94 lines
3.0 KiB
R
94 lines
3.0 KiB
R
##############################################################################
|
|
#
|
|
# Purpose:
|
|
# Use pilot project data to calculate power of a full study through simulation
|
|
#
|
|
# Parts:
|
|
# (0) - Setup
|
|
# (1) - Get the pilot data and clean it
|
|
# (2) - Run the model on the pilot data and extract effects
|
|
# (3) - Set up and run the simulation
|
|
# ====> Set variables at the arrows <====
|
|
#
|
|
##############################################################################
|
|
rm(list=ls())
|
|
set.seed(424242)
|
|
|
|
library(readr)
|
|
library(ggplot2)
|
|
|
|
# (1) - Get the pilot data and clean it
|
|
#source('~/Research/tor_wikipedia_edits/handcoded_edits/inter_coder_reliability_ns0.R')
|
|
#source ('/data/users/mgaughan/kkex_data_110823_3')
|
|
data1 <- read_csv('../power_data_111023_mmt.csv',show_col_types = FALSE)
|
|
data2 <- read_csv('../inst_all_packages_full_results.csv')
|
|
#d$nd <- to_logical(d$not.damaging, custom_true=c("Y"))
|
|
#levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors")
|
|
python_labeled <- as.numeric(data2$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$pkg)])
|
|
data1$up.fac.mean <- pmin(python_labeled, same_labeled, na.rm=TRUE)
|
|
data1$milestones <- as.numeric(data1$milestones > 0)
|
|
# (2) - Run the model on the pilot data
|
|
data1$formal.score <- data1$mmt / (data1$milestones/data1$age)
|
|
table(data1$milestones)
|
|
hist(data1$old_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 ~ old_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) < 14 )
|
|
hist(data2$age)
|
|
g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) +
|
|
geom_point() +
|
|
geom_smooth()
|
|
g
|
|
|
|
data2$yearsOld <- data2$age / 365
|
|
|
|
kmodel2 <- lm(up.fac.mean ~ mmt + milestones + yearsOld, data=data2)
|
|
summary(kmodel2)
|
|
|
|
#pilotM <- glm(up.fac.mean ~ ((mmt) / (milestones/age)), # give the anticipated regression a try
|
|
# family=gaussian(link='identity'), data=data1)
|
|
summary(pilotM) #we expect effect sizes on this order
|
|
|
|
pilot.b0 <- coef(summary(pilotM))[1,1]
|
|
pilot.b1 <- coef(summary(pilotM))[2,1]
|
|
pilot.b2 <- coef(summary(pilotM))[3,1]
|
|
pilot.b3 <- coef(summary(pilotM))[4,1]
|
|
|
|
|
|
# (3) - Set up and run the simulation
|
|
|
|
source('powerAnalysis.R') #my little "lib"
|
|
|
|
#====>
|
|
nSims <- 5000 #how many simulations to run
|
|
n <- 100 #a guess for necessary sample size (per group)
|
|
#makeData(10) #DEBUGGING CODE -- you can uncomment this if you want to see it work
|
|
#<====
|
|
|
|
#print("Levels are:")
|
|
#print(levels(d$source))
|
|
powerCheck(n, nSims)
|
|
|
|
#Sample values
|
|
powerCheck(50, 100)
|
|
powerCheck(80, 1000)
|
|
powerCheck(200, 5000)
|