mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

stats analysis from the short paper

Browse Source
This commit is contained in:
mjgaughan 2023-12-05 09:46:31 -06:00
parent 5216ca767c
commit 5dc0406c82
11 changed files with 572 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

512
R/.Rhistory Normal file
View File

@ -0,0 +1,512 @@
data1$new_milestones <- as.numeric(data1$milestones > 0) + 1
# (2) - Run the model on the pilot data
data1$formal.score <- data1$mmt / (data1$old_milestones/data1$age)
table(data1$milestones)
table(data1$old_milestones)
hist(data1$old_mmt, prob=TRUE) #inequality of participation
hist(data1$formal.score)
data1$new_mmt <- data1$mmt - 1
hist(data1$new_mmt, prob=TRUE)
data1$new.age <- as.numeric(cut(data1$age/365, breaks=c(0,9,12,15,17), labels=c(1,2,3,4)))
data1$new.formal.score <- data1$mmt / (data1$new_milestones/data1$new.age)
hist(as.numeric(data1$new.age))
hist(data1$formal.score)
hist(data1$new.formal.score)
fsmodel1 <- lm(up.fac.mean ~ formal.score, data=data1)
summary(kmodel1)
summary(fsmodel1)
kmodel3 <- lm(up.fac.mean ~ formal.score, data=data1)
# (2) - Run the model on the pilot data
data1$formal.score <- data1$mmt / (data1$old_milestones/data1$age)
table(data1$formal.score)
fsmodel1 <- lm(up.fac.mean ~ is.finite(formal.score), data=data1)
summary(fsmodel1)
fsmodel2 <- lm(up.fac.mean ~ new.formal.score, data=data1)
summary(kmodel2)
summary(fsmodel2)
mmtmodel1 <- lm(up.fac.mean ~ mmt, data=data1)
summary(mmtmodel1)
agemodel1 <- lm(up.fac.mean ~ new.age, data=data1)
summary(agemodel1)
msmodel1 <- lm(up.fac.mean ~ old_milestones, data=data1)
summary(msmodel1)
msmodel2 <- lm(up.fac.mean ~ new_milestones, data=data1)
summary(msmodel2)
texreg(list(m1,m2,m3,m4), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: no lang/network measures', 'M2: No language measures', 'M3: No network measures', 'M4: Full model'),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'Uploader Count', 'Did maintainer change?', 'Team proportion', 'Eigenvector Centrality', 'Betweenness Centrality', 'Mean Language Age', 'Package Age : Mean Language Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
install.packages(textref)
install.packages(textreg)
library(textreg)
install.packages("textreg_0.1.tar.gz", repos = NULL, type="source")
install.packages("textreg_0.1.tar.gz", repos = NULL, type="source")
install.packages("textreg_0.1.5.tar.gz", repos = NULL, type="source")
import.packages(tm)
import.package(tm)
import.package("tm")
install.package("tm")
install.packages("tm")
install.packages("nlp")
yes
install.packages("textreg_0.1.5.tar.gz", repos = NULL, type="source")
library(textreg)
texreg(list(m1,m2,m3,m4), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: no lang/network measures', 'M2: No language measures', 'M3: No network measures', 'M4: Full model'),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'Uploader Count', 'Did maintainer change?', 'Team proportion', 'Eigenvector Centrality', 'Betweenness Centrality', 'Mean Language Age', 'Package Age : Mean Language Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
textreg(list(m1,m2,m3,m4), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: no lang/network measures', 'M2: No language measures', 'M3: No network measures', 'M4: Full model'),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'Uploader Count', 'Did maintainer change?', 'Team proportion', 'Eigenvector Centrality', 'Betweenness Centrality', 'Mean Language Age', 'Package Age : Mean Language Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
textreg(list(fsmodel1,fsmodel2), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'Uploader Count', 'Did maintainer change?', 'Team proportion', 'Eigenvector Centrality', 'Betweenness Centrality', 'Mean Language Age', 'Package Age : Mean Language Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
coeff(fsmodel1)
coef(fsmodel1)
textreg(list(fsmodel1,fsmodel2), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
coef(fsmodel2)
textreg(list(fsmodel1,fsmodel2), stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
textreg(list(fsmodel1,fsmodel2), stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2), stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
install.packages(texreg)
install.packages("texreg_1.39.3.tar.gz", repos = NULL, type="source")
library(texreg)
texreg(list(fsmodel1,fsmodel2), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score'),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'test'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, msmodel2, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score', 'M3: original milestones', 'M4: binomial milestones', 'M5: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'test'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, msmodel2, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score', 'M3: original milestones', 'M4: binomial milestones', 'M5: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'test', 'test', 'test', 'test', 'test', ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, msmodel2, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score', 'M3: original milestones', 'M4: binomial milestones', 'M5: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'test', 'test', 'test', 'test', 'test' ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, msmodel2, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M5: binomial milestones', 'M6: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'test', 'test', 'test', 'test', 'test' ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, msmodel2, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M5: binomial milestones', 'M6: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Package Age (years)', 'Relationship to Underproduction', 'test', 'test', 'test', 'test' ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M6: age (grouped)' ),
custom.coef.names=c('Original formality relationship to underproduction', 'Augmented formality relationship to Underproduction', 'MMT relationship to underproduction', 'milestone usage relationship to underproduction', 'age group relationship to underproduction' ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M6: age (grouped)' ),
custom.coef.names=c('Original formality relationship to underproduction', 'Augmented formality relationship to Underproduction', 'MMT relationship to underproduction', 'milestone usage relationship to underproduction', 'age group relationship to underproduction', 'test' ),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M6: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Original formality relationship to underproduction', 'Augmented formality relationship to Underproduction', 'MMT relationship to underproduction', 'Milestone usage relationship to underproduction', 'Age group relationship to underproduction'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
data5 <- subset(data1, is.finite(data1$formal.score))
fsmodel1 <- lm(up.fac.mean ~ formal.score, data=data5)
summary(fsmodel1)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: original formality score', 'M2: augmented formality score','M3: MMT', 'M4: original milestones', 'M6: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Original formality relationship to underproduction', 'Augmented formality relationship to Underproduction', 'MMT relationship to underproduction', 'Milestone usage relationship to underproduction', 'Age group relationship to underproduction'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: orig. formality', 'M2: augm. formality','M3: MMT', 'M4: milestones', 'M6: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Original formality/underproduction', 'Augmented formality/Underproduction', 'MMT/underproduction', 'Milestones / underproduction', 'Age/underproduction'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel1,fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c('M1: orig. formality', 'M2: augm. formality','M3: MMT', 'M4: milestones', 'M5: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Original formality', 'Augmented formality', 'MMT', 'Milestones', 'Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones', 'M4: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Original formality', 'Augmented formality', 'MMT', 'Milestones', 'Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones', 'M4: age (grouped)' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones', 'Age'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
#Sample values
powerCheck(300, 1000)
source('powerAnalysis.R') #my little "lib"
#Sample values
powerCheck(300, 1000)
powerCheck(200, 1000)
powerCheck(250, 1000)
powerCheck(275, 5000)
powerCheck(275, 1000)
source('powerAnalysis.R') #my little "lib"
#Sample values
powerCheck(300, 1000)
powerCheck(275, 1000)
powerCheck(500, 1000)
powerCheck(700, 1000)
powerCheck(7000, 1000)
fsmodel2 <- lm(up.fac.mean ~ new.formal.score + as.factor(new.age), data=data1)
summary(fsmodel2)
mmtmodel1 <- lm(up.fac.mean ~ mmt + as.factor(new.age), data=data1)
summary(mmtmodel1)
mmtmodel1 <- lm(up.fac.mean ~ mmt + as.factor(age), data=data1)
summary(mmtmodel1)
mmtmodel1 <- lm(up.fac.mean ~ mmt + as.factor(new.age), data=data1)
summary(mmtmodel1)
msmodel1 <- lm(up.fac.mean ~ old_milestones + as.factor(new.age), data=data1)
summary(msmodel1)
fsmodel2 <- lm(up.fac.mean ~ new.formal.score + as.factor(new.age), data=data1)
summary(fsmodel2)
texreg(list(fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1, agemodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones', 'test'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones', 'test'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1), omit.coef = 'factor', stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
source('powerAnalysis.R') #my little "lib"
powerCheck(250, 1000)
powerCheck(275, 1000)
#Sample values
powerCheck(300, 1000)
summary(mmtmodel1)
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones', 'age 2', 'age 3', 'age 4'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
mmtmodel1 <- lm(up.fac.mean ~ mmt + as.factor(new.age), data=data1)
msmodel1 <- lm(up.fac.mean ~ old_milestones + as.factor(new.age), data=data1)
fsmodel2 <- lm(up.fac.mean ~ new.formal.score, data=data1)
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Milestones', 'age 2', 'age 3', 'age 4'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'age 2', 'age 3', 'age 4', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
summary(msmodel1)
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Age-2', 'Age-3', 'Age-4', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g
library(ggplot2)
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g
msmodel1 <- lm(up.fac.mean ~ old_milestones + as.factor(new.age), data=data1)
summary(msmodel1)
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()+
scale_color_brewer(palette="Dark2")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_brewer(palette="Dark2")
g + scale_color_viridis_b()
g + scale_color_viridis_d()
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b()
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b()
g + scale_color_viridis_b() scale_fill_continuous(name = "New Legend Title")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b() scale_fill_continuous(name = "New Legend Title")
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b() + scale_fill_continuous(name = "New Legend Title")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b() + scale_fill_continuous(name = "New Legend Title")
g + scale_color_viridis_b() + scale_color_continuous(name = "New Legend Title")
g + scale_color_viridis_b() + scale_color_continuous(name = "Age Group")
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b() + scale_color_continuous(name = "Age Group")
g
g + scale_color_viridis_b(name = "Age Group")
g + scale_color_viridis_b(name = "Age Group", labels = c('1', '2', '3', '4'))
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_viridis_b(name = "Age Group", labels = c('1', '2', '3', '4'))
g
g + scale_fill_viridis_b(name = "Age Group", labels = c('1', '2', '3', '4'))
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_fill_viridis_b(name = "Age Group", labels = c('1', '2', '3', '4'))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_fill_viridis_b(name = "Age Group")
g
g + scale_fill_viridis_b(name = "Age Group")
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_colour_viridis_b(name = "Age Group")
g + scale_fill_continuous(name = "Age Group")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_fill_continuous(name = "Age Group")
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor")
g + scale_fill_continuous(name = "Age Group")
g + scale_fill_continuous(name = "Age Group", labels=c("Woman", "Man"))
g + scale_color_continuous(name = "Age Group", labels=c("Woman", "Man"))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_continuous(name = "Age Group", labels=c("Woman", "Man"))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g + scale_color_continuous(type = "viridis", name = "Age Group", labels=c("Woman", "Man"))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels="0-9y", "9-12y", "12-15y", "15-17y")
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y"))
g
+ theme(legend.position = c(0.8, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.8, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.1))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
summary(mmtmodel1)
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=as.factor(new.age))+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_continuous(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=as.factor(new.age))+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_discrete(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_identity(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=new.age)+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_identity(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
aes(x=mmt, y=up.fac.mean, color=round(new.age))+
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw() +
scale_color_identity(type = "viridis", name = "Age Group", labels=c("0-9y", "9-12y", "12-15y", "15-17y")) +
theme(legend.position = c(0.1, 0.2))
g
g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() +
geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g

4
R/EDA.R
View File

@ -1,7 +1,7 @@
library(dplyr) library(dplyr)
df<-read.csv('~/Research/kkex_repo/power_data_111023_mmt.csv') df<-read.csv('../power_data_111023_mmt.csv')
df1 <- read.csv('~/Research/kkex_repo/inst_all_packages_full_results.csv') df1 <- read.csv('../inst_all_packages_full_results.csv')
hist(df$age/365) #there's a big bump at 9 years, why? hist(df$age/365) #there's a big bump at 9 years, why?
hist(df$contributors) #skewed hist(df$contributors) #skewed

66
R/calculatePower.R
View File

@ -20,6 +20,7 @@ library(ggplot2)
# (1) - Get the pilot data and clean it # (1) - Get the pilot data and clean it
#source('~/Research/tor_wikipedia_edits/handcoded_edits/inter_coder_reliability_ns0.R') #source('~/Research/tor_wikipedia_edits/handcoded_edits/inter_coder_reliability_ns0.R')
#source ('/data/users/mgaughan/kkex_data_110823_3') #source ('/data/users/mgaughan/kkex_data_110823_3')
data1 <- read_csv('../power_data_111023_mmt.csv',show_col_types = FALSE) data1 <- read_csv('../power_data_111023_mmt.csv',show_col_types = FALSE)
data2 <- read_csv('../inst_all_packages_full_results.csv') data2 <- read_csv('../inst_all_packages_full_results.csv')
#d$nd <- to_logical(d$not.damaging, custom_true=c("Y")) #d$nd <- to_logical(d$not.damaging, custom_true=c("Y"))
@ -27,45 +28,62 @@ data2 <- read_csv('../inst_all_packages_full_results.csv')
python_labeled <- as.numeric(data2$up.fac.mean[match(paste('python',tolower(data1$pkg), sep = "-"), data2$pkg)]) python_labeled <- as.numeric(data2$up.fac.mean[match(paste('python',tolower(data1$pkg), sep = "-"), data2$pkg)])
same_labeled <- as.numeric(data2$up.fac.mean[match(tolower(data1$pkg), data2$pkg)]) same_labeled <- as.numeric(data2$up.fac.mean[match(tolower(data1$pkg), data2$pkg)])
data1$up.fac.mean <- pmin(python_labeled, same_labeled, na.rm=TRUE) data1$up.fac.mean <- pmin(python_labeled, same_labeled, na.rm=TRUE)
data1$milestones <- as.numeric(data1$milestones > 0) + 1 data1$old_milestones <- data1$milestones
data1$new_milestones <- as.numeric(data1$milestones > 0) + 1
# (2) - Run the model on the pilot data # (2) - Run the model on the pilot data
data1$formal.score <- data1$mmt / (data1$milestones/data1$age) data1$formal.score <- data1$mmt / (data1$old_milestones/data1$age)
table(data1$milestones) table(data1$formal.score)
hist(data1$old_mmt, prob=TRUE) #inequality of participation hist(data1$old_mmt, prob=TRUE) #inequality of participation
hist(data1$formal.score) hist(data1$formal.score)
hist(data1$age/365) hist(data1$age/365)
data1$new_mmt <- data1$mmt - 1 data1$new_mmt <- data1$mmt - 1
hist(data1$new_mmt, prob=TRUE) hist(data1$new_mmt, prob=TRUE)
data3 <- subset(data1, data1$old_milestones > 0 )
data3$formal.score <- data3$mmt / (data3$old_milestones/data3$age)
data1$new.age <- as.numeric(cut(data1$age/365, breaks=c(0,9,12,15,17), labels=c(1,2,3,4))) data1$new.age <- as.numeric(cut(data1$age/365, breaks=c(0,9,12,15,17), labels=c(1,2,3,4)))
data1$formal.score <- data1$mmt / (data1$milestones/data1$new.age) data1$new.formal.score <- data1$mmt / (data1$new_milestones/data1$new.age)
hist(as.numeric(data1$new.age)) hist(as.numeric(data1$new.age))
table(data1$formal.score) table(data1$new.age)
hist(data1$formal.score) hist(data1$new.formal.score)
kmodel1 <- lm(up.fac.mean ~ mmt, data=data1) data5 <- subset(data1, is.finite(data1$formal.score))
summary(kmodel1) mmtmodel1 <- lm(up.fac.mean ~ mmt + as.factor(new.age), data=data1)
kmodel1 <- lm(up.fac.mean ~ new_mmt, data=data1) summary(mmtmodel1)
summary(kmodel1) agemodel1 <- lm(up.fac.mean ~ new.age, data=data1)
kmodel1 <- lm(up.fac.mean ~ new.age, data=data1) summary(agemodel1)
summary(kmodel1) msmodel1 <- lm(up.fac.mean ~ old_milestones + as.factor(new.age), data=data1)
kmodel1 <- lm(up.fac.mean ~ milestones, data=data1) summary(msmodel1)
summary(kmodel1) msmodel2 <- lm(up.fac.mean ~ new_milestones, data=data1)
summary(msmodel2)
fsmodel1 <- lm(up.fac.mean ~ formal.score, data=data5)
summary(fsmodel1)
t.test(data3$formal.score)
fsmodel2 <- lm(up.fac.mean ~ new.formal.score, data=data1)
summary(fsmodel2)
hist(data1$formal.score) hist(data1$formal.score)
cor.test(data1$formal.score, data1$up.fac.mean) cor.test(data1$formal.score, data1$up.fac.mean)
cor.test(data1$mmt, data1$up.fac.mean) cor.test(data1$mmt, data1$up.fac.mean)
cor.test(data1$milestones, data1$up.fac.mean) cor.test(data1$milestones, data1$up.fac.mean)
cor.test(data1$age, data1$up.fac.mean) cor.test(data1$age, data1$up.fac.mean)
g <- ggplot(data1, aes(x=new_mmt, y=up.fac.mean)) + g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
geom_point() + geom_point() +
geom_smooth() geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g
g g
data2 <- subset(data1, (data1$age / 365) < 14 ) data2 <- subset(data1, (data1$age / 365) < 14 )
hist(floor(data2$age)) hist(floor(data2$age))
g <- ggplot(data2, aes(x=mmt, y=up.fac.mean)) + g <- ggplot(data2, aes(x=mmt, y=up.fac.mean)) +
geom_point() + geom_point() +
geom_smooth() geom_smooth() +
xlab("MMT") +
ylab("Underproduction Factor") +
theme_bw()
g g
data2$yearsOld <- floor(data2$age / 365) data2$yearsOld <- floor(data2$age / 365)
@ -105,16 +123,22 @@ n <- 100 #a guess for necessary sample size (per group)
#makeData(10) #DEBUGGING CODE -- you can uncomment this if you want to see it work #makeData(10) #DEBUGGING CODE -- you can uncomment this if you want to see it work
#<==== #<====
texreg(list(fsmodel2, mmtmodel1, msmodel1), stars=NULL, digits=2,
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Age-2', 'Age-3', 'Age-4', 'Milestones'),
use.packages=FALSE, table=FALSE, ci.force = TRUE)
coef(fsmodel1)
#print("Levels are:") #print("Levels are:")
#print(levels(d$source)) #print(levels(d$source))
powerCheck(n, nSims) powerCheck(n, nSims)
#powerCheck2(n, nSims) like doesn't really work #powerCheck2(n, nSims) like doesn't really work
#Sample values #Sample values
powerCheck(100, 1000)
powerCheck(200, 1000)
powerCheck(300, 1000) powerCheck(300, 1000)
powerCheck(275, 1000)
powerCheck(7000, 1000)
powerCheck2(50, 1000) powerCheck2(50, 1000)
powerCheck2(200, 1000) powerCheck2(75, 1000)
powerCheck2(500, 1000) powerCheck2(900, 1000)

BIN
R/formal-underprod-ggplot.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 53 KiB

BIN
R/mess-mmt-ggplot.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 107 KiB

BIN
R/mmt-underprod-ggplot.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 48 KiB

BIN
R/newmmt-underprod-plot.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 65 KiB

7
R/powerAnalysis.R
View File

@ -37,7 +37,8 @@ makeDataNew2 <- function(n) {
tDF <- data.frame( tDF <- data.frame(
## don't sim the outcome ## don't sim the outcome
#up.fac.mean=rnorm(n=n, mean=-0.1296376, sd=1.479847), # up.fac.mean #up.fac.mean=rnorm(n=n, mean=-0.1296376, sd=1.479847), # up.fac.mean
formal.score=rlnorm(n=n, mean=6.220282, sd = 2.544058) # formal.score #formal.score=rlnorm(n=n, mean=6.220282, sd = 2.544058) # formal.score
formal.score=rbeta(n=n, 1, 3) * 10000
) )
tDF[is.na(tDF) | tDF=="Inf"] = NA tDF[is.na(tDF) | tDF=="Inf"] = NA
#sDF <- melt(tDF, id.vars = 0) #AKA the index is the unique id, as far as that goes #sDF <- melt(tDF, id.vars = 0) #AKA the index is the unique id, as far as that goes
@ -58,7 +59,7 @@ powerCheck <- function(n, nSims) { #run a power calculation on the dataset given
## outcome goes here --v ## outcome goes here --v
# e.g. simData$up.fac.mean <- (usefuleffsizeA * mmt) + (usefuleffsizeB * milestones) + rnorm(n=1, mean=0, sd=1) ##plus some noise # e.g. simData$up.fac.mean <- (usefuleffsizeA * mmt) + (usefuleffsizeB * milestones) + rnorm(n=1, mean=0, sd=1) ##plus some noise
#simData$up.fac.mean <- (-2.075 * simData$mmt) + (0.4284 * simData$milestones) + rnorm(n=1, mean=0, sd=1) #simData$up.fac.mean <- (-2.075 * simData$mmt) + (0.4284 * simData$milestones) + rnorm(n=1, mean=0, sd=1)
simData$up.fac.mean <- (-2.0745 * simData$new_mmt) + (0.4284 * simData$milestones) + rnorm(n=n, mean=0, sd=1) simData$up.fac.mean <- (-1.38 * simData$new_mmt) + (0.40 * simData$milestones) + rnorm(n=n, mean=0, sd=1)
#have updated for kkex through here, now need to look at the underproduction work #have updated for kkex through here, now need to look at the underproduction work
#m1.sim <- lm(up.fac.mean ~ ((mmt)/ (milestones/age)), data=simData) #m1.sim <- lm(up.fac.mean ~ ((mmt)/ (milestones/age)), data=simData)
## could leave age out for now? ## could leave age out for now?
@ -88,7 +89,7 @@ powerCheck2 <- function(n, nSims) { #run a power calculation on the dataset give
#have updated for kkex through here, now need to look at the underproduction work #have updated for kkex through here, now need to look at the underproduction work
#m1.sim <- lm(up.fac.mean ~ ((mmt)/ (milestones/age)), data=simData) #m1.sim <- lm(up.fac.mean ~ ((mmt)/ (milestones/age)), data=simData)
## outcome goes here --v ## outcome goes here --v
simData$up.fac.mean <- (0.5 * simData$formal.score) + rnorm(1, mean=0, sd=1) ##plus some noise simData$up.fac.mean <- (0.00017 * simData$formal.score) + rnorm(n, mean=0, sd=1) ##plus some noise
m1.sim <- lm(up.fac.mean ~ formal.score, data=simData) m1.sim <- lm(up.fac.mean ~ formal.score, data=simData)
p0 <- coef(summary(m1.sim))[1,4] p0 <- coef(summary(m1.sim))[1,4]
p1 <- coef(summary(m1.sim))[2,4] p1 <- coef(summary(m1.sim))[2,4]

BIN
R/texreg_1.39.3.tar.gz Normal file
View File

Binary file not shown.

BIN
R/textreg_0.1.5.tar.gz Normal file
View File

Binary file not shown.

8
kkex-github-api-key.rtf Normal file
View File

@ -0,0 +1,8 @@
{\rtf1\ansi\ansicpg1252\cocoartf2708
\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
{\colortbl;\red255\green255\blue255;}
{\*\expandedcolortbl;;}
\margl1440\margr1440\vieww11520\viewh8400\viewkind0
\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
\f0\fs24 \cf0 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}