STK4900/ Lecture 4 Program. Counterfactuals and causal effects. Example (cf. practical exercise 10)
|
|
- Roland Davis
- 5 years ago
- Views:
Transcription
1 STK4900/ Leture 4 Program 1. Counterfatuals and ausal effets 2. Confoundng 3. Interaton 4. More on ANOVA Setons 4.1, 4.4, 4.6 Supplementary materal on ANOVA Example (f. pratal exerse 10) How does exerse affet blood gluose level? Use the HERS data, dsregardng women wth dabetes Smple lnear regresson: 0 1 Estmate Std. Error t value Pr(> t ) (Interept) < 2e-16 exerse Resdual standard error: on 2030 degrees of freedom Multple R-squared: , Adjusted R-squared: F-statst: on 1 and 2030 DF, p-value: Can we onlude that exerse on average dereases the blood gluose level wth 1.7 mg/dl? 2 Problem: The women who exerse are not a random sample of all women n the ohort (as they would have been n a lnal tral), but dffer from the women who don't exerse, e.g. wth respet to age, alohol use, and body mass ndex (BMI) Gluose Further age, alohol use, and BMI may nfluene the gluose level Illustraton for BMI: Gluose Counterfatuals and ausal effets For the general dsusson we onsder some outome (e.g. gluose level) and we want to see how ths s affeted by a bnary predtor, or "exposure", X 1 (e.g. exerse) wth X 1 =1 orrespondng to "exposed" and X 1 =0 orrespondng to "unexposed" Suppose (ounter to the fat) that we ould run an experment n whh frst every ndvdual s exposed (.e. X 1 =1) and the outome Y 1 s observed then, turnng bak the lok, every ndvdual s unexposed (.e. X 1 =0) and the outome Y 0 s observed BMI Exerse=0 Exerse=1 Consderng ths problem, an anythng be sad about the "ausal effet" of exerse on blood gluose level? 3 All other haratersts of the ndvduals are assumed to be the same n the two parts of the hypothetal experment 4
2 In real lfe, we an not turn bak the lok, so one of the two expermental outomes for every ndvdual s an unobserved ounterfatual The ausal effet (n a statstal sense ) of the exposure s defned as the dfferene n populaton means under the two parts of the ounterfatual experment: Causal effet = E( Y ) E( Y ) 1 0 If the means dffer, we say that the exposure s a ausal determnant of the outome A smple model for the ounterfatual experment To make the argument smple, we assume that all other haratersts of the ndvduals are aptured by a bnary ovarate X 2 whh also has a ausal effet on the outome Further we assume that the (ounterfatual) outome for ndvdual when exposed take the form y = β + β + β x + ε whle when unexposed t beomes y = β + β x + ε Then the populaton means for the two parts of the ounterfatual experment beome exposed: E( Y ) = E( β + β + β X + ε ) = β + β + β E( X ) unexposed: E( Y ) = E( β + β X + ε ) = β + β E( X ) In the ounterfatual experment the dstrbuton of X 2 s the same n both parts of the experment, and hene ts mean s the same Hene the ausal effet of the exposure beomes Causal effet = E( Y ) E( Y ) 1 0 { E X } = β + β + β E( X ) β + β ( ) = β Confoundng In realty we annot observe the ounterfatuals We an only observe the outome for an ndvdual under one of the two ondtons (exposed/unexposed) In prate we therefore have to ompare the mean values of the outome n two dstnt populatons, one exposed and one unexposed But then there s no guarantee that the mean value of X 2 wll be the same n the exposed and unexposed populatons Let E1( X 2) denote the mean of X 2 among the exposed, and let E ( X ) denote the mean of X 2 among the unexposed 0 2 8
3 For the exposed populaton: Thus E( Y ) = β + β + β E ( X ) For the unexposed populaton: E( Y ) = β + β E ( X ) { } E( Y ) E( Y ) = β + β + β E ( X ) β + β E ( X ) { E ( X ) E ( X )} = β + β If we perform a study where we sample from the exposed and unexposed populatons, and estmate the dfferene based on the exposed and unexposed samples, we wll estmate { E ( X ) E ( X )} β + β If the mean value of X 2 dffers between the exposed and unexposed populatons, we wll get a based estmate of the ausal effet β We say that the (ausal) effet of X 1 s onfounded by X No onfoundng If the dstrbuton of X 2 s ndependent of the level of exposure (.e. X 1 = 0,1), then E1( X 2) = E0( X 2) and there wll be no onfoundng In partular ths wll be the ase n an experment where ndvduals are randomly alloated to exposure/no exposure Condtons for onfoundng A ovarate X 2 s a onfounder for the ausal effet of X 1 provded that X 2 s a ausal determnant of the outome Y (or a proxy for suh determnants) X 2 s a ausal determnant of X 1 (or they share a ommon ausal determnant) 10 Confoundng patterns Examples of onfoundng patterns when X 2 s a numeral ovarate Control of onfoundng Consder the stuaton where all ausal determnants other than X 1 are aptured by the bnary ovarate X 2 Complete onfoundng Then, gven the level of X 2 (= 0,1), there s no more onfoundng and the ausal effet of X 1 may estmated by omparng the means of exposed and unexposed wthn levels of X 2 In prate ths s obtaned by fttng the lnear model y = β + β x + β x + ε Negatve onfoundng β 1 sne here s the effet of one unt's nrease n X 1 the value of X 2 onstant keepng Fg. 4.1 n the book 11 In general we may use multple lnear regresson to orret for a number of onfounders by nludng them as ovarates n the model (assumng that all relevant onfounders are reorded n the data) 12
4 Example (ontd) We ft a multple regresson model wth blood gluose level as response and exerse, age, alohol use, and body mass ndex (BMI) as ovarates Multple lnear regresson: Estmate Std. Error t value Pr(> t ) (Interept) <2e-16 exerse age drnkany BMI <2e-16 Interaton for bnary ovarates We have onsdered the stuaton where two bnary predtors X 1 and X 2 have a ausal effet on the outome We ould then estmate the (ausal) effets by fttng the lnear model y = β + β x + β x + ε Note that we assume that the effet of X 1 s the same for both levels of X 2 (and ve versa): Resdual standard error: on 2023 degrees of freedom (4 observatons deleted due to mssngness) Multple R-squared: 0.072, Adjusted R-squared: F-statst: on 4 and 2023 DF, p-value: < 2.2e-16 We now fnd that exerse on average dereases the blood gluose level wth 1.0 mg/dl Ths should be loser to the ausal effet of exerse 13 X X E( y x) β 0 β + β 0 1 β + β 0 2 β + β + β If the effet of X 1 depends on the level of X 2 we have an nteraton We may then ft a model of the form y = β + β x + β x + β x x + ε The effet for dfferent values of the ovarates are then gven by: X X X X E( y x) β 0 β + β 0 1 β + β 0 2 β + β + β + β Example Use the HERS data to study how low-densty lpoproten holesterol after one year (LDL1) depends on hormone therapy (HT) and statn use (both bnary) R ommands: ht.ft=lm(ldl1~ht+statns+ht:statns, data=hers) summary(ht.ft) R output (edted): Estmate Std. Error t value Pr(> t ) (Interept) < 2e-16 HT < 2e-16 statns e-10 HT:statns (In the model formula HT:statn spefes the nteraton term "HT*statn") The effet of HT seems to be lower among statn users 15 16
5 Estmate Std. Error t value Pr(> t ) (Interept) < 2e-16 HT < 2e-16 statns e-10 HT:statns HT redues LDL holesterol for non-users of statns by 17.7 mg/dl For users of statns the estmated reduton s = 11.5 mg/dl To obtan the unertanty, we use the "ontrast" lbrary R ommands: lbrary(ontrast) par1= lst(ht=1,statns=1) # spefy one set of values of the ovarates par2= lst(ht=0,statns=1) # spefy another set of values of the ovarates ontrast(ht.ft, par1,par2) # ompute the dfferene between the two sets R output (edted): Contrast S.E. Lower Upper t df Pr(> t ) Interaton for one bnary and one numeral ovarate We now onsder the stuaton where X 1 s a bnary predtor and X 2 s numeral As an llustraton we onsder the HERS data, and we wll see how baselne LDL holesterol depends on statn use ( X 1 ) and BMI ( X 2 ) The model y = β + β x + β x + ε assumes that the effet of BMI s the same for statn users and those who don't use statns It may be of nterest to onsder a model where the effet of BMI may dffer between statn users and those who don't use statns,.e. where there s an nteraton 18 We then onsder the model y = β + β x + β x + β x x + ε Note that the model may be wrtten β0 + β2x2 + ε when x1 = 0 y β0 + β1 + ( β2 + β3) x2 + ε when x1 = 1 Ths s a model wth dfferent nterepts and dfferent slopes for the numeral ovarate dependng on the value of the bnary ovarate When onsderng suh a model, t s useful to enter the numer ovarate (by subtratng ts mean) to ease nterpretaton In the example, we let X 2 orrespond to the entered BMI-values, denoted BMI R ommands: hers$bmi=hers$bmi - mean(hers$bmi[!s.na(hers$bmi)]) stat.ft=lm(ldl~statns+bmi+statns:bmi,data=hers) summary(stat.ft) par1=lst(statns=1,bmi=1) par2=lst(statns=1,bmi=0) ontrast(stat.ft,par1,par2) R output (edted): Estmate Std. Error t value Pr(> t ) (Interept) < 2e-16 statns < 2e-16 BMI e-05 statns:bmi Contrast S.E. Lower Upper t df Pr(> t )
6 Interaton for two numeral ovarates We fnally onsder the stuaton where X 1 and X 2 are both numeral A model wth nteraton s then gven by y = β + β x + β x + β x x + ε For suh a model, t s useful to enter the ovarates But even then the nterpretaton of the estmates s a bt omplated Two-way ANOVA Consder the stuaton where the outome y for an ndvdual depends on two fators, A and B, eah wth two levels, denoted a 1, a 2 and b 1, b 2 One suh example s how LDL holesterol depends on HT (wth levels "plaebo" and "hormone therapy") and statn use (wth levels "no" and "yes"); f. slde 16 We may here ntrodue the ovarates: x 1 0 f ndvd has level a for fator A (referene) 1 f ndvd has level a for fator A 1 2 x 2 0 f ndvd has level b for fator B (referene) 1 f ndvd has level b for fator B Then a regresson model wth nteraton takes the form (f slde 15) y = β + β x + β x + β x x + ε If (e.g.) fator B has three levels b 1, b 2, b 3, we need to ntrodue two x's for ths fator (f slde 26 of Leture 3): x 2 x 3 1 f ndvd has level b for fator B 0 otherwse 1 f ndvd has level b for fator B 0 otherwse A model wth nteraton then takes the form y x x x x x x x = β 0 + β1 1 + β β β β ε (*) It beomes qute omplated to wrte the model lke ths, so t s ommon to use an alternatve formulaton We reaptulate: y x x x x x x x In order to rewrte model (*), we denote the outomes for level a j of fator A and level b k of fator B by y for = 1,..., n jk We may then rewrte model (*) as jk y = µ + α + β + ( αβ ) + ε (**) jk j k jk jk We have the followng relatons between the parameters n model (*) and model (**) (*) = β 0 + β1 1 + β β β β ε (*) β β β β β β (**) µ α β β ( αβ ) ( αβ ) In model (**) the parameters for the referene levels are 0 : α = β = ( αβ ) = ( αβ ) = ( αβ ) = ( αβ ) =
7 Note that the model formulaton y = µ + α + β + ( αβ ) + ε (**) jk j k jk jk works equally well when fator A has J levels and fator B has K levels, whle the formulaton (*) would beome muh more omplated In Leture 3 (f. slde 30), we onsdered a study of how the extraton rate of a ertan polymer depends on temperature and the amount of atalyst used. We there assumed a lnear effet of temperature and the amount of atalyst We wll here onsder temperature and atalyst as fators, eah wth three levels 25 R ommands: polymer=read.table(" polymer$ftemp=fator(polymer$temp) polymer$fat=fator(polymer$at) ft=lm(rate~ftemp+fat+ftemp:fat,data=polymer) summary(ft) R output: Estmate Std. Error t value Pr(> t ) (Interept) e-10 ftemp ftemp fat fat e-06 ftemp60:fat ftemp70:fat ftemp60:fat ftemp70:fat Resdual standard error: 1.73 on 9 degrees of freedom Multple R-squared: 0.986, Adjusted R-squared: F-statst: on 8 and 9 DF, p-value: 2.012e In a planned experment we an make sure that we have the same number of observatons for all the J x K ombnatons of levels of fator A and fator B We then have a balaned desgn, and the total sum of squares (TSS) may be unquely deomposed as a sum of squares for eah of the two fators (SSA, SSB), a sum of squares for nteraton (SSAB), and a resdual sum of squares (RSS): TSS = SSA + SSB + SSAB + RSS The result of a two-way ANOVA may be summarzed n the table Soure df Sum of Mean sum F statsts squares of squares Fator A J 1 SSA SSA/( J 1) SSA/( J 1) F = RSS /( n JK) Fator B K 1 SSB SSB /( K 1) SSB /( K 1) F = RSS /( n JK) Interaton ( J 1)( K 1) SSAB SSAB /( J 1)( K 1) SSAB /( J 1)( K 1) F = RSS /( n JK) Resdual n JK RSS RSS /( n JK) Total n 1 TSS To eah of these sum of squares there orrespond a degree of freedom as gven n the ANOVA table on the next slde NB! If the desgn s not balaned, the deomposton of the total sum of squares s not unque 27 The F-statsts (wth ther approprate degrees of freedom) may be used to test the followng null hypotheses: H0 : all ( αβ ) jk = 0 (no nteraton) H0 : all α j = 0 (no man effet of A) H0 : all β k = 0 (no man effet of B) 28
8 For the example: R ommands: anova(ft) Hgher level ANOVA Consder for llustraton the stuaton wth three fators, A, B, and C. R output: Analyss of Varane Table Df Sum Sq Mean Sq F value Pr(>F) ftemp e-06 fat e-08 ftemp:fat Resduals Data: y jkl = observaton number for level a j of fator A, level b of fator B, and level of fator C Model wth nteraton: k y = µ + α + β + γ + ( αβ ) + ( αγ ) + ( βγ ) + ( αβγ ) + ε jkl j k l jk jl kl jkl jkl l The result of a three-way ANOVA may be summarzed n the table Soure df * Sum of Mean sum F statsts squares of squares Fator A SSA SSA/ df F Fator B SSB SSB / df F Fator C SSC SSC / df F Interaton AB SSAB SSAB / df F Interaton AC SSAC SSAC / df F Interaton BC SSBC SSBC / df F Interaton ABC SSAB C SSABC / df F ABC Resdual RSS RSS / df Total n 1 TSS *) an be found on omputer output The deomposton of the total sum of squares s unque f the desgn s balaned A B C AB AC BC Hypothess testng s smlar to two-way ANOVA 31
The corresponding link function is the complementary log-log link The logistic model is comparable with the probit model if
SK300 and SK400 Lnk funtons for bnomal GLMs Autumn 08 We motvate the dsusson by the beetle eample GLMs for bnomal and multnomal data Covers the followng materal from hapters 5 and 6: Seton 5.6., 5.6.3,
More informationJSM Survey Research Methods Section. Is it MAR or NMAR? Michail Sverchkov
JSM 2013 - Survey Researh Methods Seton Is t MAR or NMAR? Mhal Sverhkov Bureau of Labor Statsts 2 Massahusetts Avenue, NE, Sute 1950, Washngton, DC. 20212, Sverhkov.Mhael@bls.gov Abstrat Most methods that
More informationANOVA. The Observations y ij
ANOVA Stands for ANalyss Of VArance But t s a test of dfferences n means The dea: The Observatons y j Treatment group = 1 = 2 = k y 11 y 21 y k,1 y 12 y 22 y k,2 y 1, n1 y 2, n2 y k, nk means: m 1 m 2
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experments- MODULE LECTURE - 6 EXPERMENTAL DESGN MODELS Dr. Shalabh Department of Mathematcs and Statstcs ndan nsttute of Technology Kanpur Two-way classfcaton wth nteractons
More informationChapter 13: Multiple Regression
Chapter 13: Multple Regresson 13.1 Developng the multple-regresson Model The general model can be descrbed as: It smplfes for two ndependent varables: The sample ft parameter b 0, b 1, and b are used to
More informationDepartment of Statistics University of Toronto STA305H1S / 1004 HS Design and Analysis of Experiments Term Test - Winter Solution
Department of Statstcs Unversty of Toronto STA35HS / HS Desgn and Analyss of Experments Term Test - Wnter - Soluton February, Last Name: Frst Name: Student Number: Instructons: Tme: hours. Ads: a non-programmable
More informationFirst Year Examination Department of Statistics, University of Florida
Frst Year Examnaton Department of Statstcs, Unversty of Florda May 7, 010, 8:00 am - 1:00 noon Instructons: 1. You have four hours to answer questons n ths examnaton.. You must show your work to receve
More informationStatistics II Final Exam 26/6/18
Statstcs II Fnal Exam 26/6/18 Academc Year 2017/18 Solutons Exam duraton: 2 h 30 mn 1. (3 ponts) A town hall s conductng a study to determne the amount of leftover food produced by the restaurants n the
More information17 Nested and Higher Order Designs
54 17 Nested and Hgher Order Desgns 17.1 Two-Way Analyss of Varance Consder an experment n whch the treatments are combnatons of two or more nfluences on the response. The ndvdual nfluences wll be called
More informationLecture 6: Introduction to Linear Regression
Lecture 6: Introducton to Lnear Regresson An Manchakul amancha@jhsph.edu 24 Aprl 27 Lnear regresson: man dea Lnear regresson can be used to study an outcome as a lnear functon of a predctor Example: 6
More information1. Inference on Regression Parameters a. Finding Mean, s.d and covariance amongst estimates. 2. Confidence Intervals and Working Hotelling Bands
Content. Inference on Regresson Parameters a. Fndng Mean, s.d and covarance amongst estmates.. Confdence Intervals and Workng Hotellng Bands 3. Cochran s Theorem 4. General Lnear Testng 5. Measures of
More informationLogistic regression with one predictor. STK4900/ Lecture 7. Program
Logstc regresson wth one redctor STK49/99 - Lecture 7 Program. Logstc regresson wth one redctor 2. Maxmum lkelhood estmaton 3. Logstc regresson wth several redctors 4. Devance and lkelhood rato tests 5.
More informationInterpreting Slope Coefficients in Multiple Linear Regression Models: An Example
CONOMICS 5* -- Introducton to NOT CON 5* -- Introducton to NOT : Multple Lnear Regresson Models Interpretng Slope Coeffcents n Multple Lnear Regresson Models: An xample Consder the followng smple lnear
More informationThe Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction
ECONOMICS 5* -- NOTE (Summary) ECON 5* -- NOTE The Multple Classcal Lnear Regresson Model (CLRM): Specfcaton and Assumptons. Introducton CLRM stands for the Classcal Lnear Regresson Model. The CLRM s also
More informationHere is the rationale: If X and y have a strong positive relationship to one another, then ( x x) will tend to be positive when ( y y)
Secton 1.5 Correlaton In the prevous sectons, we looked at regresson and the value r was a measurement of how much of the varaton n y can be attrbuted to the lnear relatonshp between y and x. In ths secton,
More informationChapter 9: Statistical Inference and the Relationship between Two Variables
Chapter 9: Statstcal Inference and the Relatonshp between Two Varables Key Words The Regresson Model The Sample Regresson Equaton The Pearson Correlaton Coeffcent Learnng Outcomes After studyng ths chapter,
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VII LECTURE - 3 ANALYSIS OF COVARIANCE Dr Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Any scentfc experment s performed
More informationPolynomial Regression Models
LINEAR REGRESSION ANALYSIS MODULE XII Lecture - 6 Polynomal Regresson Models Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Test of sgnfcance To test the sgnfcance
More informationEconomics 130. Lecture 4 Simple Linear Regression Continued
Economcs 130 Lecture 4 Contnued Readngs for Week 4 Text, Chapter and 3. We contnue wth addressng our second ssue + add n how we evaluate these relatonshps: Where do we get data to do ths analyss? How do
More informationLecture 2: Prelude to the big shrink
Lecture 2: Prelude to the bg shrnk Last tme A slght detour wth vsualzaton tools (hey, t was the frst day... why not start out wth somethng pretty to look at?) Then, we consdered a smple 120a-style regresson
More informationLinear Regression Analysis: Terminology and Notation
ECON 35* -- Secton : Basc Concepts of Regresson Analyss (Page ) Lnear Regresson Analyss: Termnology and Notaton Consder the generc verson of the smple (two-varable) lnear regresson model. It s represented
More informationSee Book Chapter 11 2 nd Edition (Chapter 10 1 st Edition)
Count Data Models See Book Chapter 11 2 nd Edton (Chapter 10 1 st Edton) Count data consst of non-negatve nteger values Examples: number of drver route changes per week, the number of trp departure changes
More informationComparison of Regression Lines
STATGRAPHICS Rev. 9/13/2013 Comparson of Regresson Lnes Summary... 1 Data Input... 3 Analyss Summary... 4 Plot of Ftted Model... 6 Condtonal Sums of Squares... 6 Analyss Optons... 7 Forecasts... 8 Confdence
More informationStatistics Chapter 4
Statstcs Chapter 4 "There are three knds of les: les, damned les, and statstcs." Benjamn Dsrael, 1895 (Brtsh statesman) Gaussan Dstrbuton, 4-1 If a measurement s repeated many tmes a statstcal treatment
More informationNANYANG TECHNOLOGICAL UNIVERSITY SEMESTER I EXAMINATION MTH352/MH3510 Regression Analysis
NANYANG TECHNOLOGICAL UNIVERSITY SEMESTER I EXAMINATION 014-015 MTH35/MH3510 Regresson Analyss December 014 TIME ALLOWED: HOURS INSTRUCTIONS TO CANDIDATES 1. Ths examnaton paper contans FOUR (4) questons
More informationTopic 23 - Randomized Complete Block Designs (RCBD)
Topc 3 ANOVA (III) 3-1 Topc 3 - Randomzed Complete Block Desgns (RCBD) Defn: A Randomzed Complete Block Desgn s a varant of the completely randomzed desgn (CRD) that we recently learned. In ths desgn,
More informationProperties of Least Squares
Week 3 3.1 Smple Lnear Regresson Model 3. Propertes of Least Squares Estmators Y Y β 1 + β X + u weekly famly expendtures X weekly famly ncome For a gven level of x, the expected level of food expendtures
More informationLecture 9: Linear regression: centering, hypothesis testing, multiple covariates, and confounding
Recall: man dea of lnear regresson Lecture 9: Lnear regresson: centerng, hypothess testng, multple covarates, and confoundng Sandy Eckel seckel@jhsph.edu 6 May 8 Lnear regresson can be used to study an
More informationLecture 9: Linear regression: centering, hypothesis testing, multiple covariates, and confounding
Lecture 9: Lnear regresson: centerng, hypothess testng, multple covarates, and confoundng Sandy Eckel seckel@jhsph.edu 6 May 008 Recall: man dea of lnear regresson Lnear regresson can be used to study
More informationtechnische universiteit eindhoven Analysis of one product /one location inventory control models prof.dr. A.G. de Kok 1
TU/e tehnshe unverstet endhoven Analyss of one produt /one loaton nventory ontrol models prof.dr. A.G. de Kok Aknowledgements: I would lke to thank Leonard Fortun for translatng ths ourse materal nto Englsh
More information/ n ) are compared. The logic is: if the two
STAT C141, Sprng 2005 Lecture 13 Two sample tests One sample tests: examples of goodness of ft tests, where we are testng whether our data supports predctons. Two sample tests: called as tests of ndependence
More informationLecture 16 Statistical Analysis in Biomaterials Research (Part II)
3.051J/0.340J 1 Lecture 16 Statstcal Analyss n Bomaterals Research (Part II) C. F Dstrbuton Allows comparson of varablty of behavor between populatons usng test of hypothess: σ x = σ x amed for Brtsh statstcan
More informationChapter 12 Analysis of Covariance
Chapter Analyss of Covarance Any scentfc experment s performed to know somethng that s unknown about a group of treatments and to test certan hypothess about the correspondng treatment effect When varablty
More informationJoint Statistical Meetings - Biopharmaceutical Section
Iteratve Ch-Square Test for Equvalence of Multple Treatment Groups Te-Hua Ng*, U.S. Food and Drug Admnstraton 1401 Rockvlle Pke, #200S, HFM-217, Rockvlle, MD 20852-1448 Key Words: Equvalence Testng; Actve
More informationSTAT 511 FINAL EXAM NAME Spring 2001
STAT 5 FINAL EXAM NAME Sprng Instructons: Ths s a closed book exam. No notes or books are allowed. ou may use a calculator but you are not allowed to store notes or formulas n the calculator. Please wrte
More informationLINEAR REGRESSION ANALYSIS. MODULE VIII Lecture Indicator Variables
LINEAR REGRESSION ANALYSIS MODULE VIII Lecture - 7 Indcator Varables Dr. Shalabh Department of Maematcs and Statstcs Indan Insttute of Technology Kanpur Indcator varables versus quanttatve explanatory
More informationLecture 3 Stat102, Spring 2007
Lecture 3 Stat0, Sprng 007 Chapter 3. 3.: Introducton to regresson analyss Lnear regresson as a descrptve technque The least-squares equatons Chapter 3.3 Samplng dstrbuton of b 0, b. Contnued n net lecture
More informationIntroduction to Regression
Introducton to Regresson Dr Tom Ilvento Department of Food and Resource Economcs Overvew The last part of the course wll focus on Regresson Analyss Ths s one of the more powerful statstcal technques Provdes
More informationBiostatistics 360 F&t Tests and Intervals in Regression 1
Bostatstcs 360 F&t Tests and Intervals n Regresson ORIGIN Model: Y = X + Corrected Sums of Squares: X X bar where: s the y ntercept of the regresson lne (translaton) s the slope of the regresson lne (scalng
More informationStatistics for Managers Using Microsoft Excel/SPSS Chapter 13 The Simple Linear Regression Model and Correlation
Statstcs for Managers Usng Mcrosoft Excel/SPSS Chapter 13 The Smple Lnear Regresson Model and Correlaton 1999 Prentce-Hall, Inc. Chap. 13-1 Chapter Topcs Types of Regresson Models Determnng the Smple Lnear
More informationExercise 10: Theory of mass transfer coefficient at boundary
Partle Tehnology Laboratory Prof. Sotrs E. Pratsns Sonneggstrasse, ML F, ETH Zentrum Tel.: +--6 5 http://www.ptl.ethz.h 5-97- U Stoffaustaush HS 7 Exerse : Theory of mass transfer oeffent at boundary Chapter,
More information[The following data appear in Wooldridge Q2.3.] The table below contains the ACT score and college GPA for eight college students.
PPOL 59-3 Problem Set Exercses n Smple Regresson Due n class /8/7 In ths problem set, you are asked to compute varous statstcs by hand to gve you a better sense of the mechancs of the Pearson correlaton
More informationY = β 0 + β 1 X 1 + β 2 X β k X k + ε
Chapter 3 Secton 3.1 Model Assumptons: Multple Regresson Model Predcton Equaton Std. Devaton of Error Correlaton Matrx Smple Lnear Regresson: 1.) Lnearty.) Constant Varance 3.) Independent Errors 4.) Normalty
More informationChapter 8 Indicator Variables
Chapter 8 Indcator Varables In general, e explanatory varables n any regresson analyss are assumed to be quanttatve n nature. For example, e varables lke temperature, dstance, age etc. are quanttatve n
More informationStatistics for Economics & Business
Statstcs for Economcs & Busness Smple Lnear Regresson Learnng Objectves In ths chapter, you learn: How to use regresson analyss to predct the value of a dependent varable based on an ndependent varable
More informationSTATISTICS QUESTIONS. Step by Step Solutions.
STATISTICS QUESTIONS Step by Step Solutons www.mathcracker.com 9//016 Problem 1: A researcher s nterested n the effects of famly sze on delnquency for a group of offenders and examnes famles wth one to
More informationChapter 15 - Multiple Regression
Chapter - Multple Regresson Chapter - Multple Regresson Multple Regresson Model The equaton that descrbes how the dependent varable y s related to the ndependent varables x, x,... x p and an error term
More informationPredictive Analytics : QM901.1x Prof U Dinesh Kumar, IIMB. All Rights Reserved, Indian Institute of Management Bangalore
Sesson Outlne Introducton to classfcaton problems and dscrete choce models. Introducton to Logstcs Regresson. Logstc functon and Logt functon. Maxmum Lkelhood Estmator (MLE) for estmaton of LR parameters.
More informationLecture Notes for STATISTICAL METHODS FOR BUSINESS II BMGT 212. Chapters 14, 15 & 16. Professor Ahmadi, Ph.D. Department of Management
Lecture Notes for STATISTICAL METHODS FOR BUSINESS II BMGT 1 Chapters 14, 15 & 16 Professor Ahmad, Ph.D. Department of Management Revsed August 005 Chapter 14 Formulas Smple Lnear Regresson Model: y =
More informationLecture 4 Hypothesis Testing
Lecture 4 Hypothess Testng We may wsh to test pror hypotheses about the coeffcents we estmate. We can use the estmates to test whether the data rejects our hypothess. An example mght be that we wsh to
More informationSTAT 3008 Applied Regression Analysis
STAT 3008 Appled Regresson Analyss Tutoral : Smple Lnear Regresson LAI Chun He Department of Statstcs, The Chnese Unversty of Hong Kong 1 Model Assumpton To quantfy the relatonshp between two factors,
More informationUNIVERSITY OF TORONTO Faculty of Arts and Science. December 2005 Examinations STA437H1F/STA1005HF. Duration - 3 hours
UNIVERSITY OF TORONTO Faculty of Arts and Scence December 005 Examnatons STA47HF/STA005HF Duraton - hours AIDS ALLOWED: (to be suppled by the student) Non-programmable calculator One handwrtten 8.5'' x
More informationCorrelation and Regression. Correlation 9.1. Correlation. Chapter 9
Chapter 9 Correlaton and Regresson 9. Correlaton Correlaton A correlaton s a relatonshp between two varables. The data can be represented b the ordered pars (, ) where s the ndependent (or eplanator) varable,
More informationChapter 11: Simple Linear Regression and Correlation
Chapter 11: Smple Lnear Regresson and Correlaton 11-1 Emprcal Models 11-2 Smple Lnear Regresson 11-3 Propertes of the Least Squares Estmators 11-4 Hypothess Test n Smple Lnear Regresson 11-4.1 Use of t-tests
More informationAppendix for Causal Interaction in Factorial Experiments: Application to Conjoint Analysis
A Appendx for Causal Interacton n Factoral Experments: Applcaton to Conjont Analyss Mathematcal Appendx: Proofs of Theorems A. Lemmas Below, we descrbe all the lemmas, whch are used to prove the man theorems
More informationβ0 + β1xi and want to estimate the unknown
SLR Models Estmaton Those OLS Estmates Estmators (e ante) v. estmates (e post) The Smple Lnear Regresson (SLR) Condtons -4 An Asde: The Populaton Regresson Functon B and B are Lnear Estmators (condtonal
More information4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA
4 Analyss of Varance (ANOVA) 5 ANOVA 51 Introducton ANOVA ANOVA s a way to estmate and test the means of multple populatons We wll start wth one-way ANOVA If the populatons ncluded n the study are selected
More informationof concretee Schlaich
Seoul Nat l Unersty Conrete Plastty Hong Sung Gul Chapter 1 Theory of Plastty 1-1 Hstory of truss model Rtter & Morsh s 45 degree truss model Franz Leonhardt - Use of truss model for detalng of renforement.
More informationDurban Watson for Testing the Lack-of-Fit of Polynomial Regression Models without Replications
Durban Watson for Testng the Lack-of-Ft of Polynomal Regresson Models wthout Replcatons Ruba A. Alyaf, Maha A. Omar, Abdullah A. Al-Shha ralyaf@ksu.edu.sa, maomar@ksu.edu.sa, aalshha@ksu.edu.sa Department
More informationx = , so that calculated
Stat 4, secton Sngle Factor ANOVA notes by Tm Plachowsk n chapter 8 we conducted hypothess tests n whch we compared a sngle sample s mean or proporton to some hypotheszed value Chapter 9 expanded ths to
More informationJanuary Examinations 2015
24/5 Canddates Only January Examnatons 25 DO NOT OPEN THE QUESTION PAPER UNTIL INSTRUCTED TO DO SO BY THE CHIEF INVIGILATOR STUDENT CANDIDATE NO.. Department Module Code Module Ttle Exam Duraton (n words)
More information7.1. Single classification analysis of variance (ANOVA) Why not use multiple 2-sample 2. When to use ANOVA
Sngle classfcaton analyss of varance (ANOVA) When to use ANOVA ANOVA models and parttonng sums of squares ANOVA: hypothess testng ANOVA: assumptons A non-parametrc alternatve: Kruskal-Walls ANOVA Power
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VIII LECTURE - 34 ANALYSIS OF VARIANCE IN RANDOM-EFFECTS MODEL AND MIXED-EFFECTS EFFECTS MODEL Dr Shalabh Department of Mathematcs and Statstcs Indan
More informationResource Allocation and Decision Analysis (ECON 8010) Spring 2014 Foundations of Regression Analysis
Resource Allocaton and Decson Analss (ECON 800) Sprng 04 Foundatons of Regresson Analss Readng: Regresson Analss (ECON 800 Coursepak, Page 3) Defntons and Concepts: Regresson Analss statstcal technques
More informationECONOMICS 351*-A Mid-Term Exam -- Fall Term 2000 Page 1 of 13 pages. QUEEN'S UNIVERSITY AT KINGSTON Department of Economics
ECOOMICS 35*-A Md-Term Exam -- Fall Term 000 Page of 3 pages QUEE'S UIVERSITY AT KIGSTO Department of Economcs ECOOMICS 35* - Secton A Introductory Econometrcs Fall Term 000 MID-TERM EAM ASWERS MG Abbott
More informationDepartment of Quantitative Methods & Information Systems. Time Series and Their Components QMIS 320. Chapter 6
Department of Quanttatve Methods & Informaton Systems Tme Seres and Ther Components QMIS 30 Chapter 6 Fall 00 Dr. Mohammad Zanal These sldes were modfed from ther orgnal source for educatonal purpose only.
More informationF statistic = s2 1 s 2 ( F for Fisher )
Stat 4 ANOVA Analyss of Varance /6/04 Comparng Two varances: F dstrbuton Typcal Data Sets One way analyss of varance : example Notaton for one way ANOVA Comparng Two varances: F dstrbuton We saw that the
More informationMD. LUTFOR RAHMAN 1 AND KALIPADA SEN 2 Abstract
ISSN 058-71 Bangladesh J. Agrl. Res. 34(3) : 395-401, September 009 PROBLEMS OF USUAL EIGHTED ANALYSIS OF VARIANCE (ANOVA) IN RANDOMIZED BLOCK DESIGN (RBD) ITH MORE THAN ONE OBSERVATIONS PER CELL HEN ERROR
More informationStructure and Drive Paul A. Jensen Copyright July 20, 2003
Structure and Drve Paul A. Jensen Copyrght July 20, 2003 A system s made up of several operatons wth flow passng between them. The structure of the system descrbes the flow paths from nputs to outputs.
More informationAnswers Problem Set 2 Chem 314A Williamsen Spring 2000
Answers Problem Set Chem 314A Wllamsen Sprng 000 1) Gve me the followng crtcal values from the statstcal tables. a) z-statstc,-sded test, 99.7% confdence lmt ±3 b) t-statstc (Case I), 1-sded test, 95%
More informationIntroduction to Dummy Variable Regressors. 1. An Example of Dummy Variable Regressors
ECONOMICS 5* -- Introducton to Dummy Varable Regressors ECON 5* -- Introducton to NOTE Introducton to Dummy Varable Regressors. An Example of Dummy Varable Regressors A model of North Amercan car prces
More informationTopic- 11 The Analysis of Variance
Topc- 11 The Analyss of Varance Expermental Desgn The samplng plan or expermental desgn determnes the way that a sample s selected. In an observatonal study, the expermenter observes data that already
More information18. SIMPLE LINEAR REGRESSION III
8. SIMPLE LINEAR REGRESSION III US Domestc Beers: Calores vs. % Alcohol Ftted Values and Resduals To each observed x, there corresponds a y-value on the ftted lne, y ˆ ˆ = α + x. The are called ftted values.
More information28. SIMPLE LINEAR REGRESSION III
8. SIMPLE LINEAR REGRESSION III Ftted Values and Resduals US Domestc Beers: Calores vs. % Alcohol To each observed x, there corresponds a y-value on the ftted lne, y ˆ = βˆ + βˆ x. The are called ftted
More informationInterval Estimation in the Classical Normal Linear Regression Model. 1. Introduction
ECONOMICS 35* -- NOTE 7 ECON 35* -- NOTE 7 Interval Estmaton n the Classcal Normal Lnear Regresson Model Ths note outlnes the basc elements of nterval estmaton n the Classcal Normal Lnear Regresson Model
More informationx i1 =1 for all i (the constant ).
Chapter 5 The Multple Regresson Model Consder an economc model where the dependent varable s a functon of K explanatory varables. The economc model has the form: y = f ( x,x,..., ) xk Approxmate ths by
More informationDO NOT OPEN THE QUESTION PAPER UNTIL INSTRUCTED TO DO SO BY THE CHIEF INVIGILATOR. Introductory Econometrics 1 hour 30 minutes
25/6 Canddates Only January Examnatons 26 Student Number: Desk Number:...... DO NOT OPEN THE QUESTION PAPER UNTIL INSTRUCTED TO DO SO BY THE CHIEF INVIGILATOR Department Module Code Module Ttle Exam Duraton
More informationCharged Particle in a Magnetic Field
Charged Partle n a Magnet Feld Mhael Fowler 1/16/08 Introduton Classall, the fore on a harged partle n eletr and magnet felds s gven b the Lorentz fore law: v B F = q E+ Ths velot-dependent fore s qute
More informationPhase Transition in Collective Motion
Phase Transton n Colletve Moton Hefe Hu May 4, 2008 Abstrat There has been a hgh nterest n studyng the olletve behavor of organsms n reent years. When the densty of lvng systems s nreased, a phase transton
More informationBIO Lab 2: TWO-LEVEL NORMAL MODELS with school children popularity data
Lab : TWO-LEVEL NORMAL MODELS wth school chldren popularty data Purpose: Introduce basc two-level models for normally dstrbuted responses usng STATA. In partcular, we dscuss Random ntercept models wthout
More informationStatistics MINITAB - Lab 2
Statstcs 20080 MINITAB - Lab 2 1. Smple Lnear Regresson In smple lnear regresson we attempt to model a lnear relatonshp between two varables wth a straght lne and make statstcal nferences concernng that
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Exerments-I MODULE III LECTURE - 2 EXPERIMENTAL DESIGN MODELS Dr. Shalabh Deartment of Mathematcs and Statstcs Indan Insttute of Technology Kanur 2 We consder the models
More information1-FACTOR ANOVA (MOTIVATION) [DEVORE 10.1]
1-FACTOR ANOVA (MOTIVATION) [DEVORE 10.1] Hgh varance between groups Low varance wthn groups s 2 between/s 2 wthn 1 Factor A clearly has a sgnfcant effect!! Low varance between groups Hgh varance wthn
More informationA New Method of Construction of Robust Second Order Rotatable Designs Using Balanced Incomplete Block Designs
Open Journal of Statsts 9-7 http://d.do.org/.6/os..5 Publshed Onlne January (http://www.srp.org/ournal/os) A ew Method of Construton of Robust Seond Order Rotatable Desgns Usng Balaned Inomplete Blok Desgns
More informationHorizontal mergers for buyer power. Abstract
Horzontal mergers for buyer power Ramon Faul-Oller Unverstat d'alaant Llus Bru Unverstat de les Illes Balears Abstrat Salant et al. (1983) showed n a Cournot settng that horzontal mergers are unproftable
More informationSystems of Equations (SUR, GMM, and 3SLS)
Lecture otes on Advanced Econometrcs Takash Yamano Fall Semester 4 Lecture 4: Sstems of Equatons (SUR, MM, and 3SLS) Seemngl Unrelated Regresson (SUR) Model Consder a set of lnear equatons: $ + ɛ $ + ɛ
More informationLecture Notes on Linear Regression
Lecture Notes on Lnear Regresson Feng L fl@sdueducn Shandong Unversty, Chna Lnear Regresson Problem In regresson problem, we am at predct a contnuous target value gven an nput feature vector We assume
More informationIII. Econometric Methodology Regression Analysis
Page Econ07 Appled Econometrcs Topc : An Overvew of Regresson Analyss (Studenmund, Chapter ) I. The Nature and Scope of Econometrcs. Lot s of defntons of econometrcs. Nobel Prze Commttee Paul Samuelson,
More informationFall 2012 Analysis of Experimental Measurements B. Eisenstein/rev. S. Errede
Fall 0 Analyss of Expermental easurements B. Esensten/rev. S. Errede We now reformulate the lnear Least Squares ethod n more general terms, sutable for (eventually extendng to the non-lnear case, and also
More informationTwo-factor model. Statistical Models. Least Squares estimation in LM two-factor model. Rats
tatstcal Models Lecture nalyss of Varance wo-factor model Overall mean Man effect of factor at level Man effect of factor at level Y µ + α + β + γ + ε Eε f (, ( l, Cov( ε, ε ) lmr f (, nteracton effect
More informationMachine Learning: and 15781, 2003 Assignment 4
ahne Learnng: 070 and 578, 003 Assgnment 4. VC Dmenson 30 onts Consder the spae of nstane X orrespondng to all ponts n the D x, plane. Gve the VC dmenson of the followng hpothess spaes. No explanaton requred.
More informationProblem Set 9 Solutions
Desgn and Analyss of Algorthms May 4, 2015 Massachusetts Insttute of Technology 6.046J/18.410J Profs. Erk Demane, Srn Devadas, and Nancy Lynch Problem Set 9 Solutons Problem Set 9 Solutons Ths problem
More informationLimited Dependent Variables
Lmted Dependent Varables. What f the left-hand sde varable s not a contnuous thng spread from mnus nfnty to plus nfnty? That s, gven a model = f (, β, ε, where a. s bounded below at zero, such as wages
More informationEcon Statistical Properties of the OLS estimator. Sanjaya DeSilva
Econ 39 - Statstcal Propertes of the OLS estmator Sanjaya DeSlva September, 008 1 Overvew Recall that the true regresson model s Y = β 0 + β 1 X + u (1) Applyng the OLS method to a sample of data, we estmate
More informationReduced slides. Introduction to Analysis of Variance (ANOVA) Part 1. Single factor
Reduced sldes Introducton to Analss of Varance (ANOVA) Part 1 Sngle factor 1 The logc of Analss of Varance Is the varance explaned b the model >> than the resdual varance In regresson models Varance explaned
More informationEconometrics: What's It All About, Alfie?
ECON 351* -- Introducton (Page 1) Econometrcs: What's It All About, Ale? Usng sample data on observable varables to learn about economc relatonshps, the unctonal relatonshps among economc varables. Econometrcs
More informationLecture 6 More on Complete Randomized Block Design (RBD)
Lecture 6 More on Complete Randomzed Block Desgn (RBD) Multple test Multple test The multple comparsons or multple testng problem occurs when one consders a set of statstcal nferences smultaneously. For
More informationLECTURE 9 CANONICAL CORRELATION ANALYSIS
LECURE 9 CANONICAL CORRELAION ANALYSIS Introducton he concept of canoncal correlaton arses when we want to quantfy the assocatons between two sets of varables. For example, suppose that the frst set of
More informationMaximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models
ECO 452 -- OE 4: Probt and Logt Models ECO 452 -- OE 4 Maxmum Lkelhood Estmaton of Bnary Dependent Varables Models: Probt and Logt hs note demonstrates how to formulate bnary dependent varables models
More informationwhere I = (n x n) diagonal identity matrix with diagonal elements = 1 and off-diagonal elements = 0; and σ 2 e = variance of (Y X).
11.4.1 Estmaton of Multple Regresson Coeffcents In multple lnear regresson, we essentally solve n equatons for the p unnown parameters. hus n must e equal to or greater than p and n practce n should e
More information