bfoste01

##     fancyaxis: Draw axis which shows minimum, maximum, quartiles
##                 and mean
##
##     Copyright (C) 2005 Steven J. Murdoch <http://www.cl.cam.ac.uk/users/sjm217/>
##
##     This program is free software; you can redistribute it and/or modify
##     it under the terms of the GNU General Public License as published by
##     the Free Software Foundation; either version 2 of the License, or
##     (at your option) any later version.
##

bfoste01

# credit: https://raw.githubusercontent.com/bearloga/Quartile-frame-Scatterplot/master/qfplot.R

library(ggplot2) # by Hadley Wickham
library(grid) # Required for the special axes.

qfplot <- function(x,y,...) {
	# We use margins for a cleaner graph.
	# They are calculated as 5% of the range.
	# Feel free to play around with these (10% works well too).
	y.margin <- 0.05 * (max(y)-min(y))

bfoste01

#addmargins(table) # for freq table reference and input
bayes.fisher <- function(y1, n1, y2, n2) {
  # SIMULATION
  I = 10000 # simulations
  theta1 = rbeta(I, y1+1, (n1-y1)+1)  
  theta2 = rbeta(I, y2+1, (n2-y2)+1)
  diff = theta1-theta2  # simulated diffs
  
  # OUTPUT
  quantiles = quantile(diff,c(0.005,0.025,0.5,0.975,0.995))

bfoste01

rise$PEduc <- factor(rise$PEduc, levels = c(1:7), labels = c("No Formal Schooling", "Some Elementary School",
  "Completed Elementary School", "Some Middle and High School", "Competed High School Diploma or GED",
  "Some College", "Completed 4-Year Degree or Higher"))

bfoste01

#----------------Structural Model--------------#
# Monte Carlo (MC) Study with a Simple CFA w/no missing data
# The idea with this MC study is to specify a theoretical model,
# by this I mean you input the hypothesized parameter estimates
# or estimates from a model you have already run.
# The Monte Carlo aspect means to examine the variability
# in the parameter estimates and fit statistics. 
# MC studies are an important element to establish
# power in a study. 
#-----MC Study of Uncertainty in Parameter Estimates-----#

bfoste01

#Fun stuff with plyr
#-------------------
#plyr .data, .variables to split on and .fun function applied
#understand the naming conventions of plyr with the first 2 letters
#e.g., ddply dd= split dataframe apply function out dataframe
#e.g., dlply dl = split dataframe apply function out list
#d = dataframe
#l = list
#a = array
#-------------------

bfoste01

#get variable names for mtcars dataset in rbase
colnames(mtcars)
#if yow want to recode variables the lazy way
fix(mtcars) #downside is that it isn't hard coded, and therefore not reproducible
#use the reshape package
library(reshape)
test <- rename(mtcars, c(disp="renamedisp")) #reproducible

bfoste01

#create artifical data to emulate SEM model fit statistics

chiSq <- 1600
df <- 780
p <- 0.95
CFI <- 0.95
TLI <- 0.95 
RMSEA <- 0.04
LOWRMSEA <- 0.03
HIGHRMSEA <- 0.04

bfoste01

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console