1MaincellgroupRow51+ ps3$Q1MaincellgroupRow81) / 3 # dropped 7
# ps3$percomp <- (ps3$Q1MaincellgroupRow21 + ps3$Q1MaincellgroupRow61_rc) / 2
ps3 <- ps3 %>%
mutate(int = composite_mean_maker(ps3, Q1MaincellgroupRow01, Q1MaincellgroupRow71, Q1MaincellgroupRow91, Q1MaincellgroupRow41),
uv = composite_mean_maker(ps3, Q1MaincellgroupRow11, Q1MaincellgroupRow51, Q1MaincellgroupRow81),
percomp = composite_mean_maker(ps3, Q1MaincellgroupRow11, Q1MaincellgroupRow51, Q1MaincellgroupRow81)) %>%
filter(opdata_CourseID != "@X@course.course_id@X@") %>%
separate(opdata_CourseID, c("subject", "semester", "section"), sep = "-", remove = F)
ps3_f <- select(ps3,
student_ID = opdata_username,
course_ID = opdata_CourseID,
subject, semester, section,
int, uv, percomp)
df2 <- read_excel("~/Dropbox/1_Research/utility_value_intervention_online_science/CS_2_7_13_17.xls")
df2$post_int <- (df2$Q2MaincellgroupRow01 + df2$Q2MaincellgroupRow71 + df2$Q2MaincellgroupRow91 + df2$Q2MaincellgroupRow41) / 4
df2$post_uv <- (df2$Q2MaincellgroupRow11 + df2$Q2MaincellgroupRow51+ df2$Q2MaincellgroupRow81) / 3 # dropped 7
df2$post_percomp <- (df2$Q2MaincellgroupRow21)
df2 <- mutate(df2, date = lubridate::mdy_hm(CompletedDate, tz = "America/Detroit"))
df2 <- arrange(df2, date)
df2 <- select(df2, student_ID = opdata_username, contains("post"), date)
df2 <- distinct(df2)
df2 <- select(df2, -date)
df2 <- left_join(ps3_f, df2, by = "student_ID")
3. Merging and processing merged data
ps12s <- dplyr::select(ps12_f, student_ID, course_ID, subject, semester, section, int, uv, percomp)
ps3s <- dplyr::select(ps3_f, course_ID, subject, semester, section, int, uv, percomp)
x <- bind_rows(ps12s, ps3s)
x <- as_tibble(x)
d <- bind_rows(ps12_f, ps3_f)
# treatment vs. control for sems 1 and 2
# https://docs.google.com/document/d/1g52pl-0JyEO26bFEJ9aE295dL7oZSOU1wrVXvVbd2lg/edit
d <- mutate(d,
intervention_dummy = case_when(
# Fall 15
course_ID == "AnPhA-S116-01" ~ 1,
course_ID == "AnPhA-S116-02" ~ 0,
course_ID == "BioA-S116-01" ~ 1,
course_ID == "BioA-T116-01" ~ 0,
course_ID == "FrScA-S116-01" ~ 1,
course_ID == "FrScA-S116-02" ~ 0,
course_ID == "FrScA-S116-03" ~ 1,
course_ID == "FrScA-S116-04" ~ 0,
course_ID == "FrScA-T116-01" ~ 0,
course_ID == "OcnA-S116-01" ~ 1,
course_ID == "OcnA-S116-01" ~ 0,
course_ID == "OcnA-S116-03" ~ 1,
course_ID == "OcnA-T116-01" ~ 0,
course_ID == "PhysA-S116-01" ~ 1,
course_ID == "PhysA-T116-01" ~ 0,
# Spring 16
course_ID == "AnPhA-S216-01" ~ 0,
course_ID == "AnPhA-S216-02" ~ 1,
course_ID == "BioA-S216-01" ~ 0,
course_ID == "FrScA-S216-01" ~ 0,
course_ID == "FrScA-S216-02" ~ 1,
course_ID == "FrScA-S216-03" ~ 0,
course_ID == "FrScA-S216-04" ~ 1,
course_ID == "OcnA-S216-01" ~ 0,
course_ID == "OcnA-S216-02" ~ 1,
course_ID == "PhysA-S216-01" ~ 0,
# Spring 17
course_ID == "AnPhA-S217-01" ~ 1,
course_ID == "AnPhA-S217-01" ~ 0,
course_ID == "Bio-S217-01" ~ 1,
course_ID == "FrScA-S217-01" ~ 1,
course_ID == "FrScA-S217-02" ~ 0,
course_ID == "FrScA-S217-02." ~ 0,
course_ID == "FrScA-S217-03" ~ 1,
course_ID == "OcnA-S217-01" ~ 0,
course_ID == "OcnA-S217-02" ~ 1,
course_ID == "OcnA-S217-03" ~ 1,
course_ID == "PhysA-S217-01" ~ 0,
TRUE ~ 0
))
d <- rename(d, pre_int = int, pre_uv = uv, pre_percomp = percomp)
4. Processing all gradebook data
x <- read_csv("RR_S3.csv")
x <- select(x, course_ID = Course_ID, student_ID = CU_Pk1, Item_Position:last_access_date)
x <- rename(x, Grade_Category = Grade_Catagory)
RR_Course_Data <- select(RR_Course_Data, course_ID = CourseSectionOrigID, student_ID = Bb_UserPK, Gradebook_Item:last_access_date)
xx <- bind_rows(RR_Course_Data, x)
# write_csv(RR_Course_Data, "s12_gradebook_data.csv")
5. Merging self-report and gradebook data (not run yet)
d$student_ID <- as.character(d$student_ID)
xx$student_ID <- as.character(xx$student_ID)
df <- left_join(d, xx, by = "student_ID")
6. Pre-post analysis
Using multi-level models by course.
60. Looking first at n’s
d %>%
count(intervention_dummy)
## # A tibble: 2 x 2
## intervention_dummy n
## <dbl> <int>
## 1 0 380
## 2 1 429
d[complete.cases(d), ] %>%
count(intervention_dummy)
## # A tibble: 2 x 2
## intervention_dummy n
## <dbl> <int>
## 1 0 8
## 2 1 110
6A. Just looking at pre-post changes in interest and UV
sjPlot::sjt.lmer(lme4::lmer(post_int ~ intervention_dummy + (1 | course_ID), data = d))
|
|
|
post_int
|
|
|
|
B
|
CI
|
p
|
|
Fixed Parts
|
|
(Intercept)
|
|
4.51
|
3.71 – 5.31
|
<.001
|
|
intervention_dummy
|
|
-0.85
|
-1.80 – 0.11
|
.096
|
|
Random Parts
|
|
σ2
|
|
0.705
|
|
τ00, course_ID
|
|
0.370
|
|
Ncourse_ID
|
|
12
|
|
ICCcourse_ID
|
|
0.344
|
|
Observations
|
|
121
|
|
R2 / Ω02
|
|
.262 / .252
|
sjPlot::sjt.lmer(lme4::lmer(post_uv ~ intervention_dummy + (1 | course_ID), data = d))
|
|
|
post_uv
|
|
|
|
B
|
CI
|
p
|
|
Fixed Parts
|
|
(Intercept)
|
|
3.86
|
3.03 – 4.70
|
<.001
|
|
intervention_dummy
|
|
-0.72
|
-1.70 – 0.27
|
.166
|
|
Random Parts
|
|
σ2
|
|
0.853
|
|
τ00, course_ID
|
|
0.354
|
|
Ncourse_ID
|
|
12
|
|
ICCcourse_ID
|
|
0.293
|
|
Observations
|
|
121
|
|
R2 / Ω02
|
|
.205 / .187
|
6B. With pre-values added
sjPlot::sjt.lmer(lme4::lmer(post_int ~ pre_int + intervention_dummy + (1 | course_ID), data = d))
|
|
|
post_int
|
|
|
|
B
|
CI
|
p
|
|
Fixed Parts
|
|
(Intercept)
|
|
1.24
|
0.13 – 2.35
|
.031
|
|
pre_int
|
|
0.73
|
0.52 – 0.94
|
<.001
|
|
intervention_dummy
|
|
-0.43
|
-1.06 – 0.21
|
.194
|
|
Random Parts
|
|
σ2
|
|
0.535
|
|
τ00, course_ID
|
|
0.078
|
|
Ncourse_ID
|
|
12
|
|
ICCcourse_ID
|
|
0.127
|
|
Observations
|
|
120
|
|
R2 / Ω02
|
|
.421 / .420
|
sjPlot::sjt.lmer(lme4::lmer(post_uv ~ pre_uv + intervention_dummy + (1 | course_ID), data = d))
|
|
|
post_uv
|
|
|
|
B
|
CI
|
p
|
|
Fixed Parts
|
|
(Intercept)
|
|
0.75
|
-0.20 – 1.71
|
.126
|
|
pre_uv
|
|
0.80
|
0.61 – 0.98
|
<.001
|
|
intervention_dummy
|
|
-0.22
|
-0.91 – 0.46
|
.525
|
|
Random Parts
|
|
σ2
|
|
0.556
|
|
τ00, course_ID
|
|
0.115
|
|
Ncourse_ID
|
|
12
|
|
ICCcourse_ID
|
|
0.172
|
|
Observations
|
|
118
|
|
R2 / Ω02
|
|
.457 / .456
|
6C. With all variables added
sjPlot::sjt.lmer(lme4::lmer(post_uv ~ pre_uv + pre_int + pre_percomp + intervention_dummy + (1 | course_ID), data = d))
|
|
|
post_uv
|
|
|
|
B
|
CI
|
p
|
|
Fixed Parts
|
|
(Intercept)
|
|
0.54
|
-0.72 – 1.81
|
.400
|
|
pre_uv
|
|
0.76
|
0.51 – 1.00
|
<.001
|
|
pre_int
|
|
0.04
|
-0.26 – 0.34
|
.802
|
|
pre_percomp
|
|
0.05
|
-0.23 – 0.32
|
.750
|
|
intervention_dummy
|
|
-0.20
|
-0.90 – 0.50
|
.580
|
|
Random Parts
|
|
σ2
|
|
0.565
|
|
τ00, course_ID
|
|
0.118
|
|
Ncourse_ID
|
|
12
|
|
ICCcourse_ID
|
|
0.173
|
|
Observations
|
|
118
|
|
R2 / Ω02
|
|
.459 / .458
|