How to use a covariate to get a more sensitive analysis

Slides:



Advertisements
Similar presentations
Topic 12: Multiple Linear Regression
Advertisements

Regression Bivariate Multivariate. Simple Regression line – line of best fit Ŷ = a + bX The mean point is always on the line Y is the criterion variable.
Analysis of covariance Experimental design and data analysis for biologists (Quinn & Keough, 2002) Environmental sampling and analysis.
Model Adequacy Checking in the ANOVA Text reference, Section 3-4, pg
Linear regression models
1-1 Regression Models  Population Deterministic Regression Model Y i =  0 +  1 X i u Y i only depends on the value of X i and no other factor can affect.
Be humble in our attribute, be loving and varying in our attitude, that is the way to live in heaven.
ANCOVA Workings of ANOVA & ANCOVA ANCOVA, Semi-Partial correlations, statistical control Using model plotting to think about ANCOVA & Statistical control.
Stat Today: General Linear Model Assignment 1:
Lecture 2 zLast: Sections (Read these) zToday: Quick Review of sections 1.4, 1.6, 1.7 and 1.9 with examples zWill not cover section 1.5 zNext Day:
Stat Today: Multiple comparisons, diagnostic checking, an example After these notes, we will have looked at (skip figures 1.2 and 1.3, last.
Quantitative Business Analysis for Decision Making Simple Linear Regression.
1 1 Slide Simple Linear Regression Chapter 14 BA 303 – Spring 2011.
Regression Analysis Regression analysis is a statistical technique that is very useful for exploring the relationships between two or more variables (one.
Relationship of two variables
ALISON BOWLING THE GENERAL LINEAR MODEL. ALTERNATIVE EXPRESSION OF THE MODEL.
Analysis of Covariance, ANCOVA (GLM2)
Multivariate Analysis. One-way ANOVA Tests the difference in the means of 2 or more nominal groups Tests the difference in the means of 2 or more nominal.
Multiple Linear Regression. Purpose To analyze the relationship between a single dependent variable and several independent variables.
Regression. Population Covariance and Correlation.
Be humble in our attribute, be loving and varying in our attitude, that is the way to live in heaven.
Multiple Regression BPS chapter 28 © 2006 W.H. Freeman and Company.
Inference for regression - More details about simple linear regression IPS chapter 10.2 © 2006 W.H. Freeman and Company.
Simple Linear Regression ANOVA for regression (10.2)
How to use a covariate to get a more sensitive analysis.
Problem 3.26, when assumptions are violated 1. Estimates of terms: We can estimate the mean response for Failure Time for problem 3.26 from the data by.
A medical researcher wishes to determine how the dosage (in mg) of a drug affects the heart rate of the patient. DosageHeart rate
Analysis of Covariance (ANCOVA)
3.2 - Least- Squares Regression. Where else have we seen “residuals?” Sx = data point - mean (observed - predicted) z-scores = observed - expected * note.
Chapter 6 Simple Regression Introduction Fundamental questions – Is there a relationship between two random variables and how strong is it? – Can.
Categorical Independent Variables STA302 Fall 2013.
ANCOVA. What is Analysis of Covariance? When you think of Ancova, you should think of sequential regression, because really that’s all it is Covariate(s)
FIXED AND RANDOM EFFECTS IN HLM. Fixed effects produce constant impact on DV. Random effects produce variable impact on DV. F IXED VS RANDOM EFFECTS.
Inference for regression - More details about simple linear regression IPS chapter 10.2 © 2006 W.H. Freeman and Company.
ANCOVA Workings of ANOVA & ANCOVA ANCOVA, partial correlations & multiple regression Using model plotting to think about ANCOVA & Statistical control Homogeneity.
ANCOVA.
The “Big Picture” (from Heath 1995). Simple Linear Regression.
29 October 2009 MRC CBU Graduate Statistics Lectures 4: GLM: The General Linear Model - ANOVA & ANCOVA1 MRC Cognition and Brain Sciences Unit Graduate.
1 Objective Given two linearly correlated variables (x and y), find the linear function (equation) that best describes the trend. Section 10.3 Regression.
Education 793 Class Notes ANCOVA Presentation 11.
Analyze Of VAriance. Application fields ◦ Comparing means for more than two independent samples = examining relationship between categorical->metric variables.
Predicting Energy Consumption in Buildings using Multiple Linear Regression Introduction Linear regression is used to model energy consumption in buildings.
Lecture #26 Thursday, November 17, 2016 Textbook: 14.1 and 14.3
Decomposition of Sum of Squares
B&A ; and REGRESSION - ANCOVA B&A ; and
Comparing several means: ANOVA (GLM 1)
Analysis of Covariance, ANCOVA (GLM2)
Analysis of Covariance (ANCOVA)
Understanding Standards Event Higher Statistics Award
Chapter 30: Standard Data
Analysis of Data Graphics Quantitative data
(Residuals and
Chapter 5 Introduction to Factorial Designs
BIBD and Adjusted Sums of Squares
Example Problem 3.24 Complete analysis.
How to use a covariate to get a more sensitive analysis
Soc 3306a: ANOVA and Regression Models
Comparing Several Means: ANOVA
Two Sample t-test vs. Paired t-test
STAT Two-Factor ANOVA with Kij = 1
Chapter 11: The ANalysis Of Variance (ANOVA)
Regression designs Y X1 Plant size Growth rate 1 10
Ch. 27: Standard data The reuse of previous times. Advantages
Soc 3306a Lecture 11: Multivariate 4
Linear Regression and Correlation
Linear Regression and Correlation
Be humble in our attribute, be loving and varying in our attitude, that is the way to live in heaven.
A medical researcher wishes to determine how the dosage (in mg) of a drug affects the heart rate of the patient. Find the correlation coefficient & interpret.
Decomposition of Sum of Squares
Problem 3.26, when assumptions are violated
Presentation transcript:

How to use a covariate to get a more sensitive analysis ANCOVA How to use a covariate to get a more sensitive analysis

Placebo and two treatments Suppose I have a drug treatment study: a-brand name drug (eg. Synthroid) d-generic version of first drug a (L-thyroxin) Placebo- inert substance (sham treatment) X- initial value of physiological parameter which may correlate with Response (related to thyroid function) Response- post-treatment value of physiological parameter (T4 which directly measures thyroid function) Either the brand name or generic should increase the physiological parameter (i.e. increase thyroid function)

Raw data:

Suppose I analyze the data and only look at post data (graph first)

Now ANOVA No apparent significant differences

Maybe we can improve the Model by including another predictor variable, so ANCOVA ANCOVA Model: Yij=µ+τi+β*X+εij so that i indexes the treatment group and X is now included in the model as a regression variable with slope β.

New analysis with ANCOVA model This plot looks much more convincing

ANCOVA table Now it is clear that there is a treatment group effect, so go on to test group means.

Means comparisons all groups with Tukey

Could have done contrasts (not really needed in this case because of the results of the Range test) This contrast tests Drug a vs. Drug d

Residuals vs. Predicted

Normality

Test of Normality

Drugs vs. Placebo This confirms that virtually all Treatment group variation is due to the Placebo vs. Drugs.

Why did all of this work? Compare Mean Squares for both models: σ2 approximately 36.86 for the Model without Covariate σ2 approximately 16.046 for the Model with Covariate It worked because including a meaningful explanatory variable, i.e. the covariate, reduced our estimate of experimental error.