Presentation is loading. Please wait.

Presentation is loading. Please wait.

Lecture 4 Econ 488. Ordinary Least Squares (OLS) Objective of OLS  Minimize the sum of squared residuals: where Remember that OLS is not the only possible.

Similar presentations


Presentation on theme: "Lecture 4 Econ 488. Ordinary Least Squares (OLS) Objective of OLS  Minimize the sum of squared residuals: where Remember that OLS is not the only possible."— Presentation transcript:

1 Lecture 4 Econ 488

2 Ordinary Least Squares (OLS) Objective of OLS  Minimize the sum of squared residuals: where Remember that OLS is not the only possible estimator of the βs. But OLS is the best estimator under certain assumptions…

3 Classical Assumptions 1. Regression is linear in parameters 2. Error term has zero population mean 3. Error term is not correlated with X’s 4. No serial correlation 5. No heteroskedasticity 6. No perfect multicollinearity and we usually add: 7. Error term is normally distributed

4 Assumption 1: Linearity The regression model:  A) is linear It can be written as This doesn’t mean that the theory must be linear For example… suppose we believe that CEO salary is related to the firm’s sales and CEO’s tenure. We might believe the model is:

5 Assumption 1: Linearity The regression model:  B) is correctly specified The model must have the right variables No omitted variables The model must have the correct functional form This is all untestable  We need to rely on economic theory.

6 Assumption 1: Linearity The regression model:  C) must have an additive error term The model must have + ε i

7 Assumption 2: E(ε i )=0 Error term has a zero population mean E(ε i )=0 Each observation has a random error with a mean of zero What if E(ε i )≠0? This is actually fixed by adding a constant (AKA intercept) term

8 Assumption 2: E(ε i )=0 Example: Suppose instead the mean of ε i was -4. Then we know E(ε i +4)=0 We can add 4 to the error term and subtract 4 from the constant term: Y i =β 0 + β 1 X i +ε i Y i =(β 0 -4)+ β 1 X i +(ε i +4)

9 Assumption 2: E(ε i )=0 Y i =β 0 + β 1 X i +ε i Y i =(β 0 -4)+ β 1 X i +(ε i +4) We can rewrite: Y i =β 0 *+ β 1 X i +ε i * Where β 0 *= β 0 -4 and ε i *=ε i +4 Now E(ε i *)=0, so we are OK.

10 Assumption 3: Exogeneity Important!! All explanatory variables are uncorrelated with the error term E(ε i |X 1i,X 2i,…, X Ki,)=0 Explanatory variables are determined outside of the model (They are exogenous)

11 Assumption 3: Exogeneity What happens if assumption 3 is violated? Suppose we have the model, Y i =β 0 + β 1 X i +ε i Suppose X i and ε i are positively correlated When X i is large, ε i tends to be large as well.

12 Assumption 3: Exogeneity “True” Line “True Line”

13 Assumption 3: Exogeneity “True” Line “True Line” Data “True Line” Data

14 Assumption 3: Exogeneity “True Line” Data Estimated Line

15 Assumption 3: Exogeneity Why would x and ε be correlated? Suppose you are trying to study the relationship between the price of a hamburger and the quantity sold across a wide variety of Ventura County restaurants.

16 Assumption 3: Exogeneity We estimate the relationship using the following model: sales i = β 0 +β 1 price i +ε i What’s the problem?

17 Assumption 3: Exogeneity What’s the problem?  What else determines sales of hamburgers?  How would you decide between buying a burger at McDonald’s ($0.89) or a burger at TGI Fridays ($9.99)?  Quality differs  sales i = β 0 +β 1 price i +ε i  quality isn’t an X variable even though it should be.  It becomes part of ε i

18 Assumption 3: Exogeneity What’s the problem?  But price and quality are highly positively correlated  Therefore x and ε are also positively correlated.  This means that the estimate of β 1 will be too high  This is called “Omitted Variables Bias” (More in Chapter 6)

19 Assumption 4: No Serial Correlation Serial Correlation: The error terms across observations are correlated with each other i.e. ε 1 is correlated with ε 2, etc. This is most important in time series If errors are serially correlated, an increase in the error term in one time period affects the error term in the next.

20 Assumption 4: No Serial Correlation The assumption that there is no serial correlation can be unrealistic in time series Think of data from a stock market…

21 Assumption 4: No Serial Correlation Stock data is serially correlated!

22 Assumption 5: Homoskedasticity Homoskedasticity: The error has a constant variance This is what we want…as opposed to Heteroskedasticity: The variance of the error depends on the values of Xs.

23 Assumption 5: Homoskedasticity Homoskedasticity: The error has constant variance

24 Assumption 5: Homoskedasticity Heteroskedasticity: Spread of error depends on X.

25 Assumption 5: Homoskedasticity Another form of Heteroskedasticity

26 Assumption 6: No Perfect Multicollinearity Two variables are perfectly collinear if one can be determined perfectly from the other (i.e. if you know the value of x, you can always find the value of z). Example: If we regress income on age, and include both age in months and age in years.  But age in years = age in months/12  e.g. if we know someone is 246 months old, we also know that they are 20.5 years old.

27 Assumption 6: No Perfect Multicollinearity What’s wrong with this? income i = β 0 + β 1 agemonths i + β 2 ageyears i + ε i What is β 1 ? It is the change in income associated with a one unit increase in “age in months,” holding age in years constant.  But if you hold age in years constant, age in months doesn’t change!

28 Assumption 6: No Perfect Multicollinearity β 1 = Δincome/Δagemonths Holding Δageyears = 0 If Δageyears = 0; then Δagemonths = 0 So β 1 = Δincome/0 It is undefined!

29 Assumption 6: No Perfect Multicollinearity When more than one independent variable is a perfect linear combination of the other independent variables, it is called Perfect MultiCollinearity Example: Total Cholesterol, HDL and LDL Total Cholesterol = LDL + HDL Can’t include all three as independent variables in a regression. Solution: Drop one of the variables.

30 Assumption 7: Normally Distributed Error

31 This is required not required for OLS, but it is important for hypothesis testing More on this assumption next time.

32 Putting it all together Last class, we talked about how to compare estimators. We want: 1. is unbiased.   on average, the estimator is equal to the population value 2. is efficient  The variance of the estimator is as small as possible

33 Putting it all togehter

34 Gauss-Markov Theorem Given OLS assumptions 1 through 6, the OLS estimator of β k is the minimum variance estimator from the set of all linear unbiased estimators of β k for k=0,1,2,…,K OLS is BLUE The Best, Linear, Unbiased Estimator

35 Gauss-Markov Theorem What happens if we add assumption 7? Given assumptions 1 through 7, OLS is the best unbiased estimator Even out of the non-linear estimators OLS is BUE?

36 Gauss-Markov Theorem With Assumptions 1-7 OLS is: 1. Unbiased: 2. Minimum Variance – the sampling distribution is as small as possible 3. Consistent – as n  ∞, the estimators converge to the true parameters  As n increases, variance gets smaller, so each estimate approaches the true value of β. 4. Normally Distributed. You can apply statistical tests to them.


Download ppt "Lecture 4 Econ 488. Ordinary Least Squares (OLS) Objective of OLS  Minimize the sum of squared residuals: where Remember that OLS is not the only possible."

Similar presentations


Ads by Google