09/15/05William Wu / MS meeting1 Measurement error and measurement model with an example in dietary data.

Slides:



Advertisements
Similar presentations
Gage R&R Estimating measurement components
Advertisements

Research Curriculum Session II –Study Subjects, Variables and Outcome Measures Jim Quinn MD MS Research Director, Division of Emergency Medicine Stanford.
REGRESSION, IV, MATCHING Treatment effect Boualem RABTA Center for World Food Studies (SOW-VU) Vrije Universiteit - Amsterdam.
Tests of Significance for Regression & Correlation b* will equal the population parameter of the slope rather thanbecause beta has another meaning with.
3.2 OLS Fitted Values and Residuals -after obtaining OLS estimates, we can then obtain fitted or predicted values for y: -given our actual and predicted.
Review of the Basic Logic of NHST Significance tests are used to accept or reject the null hypothesis. This is done by studying the sampling distribution.
BIAS AND CONFOUNDING Nigel Paneth. HYPOTHESIS FORMULATION AND ERRORS IN RESEARCH All analytic studies must begin with a clearly formulated hypothesis.
Chance, bias and confounding
Evaluation (practice). 2 Predicting performance  Assume the estimated error rate is 25%. How close is this to the true error rate?  Depends on the amount.
Correcting for measurement error in nutritional epidemiology Ruth Keogh MRC Biostatistics Unit MRC Centre for Nutritional Epidemiology in Cancer Prevention.
Writing a Research Protocol Michael Aronica MD Program Director Internal Medicine-Pediatrics.
What z-scores represent
Sample size computations Petter Mostad
SIMPLE LINEAR REGRESSION
Lecture Inference for a population mean when the stdev is unknown; one more example 12.3 Testing a population variance 12.4 Testing a population.
Chapter 6 Reproducibility: duplicate measurements of the same individual in the same situation and time frame. Validity: comparison of questionnaire data.
Topic 3: Regression.
Using data to tailor a school-based worksite wellness program Stephanie Vecchiarelli, Judith Siegel, Michael Prelip University of California Los Angeles,
SIMPLE LINEAR REGRESSION
Analysis of Individual Variables Descriptive – –Measures of Central Tendency Mean – Average score of distribution (1 st moment) Median – Middle score (50.
Chapter 12 Inferring from the Data. Inferring from Data Estimation and Significance testing.
Impact Evaluation Session VII Sampling and Power Jishnu Das November 2006.
FINAL REPORT: OUTLINE & OVERVIEW OF SURVEY ERRORS
Cover Letters for Survey Research Studies
Validity and Reliability Dr. Voranuch Wangsuphachart Dept. of Social & Environmental Medicine Faculty of Tropical Medicine Mahodil University 420/6 Rajvithi.
SIMPLE LINEAR REGRESSION
Cohort Study.
Lecture 8 Objective 20. Describe the elements of design of observational studies: case reports/series.
Conducting a User Study Human-Computer Interaction.
Modeling errors in physical activity data Sarah Nusser Department of Statistics and Center for Survey Statistics and Methodology Iowa State University.
Understanding Multivariate Research Berry & Sanders.
Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 5 of Data Mining by I. H. Witten, E. Frank and M. A. Hall 報告人:黃子齊
Statistical Methods, part 1 Module 2: Latent Class Analysis of Survey Error Models for measurement errors Dan Hedlin Stockholm University November 2012.
Cross-sectional study
Estimation Bias, Standard Error and Sampling Distribution Estimation Bias, Standard Error and Sampling Distribution Topic 9.
Instructor Resource Chapter 5 Copyright © Scott B. Patten, Permission granted for classroom use with Epidemiology for Canadian Students: Principles,
Chapter 5 Errors In Chemical Analyses Mean, arithmetic mean, and average (x) are synonyms for the quantity obtained by dividing the sum of replicate measurements.
Bias Defined as any systematic error in a study that results in an incorrect estimate of association between exposure and risk of disease. To err is human.
Systematic Review Module 7: Rating the Quality of Individual Studies Meera Viswanathan, PhD RTI-UNC EPC.
SAMPLE SIZE AND POWER Adapted from slides attributed to Patrick S. Romano, MD, MPH Professor of Medicine and Pediatrics Adapted from slides attributed.
Assessing dietary intakes in food environment research: Implications for policy and practice SHARON KIRKPATRICK University of Waterloo JILL REEDY, KEVIN.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
AP Stat Review Descriptive Statistics Grab Bag Probability
Relationship between two variables Two quantitative variables: correlation and regression methods Two qualitative variables: contingency table methods.
Potential Errors In Epidemiologic Studies Bias Dr. Sherine Shawky III.
Controlling for Baseline
7.4 DV’s and Groups Often it is desirous to know if two different groups follow the same or different regression functions -One way to test this is to.
Overview of Study Designs. Study Designs Experimental Randomized Controlled Trial Group Randomized Trial Observational Descriptive Analytical Cross-sectional.
Sean Canavan David Hann Oregon State University The Presence of Measurement Error in Forestry.
General Linear Model.
Chapter 13: Inferences about Comparing Two Populations Lecture 8b Date: 15 th November 2015 Instructor: Naveen Abedin.
Reliability: Introduction. Reliability Session 1.Definitions & Basic Concepts of Reliability 2.Theoretical Approaches 3.Empirical Assessments of Reliability.
Understanding lack of validity: Bias
Hypothesis Testing and Statistical Significance
When  is unknown  The sample standard deviation s provides an estimate of the population standard deviation .  Larger samples give more reliable estimates.
Chapter 11: Test for Comparing Group Means: Part I.
5. Evaluation of measuring tools: reliability Psychometrics. 2011/12. Group A (English)
Analysis of Mismeasured Data David Yanez Department of Biostatistics University of Washington July 5, 2005 Biost/Stat 579.
Bivariate Regression. Bivariate Regression analyzes the relationship between two variables. Bivariate Regression analyzes the relationship between two.
NS 210 – Unit 3 Seminar Interview Techniques Leslie Young MS RD LDN.
Qualitative vs. Quantitative
Reliability and Validity
Multiple Regression Lecture 13 Lecture 12.
Correlation and Simple Linear Regression
Projects: Background, Design, Study Population, Exposure & Outcome Presentations start Continue on and
Correlation and Simple Linear Regression
Chapter 11: Introduction to Hypothesis Testing Lecture 5a
ERRORS, CONFOUNDING, and INTERACTION
Evaluating the Role of Bias
Simple Linear Regression and Correlation
Presentation transcript:

09/15/05William Wu / MS meeting1 Measurement error and measurement model with an example in dietary data

09/15/05William Wu / MS meeting2 Why the established association was not found in my study, or why the findings on the association from similar studies were inconsistent? When we say established association, it means it was well studied, generally acknowledged, and widely cited. Examples: Physical activity and the occurrence of CVDs. NSAID intake and colon cancer Dietary fiber

09/15/05William Wu / MS meeting3 Possible answers to the question Sample size and the power not enough, Measurement error, others

09/15/05William Wu / MS meeting4 Measurement Error The error that arises when a recorded value is not exactly the same as the true value due to a flaw in the measurement process.

09/15/05William Wu / MS meeting5 Two distinguished variation Biological or natural variation (not measurement error), Variation in measurement process (systematic error and random error)

09/15/05William Wu / MS meeting6 Potential causes of measurement error Misuse of tools, Poor choice of measurement tool Lack of training Carelessness Not possible to measure exactly

09/15/05William Wu / MS meeting7 Causes of measurement error in dietary record Underreporting Subjects generally report eating less than they actually do eat. Differential recall Subjects are more likely to recall eating foods that they perceive as healthy than those considered unhealthy. Regression dilution When the object of interest is long-term diet, a measurement on a short-term record of diet measures this with error.

09/15/05William Wu / MS meeting8 Two other often seen terms Selection bias subjects recruited not representative of the target population e.g. Information bias Arising from errors in measuring exposure or disease e.g. exaggerate risk estimate for case subjects.

09/15/05William Wu / MS meeting9 Consequences of measurement error Effect size attenuated measurement error dilutes the effects (referred to as ‘regression dilution bias’) Significance biased measurement error favors the null hypothesis

09/15/05William Wu / MS meeting10 Approaches to reducing measurement error Study design stage Conduct pilot study improve Instrument re-design the questionnaire validate the equipment standardize measurement protocols reproducibility reliability train study personnel, Analytical stage statistical approaches average the repeated measurements measurement model others

09/15/05William Wu / MS meeting11 Measurement model with two indicators Our general question: Y= a + bX* + e where X* is the true score. In reality the X* is not available, instead, we have two rough measurements of X*, say, X1 and X2.

09/15/05William Wu / MS meeting12 Solutions to the regression T here are three ways to address this question: Y = a + bX1 + e Y = a + bX2 + e Y = a + b[(X1+X2)/2] + e Y = a + b1X1 + b2X2 + e

09/15/05William Wu / MS meeting13 Measurement model The question can also be addressed with a better way by building a measurement model which is specified as follows: X1 = X* + e1 X2 = X* + e2 Where X1 and X2 are the two indictors of X* which is unobserved and thus called latent variable. Two assumptions: e1 and e2 are symmetrically distributed about the true scores, and are uncorrelated with each other and X*.

09/15/05William Wu / MS meeting14 Parallelism of the two indicators is specified when repeated measurements with the same method is involved. It is the most restrictive constrain to a measurement model. Parallel of two indicators

09/15/05William Wu / MS meeting15 Measurement model incorporated with structural model The general question thus can be depicted with path diagram as follows: e1e2 X1X2d X* Y

09/15/05William Wu / MS meeting16 Packages for the implementation of the equation SAS proc calis AMOS structural equation model

09/15/05William Wu / MS meeting17 Study Setting Project: The Los Angeles Atherosclerosis Study Study design: Cohort study Study question: Association between dietary fiber intake and atherosclerosis progression. Study population: 700 middle-aged man and women in a company. Outcome: Atherosclerosis progression = yearly enlargement rate of common carotid intima-media thickness (IMT), which was derived from a baseline measurement, and two follow-up measurements with 1.5 years apart.

09/15/05William Wu / MS meeting18 Measurement of dietary intake Dietary data interested: Daily intake of viscous dietary fiber (also classified as water-soluble fiber) and its major component, pectin. Data collection instrument: three days 24-hours recall Measurements: Two measurements, one in baseline and one in 1.5 years follow-up.

09/15/05William Wu / MS meeting19 In this study, we try to estimates the slope of the dependent variable (IMT progression) regressed on the long-term average intake of viscous dietary fiber or pectin which was unobserved, assume that the errors of measurement at each examination were random.

09/15/05William Wu / MS meeting20 Building Measurement model

09/15/05William Wu / MS meeting21 Structural model

09/15/05William Wu / MS meeting22 Model of the example

09/15/05William Wu / MS meeting23 RESULT: Influence of measurement error on the estimates of regression slope relating IMT progression to dietary fiber. The LAAS ( ) ModelRegression slope*P value Viscous fiber Baseline  follow-up  Average of baseline and follow-up  Measurement error corrected  Pectin Baseline  follow-up  Average of baseline and follow-up  Measurement error corrected  * Regression slope is the regression coefficient in the structural model.

09/15/05William Wu / MS meeting24 Questions and Discussion