D of disturbance term ui and xi mechanics 1 order n

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: y assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Consequences Wrong s.e. Consequence s.e. are estimators of s.d. of estimators. They assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Usually s.e.’s will be biased downwards in the presence of heteroscedasticity. Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Consequences Wrong s.e. Consequence s.e. are estimators of s.d. of estimators. They assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Usually s.e.’s will be biased downwards in the presence of heteroscedasticity. In turn, t-stats will be larger than what they should be. Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Consequences Wrong s.e. Consequence s.e. are estimators of s.d. of estimators. They assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Usually s.e.’s will be biased downwards in the presence of heteroscedasticity. In turn, t-stats will be larger than what they should be. Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Consequences Wrong s.e. Consequence s.e. are estimators of s.d. of estimators. They assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Usually s.e.’s will be biased downwards in the presence of heteroscedasticity. In turn, t-stats will be larger than what they should be. Bonus Question If t-stat larger than correct value, what type of error will occur more often? Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Consequences Wrong s.e. Consequence s.e. are estimators of s.d. of estimators. They assume that distribution of disturbance term is homoscedastic (which reflects in s.d. of estimators). If heteroscedasticity present, assumption is wrong leading to biased s.e. estimators. Usually s.e.’s will be biased downwards in the presence of heteroscedasticity. In turn, t-stats will be larger than what they should be. Bonus Question If t-stat larger than correct value, what type of error will occur more often? Type-I error as reject more often than you should. Introduction Heteroscedasticity Past Exam Practice Question Moving Forward: Model B Detection Goldfeld-Quandt Test This test assumes that σui is proportional to size o...
View Full Document

Ask a homework question - tutors are online