REALCOM Multilevel models for realistically complex data Measurement errors Multilevel Structural equations Multivariate responses at several levels and.

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

Bayes rule, priors and maximum a posteriori
Handling attrition and non- response in longitudinal data Harvey Goldstein University of Bristol.
Missing data – issues and extensions For multilevel data we need to impute missing data for variables defined at higher levels We need to have a valid.
MCMC estimation in MlwiN
Non response and missing data in longitudinal surveys.
Multilevel modelling short course
Multilevel Multivariate Models with responses at several levels Harvey Goldstein Centre for Multilevel Modelling University of Bristol.
Continued Psy 524 Ainsworth
Statistical Analysis SC504/HS927 Spring Term 2008
Latent normal models for missing data Harvey Goldstein Centre for Multilevel Modelling University of Bristol.
Efficient modelling of record linked data A missing data perspective Harvey Goldstein Record Linkage Methodology Research Group Institute of Child Health.
Probit The two most common error specifications yield the logit and probit models. The probit model results if the are distributed as normal variates,
Brief introduction on Logistic Regression
ECE 8443 – Pattern Recognition LECTURE 05: MAXIMUM LIKELIHOOD ESTIMATION Objectives: Discrete Features Maximum Likelihood Resources: D.H.S: Chapter 3 (Part.
FTP Biostatistics II Model parameter estimations: Confronting models with measurements.
6-1 Introduction To Empirical Models 6-1 Introduction To Empirical Models.
Fast Bayesian Matching Pursuit Presenter: Changchun Zhang ECE / CMR Tennessee Technological University November 12, 2010 Reading Group (Authors: Philip.
Multilevel survival models A paper presented to celebrate Murray Aitkin’s 70 th birthday Harvey Goldstein ( also 70 ) Centre for Multilevel Modelling University.
Objectives (BPS chapter 24)
The General Linear Model. The Simple Linear Model Linear Regression.
Efficient modelling of record linked data A missing data perspective Harvey Goldstein Record Linkage Methodology Research Group Institute of Child Health.
Latent Growth Curve Modeling In Mplus:
Structural Equation Modeling
Clustered or Multilevel Data
Introduction to Linear and Logistic Regression. Basic Ideas Linear Transformation Finding the Regression Line Minimize sum of the quadratic residuals.
1 A MONTE CARLO EXPERIMENT In the previous slideshow, we saw that the error term is responsible for the variations of b 2 around its fixed component 
Structural Equation Modeling Intro to SEM Psy 524 Ainsworth.
Review for Final Exam Some important themes from Chapters 9-11 Final exam covers these chapters, but implicitly tests the entire course, because we use.
Mixture Modeling Chongming Yang Research Support Center FHSS College.
Introduction to Multilevel Modeling Using SPSS
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. Chapter 14 Comparing Groups: Analysis of Variance Methods Section 14.2 Estimating Differences.
Modelling non-independent random effects in multilevel models William Browne Harvey Goldstein University of Bristol.
2 nd Order CFA Byrne Chapter 5. 2 nd Order Models The idea of a 2 nd order model (sometimes called a bi-factor model) is: – You have some latent variables.
Applications The General Linear Model. Transformations.
Introduction Multilevel Analysis
Finding Scientific topics August , Topic Modeling 1.A document as a probabilistic mixture of topics. 2.A topic as a probability distribution.
Modelling non-independent random effects in multilevel models Harvey Goldstein and William Browne University of Bristol NCRM LEMMA 3.
Applied Epidemiologic Analysis - P8400 Fall 2002 Lab 10 Missing Data Henian Chen, M.D., Ph.D.
Linear correlation and linear regression + summary of tests
Multilevel Modeling Software Wayne Osgood Crime, Law & Justice Program Department of Sociology.
Multiple Regression Petter Mostad Review: Simple linear regression We define a model where are independent (normally distributed) with equal.
Calibrated imputation of numerical data under linear edit restrictions Jeroen Pannekoek Natalie Shlomo Ton de Waal.
BUSI 6480 Lecture 8 Repeated Measures.
Regression Analysis Part C Confidence Intervals and Hypothesis Testing
The Impact of Missing Data on the Detection of Nonuniform Differential Item Functioning W. Holmes Finch.
Missing Values Raymond Kim Pink Preechavanichwong Andrew Wendel October 27, 2015.
Lecture 2: Statistical learning primer for biologists
Tutorial I: Missing Value Analysis
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Multiple Linear Regression An introduction, some assumptions, and then model reduction 1.
The SweSAT Vocabulary (word): understanding of words and concepts. Data Sufficiency (ds): numerical reasoning ability. Reading Comprehension (read): Swedish.
Ch 1. Introduction Pattern Recognition and Machine Learning, C. M. Bishop, Updated by J.-H. Eom (2 nd round revision) Summarized by K.-I.
Markov Chain Monte Carlo in R
Stats Methods at IC Lecture 3: Regression.
Missing data: Why you should care about it and what to do about it
Bayesian Semi-Parametric Multiple Shrinkage
BINARY LOGISTIC REGRESSION
Chapter 7. Classification and Prediction
CH 5: Multivariate Methods
Maximum Likelihood & Missing data
How to handle missing data values
CHAPTER 29: Multiple Regression*
Predictive distributions
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
Non response and missing data in longitudinal surveys
Multivariate Methods Berlin Chen
Multivariate Methods Berlin Chen, 2005 References:
Structural Equation Modeling
Classical regression review
Presentation transcript:

REALCOM Multilevel models for realistically complex data Measurement errors Multilevel Structural equations Multivariate responses at several levels and of different types Methodology and examples for: An ESRC research project at Bristol University

General Format MATLAB software –Free standing executable programs –ASCII and worksheet input and output –Graphical menu based input specification –Model equation display –Monitoring of MCMC chains A training manual containing: –Outline of methodology –Worked through examples

Markov Chain Monte Carlo – a quick introduction Bayesian simulation based method that, given starting values samples a new set of parameters at each cycle of a Markov chain This yields a final chain (after discarding a burn- in set) of, say, 5000 sets of values from the (joint) posterior distribution of the parameters This is formed by combining the likelihood based on the data and a prior distribution – typically diffuse. These chains are used for inference – e.g. the mean for a parameter is analogous to the point estimate from a likelihood analysis, intervals etc.

The parameters in this model are the fixed coefficients, the two variances and the level 2 residuals. Consider the simple 2-level model: From suitable starting values eventually the chain settles down so that sampling is from the true posterior distribution and we need to sample sufficient to provide stable estimates – using suitable convergence criteria. All the MATLAB routines use MCMC sampling.

Measurement errors 1.Continuous variables: a simple example: Basic model is: With a model of interest e.g.

Some assumptions we need to make Variance assumed known – or alternatively Reliability: We also need a distribution for true value: An important issue is value for and sensitivity analysis useful – we can also give it a prior.

2. Missclassification errors Assume a binary (0,1) variable, for example whether or not a school pupil is eligible for free school meals (yes=1) Probability of observing a zero (no eligibility), given that the true value is zero, is and the probability of observing a one given that the true value is zero by - likewise we have and We now assume we know these missclassification probabilities – similar target model as before with a binary predictor.

Modelling considerations We can model multivariate continuous measurement errors, but only independent binary missclassifications. We can allow different measurement error variances and covariances for different groups – e.g. gender. In multivariate case we typically need non-zero correlations between measurement errors: Thus, say, if R=0.7 observed correlation = 0.8 then we require measurement error correlation >0.33

An educational example Maths test score related to prior test scores and FSM eligibility. We will look at continuous, correlated and binary measurement errors. Open measurement-error.exe and read file classsize

Summary table for analyses:

Factor analysis and structural equation models Consider a single level factor model where we have several responses on each member of a sample: Where r indexes the response variable and i the person. This is a special kind of multivariate model where we assume the residuals are independent and the covariance between two responses is thus given by A constraint is needed for identifiability and the default is to choose

Extensions- further factors We can add explanatory variables in addition to the (see later) or we can add further factors: As number of factors increases, we require further constraints, typically on loading values. A popular choice is simple structure with each response loading on only 1 factor and non-zero correlations between factors.

Extensions – structural variables We can allow the factors themselves to depend on further variables e.g. Or alternatively, but less commonly

Two level factor models Standard formulation Alternatively But we shall not consider this case

Example – PISA data A survey of reading performance, of 15 year olds in 32 countries by OECD in We use one subscale of 35 items retrieving information and look at France and England. First we shall fit one and two level models assuming responses are Normal – in fact they are binary and ordered but we come to that later. Open structural-equation.exe load pisadata

Binary and ordered responses Assume a binary response z. We will use the idea of a latent Normal distribution. Consider the (factor) model for a single response: Where we observe a positive (=1) response for our binary variable z if y is positive, that is So that we obtain the probit model

Ordered data Consider the cumulative probability of being in one of the lowest s+1 categories of a p category variable - categories numbered from 0 upwards: s=0,…p-2 We extend the binary response model as: Where the define a set of thresholds for the categories. So suppose we have a 3-category variable, then for observed responses

PISA data with binary/ordered responses In fact all the responses are binary except for 4 with 3 ordered categories: C9, C14, C20, and C26 Change these responses and rerun models. Finally fit explanatory variables Country and Gender in structural part of model.

Multivariate models with responses at 2 levels Consider first 2 Normal responses: Superscript indicates level Models are linked via level 2 covariance matrix MCMC algorithm handles missing response data and categorical (binary, ordered and unordered) as well as Normal data. First example is a repeated measures growth curve model

Child heights + adult height Child height as a cubic polynomial with intercept + slope random at level 2

Load growthdata.txt and fit the model Results:

Adult height prediction Suppose we have 2 growth measures: we want a regression prediction of the form This leads to:

Mixed response types and missing data Normal and ordered data already considered in structural equation models We now introduce unordered categorical responses We can also have general Normalising transformations Missing data via imputation is an important application for these models

Unordered categorical responses We have where h indexes the response. For each we assume an underlying latent variable exists and that we have the following model: For identifiability we model p-1 categories and assume. The maximum indicant model: we observe category h for individual i iff. so that Assume p categories where an individual responds to just one.

Multiple imputation – briefly and simply Consider the model of interest (MOI) We turn this into a multivariate response model and obtain residual estimates of (from an MCMC chain) which are missing. Use these to fill in and produce a complete data set. Do this (independently) n (e.g. = 20) times. Fit MOI to each data set and combine according to rules to get estimates and standard errors.

Class size example Load classsize_impute MOI is Normalised exam score as response regressed on pretest score, gender, FSM, class size. 50% level 1 units have missing data. Multivariate model:

MI estimates vs listwise deletion Fixed effects in multivariate model: 50% records MCAR Estimate Listwise (SE)MI (SE): Complete (SE) Post maths (0.088) (0.071) : (0.070) Pre Maths (0.088) (0.071) : (0.071) Gender (0.074) (0.047) : (0.047) FSM (0.159) (0.129) : (0.129) Class size (-30) (0.602) (0.597) : (0.544)

Further extensions Box-Cox normalising transformations: Application to survival data treated as an ordered response when divided into discrete time intervals Combination of measurement errors, structural models and responses at >1 level into a single program Incorporation into MLwiN

General remarks Report back welcome A REALCOM discussion group is under consideration Use with care!