From 27856dfd2dca3eed4eaac28689b5746f74d006aa Mon Sep 17 00:00:00 2001
From: mjgaughan <mgaughan@proton.me>
Date: Tue, 14 Nov 2023 22:54:32 -0600
Subject: [PATCH] binning age and trying to figure out power

---
 R/calculatePower.R | 11 +++++++++--
 R/powerAnalysis.R  |  3 ++-
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/R/calculatePower.R b/R/calculatePower.R
index 90be49f..669addf 100644
--- a/R/calculatePower.R
+++ b/R/calculatePower.R
@@ -34,12 +34,19 @@ table(data1$milestones)
 hist(data1$old_mmt) #inequality of participation
 hist(data1$formal.score)
 hist(data1$age/365)
+
+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)
+hist(as.numeric(data1$new.age))
+table(data1$formal.score)
 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)
+kmodel1 <- lm(up.fac.mean ~ new.age, 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)
@@ -52,13 +59,13 @@ g <- ggplot(data1, aes(x=mmt, y=up.fac.mean)) +
 g
 
 data2 <- subset(data1, (data1$age / 365) < 14 )
-hist(data2$age)
+hist(floor(data2$age))
 g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) +
   geom_point() +
   geom_smooth()
 g
 
-data2$yearsOld <- data2$age / 365
+data2$yearsOld <- floor(data2$age / 365)
 
 kmodel2 <- lm(up.fac.mean ~ mmt + milestones + age, data=data1)
 kmodel5 <- lm(up.fac.mean ~ mmt + milestones, data=data1)
diff --git a/R/powerAnalysis.R b/R/powerAnalysis.R
index 8eb0c44..aab5f18 100644
--- a/R/powerAnalysis.R
+++ b/R/powerAnalysis.R
@@ -55,6 +55,7 @@ powerCheck <- function(n, nSims) { #run a power calculation on the dataset given
     simData <- makeDataNew(n)       # make some data
     ## outcome goes here --v
     # 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 * simData$mmt) + (1.5 * simData$milestones) + rnorm(n=1, mean=0, sd=1)
     #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)
     ## could leave age out for now?
@@ -84,7 +85,7 @@ 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
     #m1.sim <- lm(up.fac.mean ~ ((mmt)/ (milestones/age)), data=simData)
     ## outcome goes here --v
-    ## e.g. simData$up.fac.mean <- (usefuleffsizeC * formal.score) + rnorm(1, mean=0, sd=1) ##plus some noise
+    simData$up.fac.mean <- (0.5 * simData$formal.score) + rnorm(1, mean=0, sd=1) ##plus some noise
     m1.sim <- lm(up.fac.mean ~ formal.score, data=simData)
     p0 <- coef(summary(m1.sim))[1,4] 
     p1 <- coef(summary(m1.sim))[2,4]