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

demos some changes

Browse Source
This commit is contained in:
Kaylea Champion 2023-11-10 11:22:58 -08:00
parent 343b623891
commit 1a5b698512
1 changed files with 36 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
R/calculatePower.R
View File

@ -15,20 +15,53 @@ rm(list=ls())
set.seed(424242) set.seed(424242)
library(readr) library(readr)
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_110923_mmt.csv',show_col_types = FALSE) data1 <- read_csv('../power_data_110923_mmt.csv',show_col_types = FALSE)
data2 <- read_csv('/data_ext/users/kcz1100/kaylea_dissertation/collabnetXS/raw_data/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"))
#levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors") #levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors")
data1$up.fac.mean <- as.numeric(data2$up.fac.mean[match(data1$pkg, data2$pkg)]) data1$up.fac.mean <- as.numeric(data2$up.fac.mean[match(data1$pkg, data2$pkg)])
data1$milestones <- as.numeric(data1$milestones > 0) + 1 data1$milestones <- as.numeric(data1$milestones > 0) + 1
# (2) - Run the model on the pilot data # (2) - Run the model on the pilot data
pilotM <- glm(up.fac.mean ~ ((mmt) / (milestones/age)), # give the anticipated regression a try data1$formal.score <- data1$mmt / (data1$milestones/data1$age)
family=gaussian(link='identity'), data=data1) table(data1$milestones)
hist(data1$mmt) #inequality of participation
hist(data1$formal.score)
hist(data1$age/365)
kmodel1 <- lm(up.fac.mean ~ mmt, data=data1)
summary(kmodel1)
kmodel1 <- lm(up.fac.mean ~ formal.score, data=data1)
summary(kmodel1)
hist(data1$formal.score)
cor.test(data1$formal.score, data1$up.fac.mean)
cor.test(data1$mmt, data1$up.fac.mean)
cor.test(data1$milestones, data1$up.fac.mean)
cor.test(data1$age, data1$up.fac.mean)
g <- ggplot(data1, aes(x=formal.score, y=up.fac.mean)) +
geom_point() +
geom_smooth()
g
data2 <- subset(data1, (data1$age / 365) < 9 )
hist(data2$age)
g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) +
geom_point() +
geom_smooth()
g
data2$yearsOld <- data2$age / 365
kmodel2 <- lm(up.fac.mean ~ mmt + milestones + yearsOld, data=data2)
summary(kmodel2)
#pilotM <- glm(up.fac.mean ~ ((mmt) / (milestones/age)), # give the anticipated regression a try
# family=gaussian(link='identity'), data=data1)
summary(pilotM) #we expect effect sizes on this order summary(pilotM) #we expect effect sizes on this order
pilot.b0 <- coef(summary(pilotM))[1,1] pilot.b0 <- coef(summary(pilotM))[1,1]