21
Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Embed Size (px)

Citation preview

Page 1: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Linear Regression Basics IIIViolating Assumptions

Fin250f: Lecture 7.2

Spring 2010

Brooks, chapter 4(skim)

4.1-2, 4.4, 4.5, 4.7, 4.9-13

Page 2: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Outline

Violating assumptionsParameter stabilityModel building

Page 3: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

OLS Assumptions

Error variancesError correlationsError normalityFunctional forms and linearityOmitting variablesAdding irrelevant variables

Page 4: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Error Variance

var(ut )=σ2

var(ut) =σ t2

OLS unbiased, consistent, but inefficient

Weighting observations by noise (ARCH/GARCH)

Page 5: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Error VarianceWhich is a bigger error?

yt

yt

*

*

*

***

Y

X

Page 6: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Error Correlations

E(utut+ j ) ≠0

Patterns in residualsPlot residuals/residual diagnosticsFurther modeling necessary

If you can forecast u(t+1), need to work harder

Page 7: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Error Normality

Skewness and kurtosis in residualsTesting

Plots Bera-Jarque test

How can this impact results?

Page 8: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Bera-Jarque Test for Normality

b1 =E(u3)σ 3 ,b2 =

E(u4 )σ 4

W =Tb12

6+(b2 −3)2

24⎛

⎝⎜⎞

⎠⎟

W : χ 2 (2)

Page 9: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Nonnormal Errors: Impact

For some theory: No In practice can be big problem Many extreme data points Forecasting models work hard to fit these

extreme outliers Some solutions:

Drop data points Robust forecast objectives (absolute errors)

Page 10: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Functional Forms

Y=a+bXActual function is nonlinearSeveral types of diagnostics

Higher order (squared) terms (RESET) Think about specific nonlinear models

Neural networks Threshold models

Tricky: More later

Page 11: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

yt =a+β1xt,1 +β2xt,2 +ut

Omitting Variables

Leave out x(2)

If it is correlated with x(1) this is a problem.

Beta(1) will be biased and inconsistent.

Forecast will not be optimal

Page 12: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Irrelevant Variables

Overfitting/data snooping Model fits to noise

Impacts standard errors for coefficientsCoefficients still consistent and

unbiased

Page 13: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Parameter Stability

Known break point Chow test Predictive failure test

Unknown break Quant likelihood ratio test Recursive least squares

Page 14: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Chow Test

yt =a+ βxt + ut

yt1 =a1 +β1xt

1 + ut1

yt2 =a2 +β 2xt

2 + ut2

RSS= u∑ t

2

RSS1 = (∑ ut1)2

RSS2 = (∑ ut2 )2

Page 15: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Chow Test

RSS−(RSS1 + RSS2 )RSS1 + RSS2

(T −2k)k

k=number of regressors

2k = number of regressors unrestricted

Test statistic F(k,T-2k)

Page 16: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Predictive Failureyt =a+ βxt + ut

yt1 =a1 +β1xt

1 + ut1, Large subsample 1,T1

RSS= ut2

t=1

T

RSS1 = (t=1

T1

∑ ut1)2

T2 =T −T1

Page 17: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Predictive Failure

(RSS−RSS1) /T2

RSS1 / (T1 −k)=

Expected squared error at endExpected squared error before end

F(T2 ,T1 −k)

Page 18: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Unknown Breaks

Search for breakLook for maximum Chow levelDistribution is tricky

Monte-carlo/bootstrap

Page 19: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Recursive/rolling estimation

Recursive Estimate (1,T1) move T1 to full sample T See if parameters converge

Rolling Roll bands (t-T,t) through data Watch parameters move through time

We’ll use some of these

Page 20: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Pure Out of Sample Tests

Estimate parameters over (1,T1)Get errors over (T1+1,T)

Page 21: Linear Regression Basics III Violating Assumptions Fin250f: Lecture 7.2 Spring 2010 Brooks, chapter 4(skim) 4.1-2, 4.4, 4.5, 4.7, 4.9-13

Model Construction

General -> specific Less financial theory More statistics Problems: large unwieldy models

Simple -> general More theory at the start Problems: can leave out important stuff