# Heteroskedasticity WLS Lecture

Description
Categories
Published

View again

All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
Share
Transcript
Heteroskedasticity 1/55 Heteroskedasticity in Regression Paul E. Johnson 1 2 1 Department of Political Science 2 Center for Research Methods and Data Analysis, University of Kansas 2014  Heteroskedasticity 2/55Introduction Outline 1  Introduction 2  Fix #1: Robust Standard Errors 3  Weighted Least SquaresCombine Subsets of a SampleRandom coeﬃcient modelAggregate Data 4  Testing for heteroskedasticityCategorical HeteroskedasticityChecking for Continuous HeteroskedasticityToward a General Test for Heteroskedasticity 5  Appendix: Robust Variance Estimator Derivation 6  Practice Problems  Heteroskedasticity 3/55Introduction Remember the Theory Linear Model y  i   =  β  0  +  β  1 x  1 i   +  e  i  About the error term, we assumed, for all  i  , E  ( e  i  ) = 0 for all i Var  ( e  i  ) =  E  [( e  i  − E  ( e  i  )) 2 ] =  σ 2 (Homoskedasticity).There is no  i   subscript on  σ 2 . It is the same for all rows. Heteroskedasticity (or heteroscedasticity): the assumption of homogeneous variance is violated.  Heteroskedasticity 4/55Introduction Homoskedasticity means Var  ( e  ) =  σ 2 e   0 0 0 00  σ 2 e   0 0 00 0  σ 2 e   0 00 0 0 ... 00 0 0 0  σ 2 e  

Apr 16, 2018

#### Sugestões. Parte 2 Rio 2012

Apr 16, 2018
Search
Similar documents

View more...
Tags

Related Search