# ie_Slide04 - Introductory Econometrics ECON2206/ECON3209...

This preview shows pages 1–8. Sign up to view the full content.

Introductory Econometrics ECON2206/ECON3209 Slides04 LecturerRachida Ouysse ie_Slides04 RO, School of Economics, UNSW 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4. Multiple Regression Model: Inference (Ch4) 4. Multiple Regression Model: Inference • Lecture plan lassical linear model assumptions Classical linear model assumptions – Sampling distribution of OLS estimators under CLM esting hypothesis about one population parameter – Testing hypothesis about one population parameter – p-values onfidence intervals – Confidence intervals – Test hypothesis with CI ie_Slides04 RO, School of Economics, UNSW 2
4. Multiple Regression Model: Inference (Ch4) • Motivation: y = β 0 + β 1 x 1 +...+ β k x k + u – Goal is to gain knowledge about the population parameters ( β ’s) in the model. – OLS provides the point estimates of the parameters. OLS will get it right on average (being unbiased). – Knowing the mean and variance of is not enough. j ˆ • how to decide if a hypothesis is supported or not? • what we can say about the “true values”? We need the sampling distribution of the OLS estimators to answer these questions. – To simplify, we use a strong assumption here (and will relax it for large-sample cases). ie_Slides04 RO, School of Economics, UNSW 3

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4. Multiple Regression Model: Inference (Ch4) • Normality assumption 6. (MLR6, normality) The disturbance u is independent of all explanatory variables and normally distributed with mean zero and variance σ 2 : u ~ Normal(0, σ 2 ) . This is a very strong assumption. It implies both yg p p MLR4 (ZCM) and MLR5 (homoskedasticity). MLR1-6 together are known as the classical linear model (CLM) assumptions. Under CLM, the OLS produces the minimum variance unbiased estimators. They are the best of unbiased estimators ( not just the est of linear unbiased estimators best of linear unbiased estimators ). ie_Slides04 RO, School of Economics, UNSW 4
4. Multiple Regression Model: Inference (Ch4) • Normality assumption – CLM implies It is completely characterised by the mean and variance. y | x ~ Normal( β 0 + β 1 x 1 +...+ β k x k , σ 2 ) . LM also implies is normally distributed ˆ CLM also implies is normally distributed. – Whether or not MLR6 is a reasonable assumption j depends on data. Is it reasonable for wage model, given that no wage can be negative? Empirically, it is reasonable for log( wage ) model. – MLR6 is restrictive. But the results here will be useful for large-sample cases (Ch5) without MLR6. ie_Slides04 RO, School of Economics, UNSW 5

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4. Multiple Regression Model: Inference (Ch4) • Sampling distribution of OLS Theorem 4.1 (normal sampling distribution) Under CLM, conditional on independent variables, ormal ˆ 2 where the variance is given in Ch3 (ie_Slides03):   , , Normal ~ j j j . ,..., 1 , ) 1 ( ) ˆ ( 2 2 2 k j R SST Var j j j j – It implies: ˆ . ) ˆ ( ) ˆ ( ), , ( Normal ~ ) ˆ ( j j j j j Var sd sd 1 0 ie_Slides04 RO, School of Economics, UNSW 6
4. Multiple Regression Model: Inference (Ch4) • Sampling distribution of OLS – In practice, we have to estimate σ 2 and ˆ β Var . ,..., , ) ( ˆ ) ˆ ( ˆ k j R SST ar V j j j 1

This preview has intentionally blurred sections. Sign up to view the full version.

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

{[ snackBarMessage ]}

### Page1 / 38

ie_Slide04 - Introductory Econometrics ECON2206/ECON3209...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online