Tim Bates tbates

Models

Structural Equation Model

RAM or LISREL model where the entries of A and S are numeric

Extended SEM

Model in which the RAM equivalent of A and S entries may be arbitrary algebras.

Definition variable

Any value in an SEM that is replaced with a person-specific value such that it is different for every row or person.

Multilevel model

Relational SEM (by analogy to the way in which a relational database links values in different tables. How OpenMx implements mulit-level

Item Response Theory

Haimovitz, K., & Dweck, C. S. (2016). What Predicts Children's Fixed and Growth Intelligence Mind-Sets? Not Their Parents' Views of Intelligence but Their Parents' Views of Failure. Psychological Science. doi:10.1177/0956797616639727

    
require(umx)
data = sem::readMoments(file = "", diag = TRUE)
1
.29	1
.29	-.06	1
.24	.17	-.07	1

List of Topics for OpenMx Workshop

Re-Introduction to SEM

Calculation of Linear Combinations
Notions of Path Analysis

Introduction to the OpenMx Package

Loading in the Package
Basic Functions in the Package
Optimizer choice

Univariate and Bivariate Regression

This is a page of example models. To learn about installing click here, to learn about path-based model syntax click here.

Three basic methods of modeling supported in OpenMx

Path analysis
RAM - LISREL
Matrix algebra

Confirmatory Factor Analysis

One factor models
Multiple factor models

	# ================================================================ #
	# = Task: Write a 1-paragraph summary of your thesis experiment, #
	# = first in 1st person active, then in 3rd person passive #
	# ================================================================ #

	# Rated objectivity of text
	objectivity1stPerson = c(7, 6.5, 7.2, 6, 6);
	objectivity3rdPerson = c(9, 8.5, 8.0, 8, 8)
	t.test(one, two, paired= TRUE, alt= "less")
	# Mean difference: -1.76 [-Inf -1.25] (t(4) = -7.3, p = <.001)

	# ============================
	# = How heritable is height? =
	# ============================
	require(umx)

	data(twinData) # ?twinData from Australian twins.
	# Pick the variables
	selDVs = c("ht1", "ht2")
	mzData <- twinData[twinData$zygosity %in% "MZFF", ]
	dzData <- twinData[twinData$zygosity %in% "DZFF", ]

	library("umx")
	con <- url("https://www.dropbox.com/s/r9e3om73viquzfq/disc.rda?raw=1")
	print(load(con)); close(con)
	manifests = c("q1", "q2", "q3", "q4", "q5", "q6", "q7")
	latents <- c("F1", "F2") # 2 factors

	m1 <- mxModel("twoFactors", type="RAM", manifestVars = manifests, latentVars = latents,
	mxPath("F1", to = manifests),
	mxPath("F2", to = manifests),
	mxPath(latents, arrows = 2, free = FALSE, values = 1),

	data(demoOneFactor)
	manifests <- names(demoOneFactor)
	latents <- c("G1", "G2")

	fit2 <- mxRun(mxModel("Two Factor", type="RAM",
	manifestVars = manifests, latentVars = latents,
	mxPath(from = latents[1], to=manifests[1:3]),
	mxPath(from = latents[2], to=manifests[4:5]),
	mxPath(from = manifests, arrows = 2),
	mxPath(from = latents, arrows = 2, free = FALSE, values = 1.0),

	# mate ~/.R/Makevars
	# The following statements are required to use the clang4 binary
	CC=/usr/local/clang4/bin/clang
	CXX=/usr/local/clang4/bin/clang++
	CXX1X=/usr/local/clang4/bin/clang++
	CXX98=/usr/local/clang4/bin/clang++
	CXX11=/usr/local/clang4/bin/clang++
	CXX14=/usr/local/clang4/bin/clang++
	CXX17=/usr/local/clang4/bin/clang++
	LDFLAGS=-L/usr/local/clang4/lib

	These code snippets have been tested on R 3.1.0 and Mac OS 10.9.3. They presumably do not work on R 2.X!

	## Enter these commands in the Mac OS Terminal

	# use faster vecLib library
	cd /Library/Frameworks/R.framework/Resources/lib
	ln -sf /System/Library/Frameworks/Accelerate.framework/Frameworks/vecLib.framework/Versions/Current/libBLAS.dylib libRblas.dylib

	# return to default settings
	cd /Library/Frameworks/R.framework/Resources/lib