RDPStatistical Methods in Scientific Research - Lecture 21 Lecture 2 Regression relationships 2.1 The influence of actual widths of the anorexics 2.2 Testing.

Slides:



Advertisements
Similar presentations
11-1 Empirical Models Many problems in engineering and science involve exploring the relationships between two or more variables. Regression analysis.
Advertisements

Copyright © 2009 Pearson Education, Inc. Chapter 29 Multiple Regression.
11 Simple Linear Regression and Correlation CHAPTER OUTLINE
Regression Analysis Once a linear relationship is defined, the independent variable can be used to forecast the dependent variable. Y ^ = bo + bX bo is.
Correlation and regression
Chapter 8 Linear Regression © 2010 Pearson Education 1.
Objectives (BPS chapter 24)
LINEAR REGRESSION: Evaluating Regression Models Overview Assumptions for Linear Regression Evaluating a Regression Model.
LINEAR REGRESSION: Evaluating Regression Models. Overview Assumptions for Linear Regression Evaluating a Regression Model.
LINEAR REGRESSION: Evaluating Regression Models. Overview Standard Error of the Estimate Goodness of Fit Coefficient of Determination Regression Coefficients.
Copyright (c) Bani K. Mallick1 STAT 651 Lecture #18.
Business Statistics - QBM117 Interval estimation for the slope and y-intercept Hypothesis tests for regression.
Quantitative Business Analysis for Decision Making Simple Linear Regression.
BCOR 1020 Business Statistics Lecture 24 – April 17, 2008.
11-1 Empirical Models Many problems in engineering and science involve exploring the relationships between two or more variables. Regression analysis.
Review for Exam 2 Some important themes from Chapters 6-9 Chap. 6. Significance Tests Chap. 7: Comparing Two Groups Chap. 8: Contingency Tables (Categorical.
Copyright ©2006 Brooks/Cole, a division of Thomson Learning, Inc. More About Regression Chapter 14.
Relationships Among Variables
1 Chapter 20 Two Categorical Variables: The Chi-Square Test.
Correlation and Linear Regression
Inference for regression - Simple linear regression
Hypothesis Testing.
Copyright © 2010, 2007, 2004 Pearson Education, Inc. Chapter 26 Comparing Counts.
September In Chapter 14: 14.1 Data 14.2 Scatterplots 14.3 Correlation 14.4 Regression.
1 Least squares procedure Inference for least squares lines Simple Linear Regression.
1 Chapter 3: Examining Relationships 3.1Scatterplots 3.2Correlation 3.3Least-Squares Regression.
RDPStatistical Methods in Scientific Research - Lecture 11 Lecture 1 Interpretation of data 1.1 A study in anorexia nervosa 1.2 Testing the difference.
Review of Statistical Models and Linear Regression Concepts STAT E-150 Statistical Methods.
1 1 Slide Multiple Regression n Multiple Regression Model n Least Squares Method n Multiple Coefficient of Determination n Model Assumptions n Testing.
Correlation & Regression
Ordinary Least Squares Estimation: A Primer Projectseminar Migration and the Labour Market, Meeting May 24, 2012 The linear regression model 1. A brief.
Chapter 4 Linear Regression 1. Introduction Managerial decisions are often based on the relationship between two or more variables. For example, after.
L Berkley Davis Copyright 2009 MER301: Engineering Reliability Lecture 9 1 MER301:Engineering Reliability LECTURE 9: Chapter 4: Decision Making for a Single.
Goodness-of-Fit Chi-Square Test: 1- Select intervals, k=number of intervals 2- Count number of observations in each interval O i 3- Guess the fitted distribution.
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. Chapter 13 Multiple Regression Section 13.3 Using Multiple Regression to Make Inferences.
Multiple Regression BPS chapter 28 © 2006 W.H. Freeman and Company.
RDPStatistical Methods in Scientific Research - Lecture 41 Lecture 4 Sample size determination 4.1 Criteria for sample size determination 4.2 Finding the.
Simple Linear Regression ANOVA for regression (10.2)
BPS - 5th Ed. Chapter 221 Two Categorical Variables: The Chi-Square Test.
© Copyright McGraw-Hill Correlation and Regression CHAPTER 10.
Copyright ©2011 Brooks/Cole, Cengage Learning Inference about Simple Regression Chapter 14 1.
Lecture 11 Preview: Hypothesis Testing and the Wald Test Wald Test Let Statistical Software Do the Work Testing the Significance of the “Entire” Model.
Agresti/Franklin Statistics, 1 of 88 Chapter 11 Analyzing Association Between Quantitative Variables: Regression Analysis Learn…. To use regression analysis.
Business Statistics for Managerial Decision Farideh Dehkordi-Vakil.
[1] Simple Linear Regression. The general equation of a line is Y = c + mX or Y =  +  X.  > 0  > 0  > 0  = 0  = 0  < 0  > 0  < 0.
Chapter 13 Repeated-Measures and Two-Factor Analysis of Variance
Chapter 2 Examining Relationships.  Response variable measures outcome of a study (dependent variable)  Explanatory variable explains or influences.
Chapter 8: Simple Linear Regression Yang Zhenlin.
Business Statistics for Managerial Decision Farideh Dehkordi-Vakil.
Residuals Recall that the vertical distances from the points to the least-squares regression line are as small as possible.  Because those vertical distances.
June 30, 2008Stat Lecture 16 - Regression1 Inference for relationships between variables Statistics Lecture 16.
Statistical Data Analysis 2010/2011 M. de Gunst Lecture 9.
1 HETEROSCEDASTICITY: WEIGHTED AND LOGARITHMIC REGRESSIONS This sequence presents two methods for dealing with the problem of heteroscedasticity. We will.
Maths Study Centre CB Open 11am – 5pm Semester Weekdays
Chapter 26: Inference for Slope. Height Weight How much would an adult female weigh if she were 5 feet tall? She could weigh varying amounts – in other.
Describing Relationships. Least-Squares Regression  A method for finding a line that summarizes the relationship between two variables Only in a specific.
Chapter 15 Inference for Regression. How is this similar to what we have done in the past few chapters?  We have been using statistics to estimate parameters.
Stats Methods at IC Lecture 3: Regression.
Inference for Least Squares Lines
11-1 Empirical Models Many problems in engineering and science involve exploring the relationships between two or more variables. Regression analysis.
CHAPTER 3 Describing Relationships
Model validation and prediction
POSC 202A: Lecture Lecture: Substantive Significance, Relationship between Variables 1.
Correlation and Regression
Least-Squares Regression
Simple Linear Regression and Correlation
3.2 – Least Squares Regression
Correlation and Simple Linear Regression
Correlation and Simple Linear Regression
Presentation transcript:

RDPStatistical Methods in Scientific Research - Lecture 21 Lecture 2 Regression relationships 2.1 The influence of actual widths of the anorexics 2.2 Testing the importance of each influence 2.3 Comments on the anorexia study

RDPStatistical Methods in Scientific Research - Lecture The influence of actual widths of the anorexics AnorexicsControls BPIActual widthBPIActual width

RDPStatistical Methods in Scientific Research - Lecture 23 Scatter plot

RDPStatistical Methods in Scientific Research - Lecture 24 Observations  BPI decreases with actual width  The controls have smaller waists than the anorexics!  Actual width appears to be a stronger determinant of BPI than anorexic status

RDPStatistical Methods in Scientific Research - Lecture 25 Five models for the data 1 INTERCEPT Neither anorexia nor actual width affect BPI 2 INTERCEPT + GROUP Anorexia affects BPI, but actual width does not

RDPStatistical Methods in Scientific Research - Lecture 26 3 INTERCEPT + AW Actual width affects BPI, but anorexia does not 4 INTERCEPT + GROUP + AW Anorexia and actual width affect BPI additively

RDPStatistical Methods in Scientific Research - Lecture 27 5 INTERCEPT + GROUP + AW + INTERACTION Anorexia and actual width affect BPI non-additively Which model fits the data best? How can we judge? How should we play off goodness-of-fit against complexity?

RDPStatistical Methods in Scientific Research - Lecture 28 Residuals The residuals are the vertical distances between the observed points and the fitted models: residual = BPI observed – BPI fitted For example, for Model 4 we have:

RDPStatistical Methods in Scientific Research - Lecture 29

RDPStatistical Methods in Scientific Research - Lecture 210 Showing only the residuals, we have:

RDPStatistical Methods in Scientific Research - Lecture 211 Moving them all down to 0 gives: The goodness-of-fit of a models is assessed in terms of the residual sum of squares, RSS, (the smaller, the better):

RDPStatistical Methods in Scientific Research - Lecture 212 Model fits degrees-of-freedom (df) = n  # parameters Goodness-of-fit improves as terms are added into the model, although model complexity (number of parameters) increases (which is a bad thing) AnorexicsControls ModelinterceptslopeinterceptslopeRSSdf      

RDPStatistical Methods in Scientific Research - Lecture 213 Interaction  We start with the most complex model (Model 5), and see whether it can be simplified  That is, we test H 0 : there is no aw  group interaction (Model 4 is valid)  If the observations are normally distributed, then if Model 4 is true, then F int follows an F-distribution with (1, 15) degrees-of-freedom: that is F int ~ F 1,15, where 2.2 Testing the importance of each influence

RDPStatistical Methods in Scientific Research - Lecture 214 Interaction Large values of F int indicate that H 0 is false Here, we have This value is too small to suggest that interaction is important The p-value is p = P(F  0.38) where F ~ F 1,15, and p =

RDPStatistical Methods in Scientific Research - Lecture 215 Actual width  Take the model in which BPI depends on actual width only (Model 3), and see whether the effect of actual width is necessary  That is, we test H 0 : actual width does not effect BPI, which means that Model 1 is valid  If the observations are normally distributed, then if Model 1 is true, then F aw ~ F 1,17, where

RDPStatistical Methods in Scientific Research - Lecture 216 Actual width We have This value is too large to come from the F 1,17 distribution The p-value is p = P(F  28.26) where F ~ F 1,17, and p < H 0 : actual width does not effect BPI is rejected

RDPStatistical Methods in Scientific Research - Lecture 217 Group  Accepting that actual width is needed in the model, now take Model 4, and see whether it can be simplified by removing the effect of anorexia  That is, we test H 0 : anorexia does not effect BPI (once aw is allowed for), which means that Model 3 is valid  If the observations are normally distributed, then if Model 3 is true, then F group  aw ~ F 1,16, where

RDPStatistical Methods in Scientific Research - Lecture 218 Group We have This value is too small to suggest that group is important The p-value is p = P(F  0.74) where F ~ F 1,16, and p =

RDPStatistical Methods in Scientific Research - Lecture 219 Final model This is Model 3, which states that BPI has mean =  aw standard deviation =  = and that being anorexic has no significant effect on body perception index

RDPStatistical Methods in Scientific Research - Lecture 220 Order of fitting is important  Test interaction first: if this is significant, then the two main effects should not be tested: Model 5 is needed to describe the data  Then determine whether actual width is needed in the model  As actual width is needed, test the effect of group (the factor that is of interest), by comparing Model 3 with Model 4  If actual width were not needed, test the effect of group by comparing Model 1 with Model 2

RDPStatistical Methods in Scientific Research - Lecture 221 Order of fitting is important To compare Model 1 with Model 2, find which is The p-value is p = P(F  2.63) where F ~ F 1,16, and p =

RDPStatistical Methods in Scientific Research - Lecture 222 Order of fitting is important The t-statistic for testing the effect of anorexia shown on Slide 1.11 was equal to  The square of  is 2.631, which is equal to F group This is no coincidence: these two tests are in fact identical BUT, in this case, due to the important influence of actual width, any analysis that fails to account for aw is invalid

RDPStatistical Methods in Scientific Research - Lecture 223 Choice of subjects  The anorexics were consecutive unmarried female patients at St George’s Hospital, London  The controls were volunteer fifth form pupils from Putney Girls’ High School, with normal dietary habits Ages: Anorexics mean = 19.7, sd = 3.6 Controls mean = 15.4, sd = 0.5 This was not a suitable control group for this study 2.3 Comments on the anorexia study