Hause Lin hauselin

Using Git

	############################################################################
	# #
	# Excluding participants who participated in previous studies #
	# By Arnoud Plantinga, based on Gabriele Paolacci's Excel solution #
	# #
	# Instructions (Note: edit only the non-indented lines): #
	# #
	# 1. Create a qualification (e.g., "Study 1"; keep in mind that the name #
	# will be visible to Workers) in MTurk/Manage/Qualification Types #
	# #

	#for tutorial, see https://rpubs.com/hauselin/outliersDetect
	#clean vector using Z-score cut-off method; return a vector with outliers = replace (default is NA)
	outliersZ <- function(data, zCutOff = 1.96, replace = NA, values = FALSE, digits = 2) {
	#compute standard deviation (sample version n = n [not n-1])
	stdev <- sqrt(sum((data - mean(data, na.rm = T))^2, na.rm = T) / sum(!is.na(data)))
	#compute absolute Z values for each value
	absZ <- abs(data - mean(data, na.rm = T)) / stdev
	#subset data that has absZ greater than the zCutOff and replace them with replace
	#can also replace with other values (such as max/mean of data)
	data[absZ > zCutOff] <- replace

	#function to read raw data from Qualtrics
	cleanQualtrics <- function(csvFile, rowAsHeader, skipRows) {
	#this function assumes that you have named your
	#Qualtrics questions properly when setting up the survey;
	#if questions are properly named, then the first row
	#will be most informative and suitable for use as column names
	#read.csv sets header = T by default; stringsAsFactor set to FALSE to ensure strings aren't converted to factors
	QualtricsRaw <- read.csv(csvFile, header = F, stringsAsFactors = F)
	#row 1 contains the strings that we'd like to use as column names; select row 1 and turn them into characters
	colNames <- as.character(QualtricsRaw[rowAsHeader,])

	data <- structure(list(id = structure(c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
	2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L,
	5L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L,
	8L, 9L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L,
	11L, 11L, 12L, 12L, 12L, 12L, 12L, 13L, 13L, 13L, 13L, 13L, 14L,
	14L, 14L, 14L, 14L, 15L, 15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L,
	16L, 17L, 17L, 17L, 17L, 17L, 18L, 18L, 18L, 18L, 18L, 19L, 19L,
	19L, 19L, 19L, 20L, 20L, 20L, 20L, 20L, 21L, 21L, 21L, 21L, 21L,
	22L, 22L, 22L, 22L, 22L, 23L, 23L, 23L, 23L, 23L, 24L, 24L, 24L,
	24L, 24L, 25L, 25L, 25L, 25L, 25L, 26L, 26L, 26L, 26L, 26L, 27L,

	#function to compute R2s in logistic regression
	logisticR2s <- function(logisticModel) {
	modelDeviance <- logisticModel$deviance
	nullDeviance <- logisticModel$null.deviance
	n <- length(logisticModel$fitted.values)

	R2HosmerLemeshow <- 1 - modelDeviance / nullDeviance
	R2CoxSnell <- 1 - exp((modelDeviance - nullDeviance) / n)
	R2Nagelkerke <- R2CoxSnell / (1 - exp( - (nullDeviance / n)))

	summarySE2 <- function (data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95) {
	library(data.table)
	data <- data.table(data)

	length2 <- function(x, na.rm = FALSE) {
	if (na.rm)
	sum(!is.na(x))
	else length(x)
	}

	# see also seWithin function in hausekeep package
	# https://hauselin.github.io/hausekeep/reference/seWithin.html
	summarySE2 <- function (data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95) {
	library(data.table)
	data <- data.table(data)

	length2 <- function(x, na.rm = FALSE) {
	if (na.rm)
	sum(!is.na(x))
	else length(x)

	def simulate(simulations=1000, n=500, quantile=0.80):

	correlations = np.zeros(simulations)

	for i in range(simulations):

	data = {"personality": np.random.randn(
	n), "attract": np.random.randn(n)}
	df = pd.DataFrame(data)