# CAO HỌC TÀI LIỆU PHÂN TÍCH STATA 2

32 327 2

Tài liệu hạn chế xem trước, để xem đầy đủ mời bạn chọn Tải xuống

## Thông tin tài liệu

Ngày đăng: 27/10/2014, 22:40

CAO HỌC TÀI LIỆU PHÂN TÍCH STATA . NHỮNG ĐIỀU CẦN BIẾT VỀ CAO HỌC TÀI LIỆU PHÂN TÍCH STATA, LÝ THUYẾT CAO HỌC TÀI LIỆU PHÂN TÍCH STATA, BÀI GIẢNG CAO HỌC TÀI LIỆU PHÂN TÍCH STATA. TỔNG QUAN CAO HỌC TÀI LIỆU PHÂN TÍCH STATA Pham Thi Bich Ngoc, Ph.D. (University of Kiel, Germany) FEC/Hoa Sen University ngoc.phamthibich@hoasen.edu.vn UNIVERSITY OF ECONOMICS HOCHIMINHCITY, June 2014 June 14 - Dr. Pham Thi Bich Ngoc 1  Multicollinearity occurs when two or more independent variables in a regression model are highly correlated to each other  Standard error of the OLS parameter estimate will be higher if the corresponding independent variable is more highly correlated to the other independent variables in the model June 14 - Dr. Pham Thi Bich Ngoc 2  Perfect multicollinearity occurs when there is a perfect linear correlation between two or more independent variables  When independent variable takes a constant value in all observations June 14 - Dr. Pham Thi Bich Ngoc 3  The symptoms of a multicollinearity problem 1. independent variable(s) considered critical in explaining the model’s dependent variable are not statistically significant according to the tests June 14 - Dr. Pham Thi Bich Ngoc 4 2. High R 2 , highly significant F-test, but few or no statistically significant t tests 3. Parameter estimates drastically change values and become statistically significant when excluding some independent variables from the regression June 14 - Dr. Pham Thi Bich Ngoc 5  A simple test for multicollinearity is to conduct “artificial” regressions between each independent variable (as the “dependent” variable) and the remaining independent variables  Variance Inflation Factors (VIF j ) are calculated as:    2 j j R1 1 VIF   June 14 - Dr. Pham Thi Bich Ngoc 6  VIF j = 2, for example, means that variance is twice what it would be if X j , was not affected by multicollinearity  A VIF j >10 is clear evidence that the estimation of B j is being affected by multicollinearity June 14 - Dr. Pham Thi Bich Ngoc 7  Although it is useful to be aware of the presence of multicollinearity, it is not easy to remedy severe (non-perfect) multicollinearity  If possible, adding observations or taking a new sample might help lessen multicollinearity June 14 - Dr. Pham Thi Bich Ngoc 8  Exclude the independent variables that appear to be causing the problem  Modifying the model specification sometimes help, for example:  using real instead of nominal economic data  using a reciprocal instead of a polynomial specification on a given independent variable June 14 - Dr. Pham Thi Bich Ngoc 9 10  Var( u | x ) = σ 2 [MLR.5]  Homoscedasticity assumption: variance is constant  Recall the assumption of homoskedasticity implied that conditional on the explanatory variables, the variance of the unobserved error, u , was constant  If this is not true, that is if the variance of u is different for different values of the x ’s, then the errors are heteroskedastic June 14 - Dr. Pham Thi Bich Ngoc [...]... Ngoc 20     Pooled OLS Fixed Effects (FE), Random Effects (RE), and Hausman test Two stages Least Square (2SLS) Generalized Methods of Moments (GMM) David Roodman, 20 09 "How to do xtabond2: An introduction to difference and system GMM in Stata, " Stata Journal, StataCorp LP, vol 9(1), pages 86-136, March David Roodman, 20 06 "How to Do xtabond2: An Introduction to "Difference" and "System" GMM in Stata, "... Dr Pham Thi Bich Ngoc 27 We assume that: E (v i )  E ( it )  0 E (v i2 )  v2 2 2 E ( it )    E ( it v j )  0  i ,t , j (both components homoscedas tic) E ( it  js )  0 if t  s or i  j (no autocorrel ation) E (v i v j )  0 if i  j (no across group correlatio n) E (v i x it )  E ( it x it )  0 (both independen t of regressor) (independe nce of two components ) STATA: xtreg … , re... Variables (LSDV) N yit   a0i Dit  a1 xit  uit i 1 STATA: xtreg … i.year June 14 - Dr Pham Thi Bich Ngoc 24 (Two Way) Fixed Effects Model:  allow the intercept to vary across the different time periods (Two Way Fixed Effects): N T i 1 t 1 yit   a0i Dit   a2iTit  a1 xit  uit STATA: xtreg … i.id i.year June 14 - Dr Pham Thi Bich Ngoc 25 Fixed Effects/Within:  discards all variation between... captures differences over time and over firms??? June 14 - Dr Pham Thi Bich Ngoc 22 Pooled regression by OLS may result in heterogeneity bias : Pooled regression: y yit=a0+a1xit+uit • • • • • • • • • • • • • • • • True model: Firm 4 True model: Firm 3 True model: Firm 2 True model: Firm 1 x June 14 - Dr Pham Thi Bich Ngoc 23 Fixed Effects Estimation: (One Way) Fixed Effects Model: If each group (firm)... Papers 103, Center for Global Development June 14 - Dr Pham Thi Bich Ngoc 21 Pooled regression by OLS (STATA_ xtreg…) • Suppose y is firm output and x is a number of employees • We have i = 1…n firms and t = 1…T time periods (year) • A simple econometric model: yit  a0  a1 xit  uit uit is a random error term: E (uit ) ~ N (0, 2) Assumptions: intercept and slope coefficients are constant across time... years June 14 - Dr Pham Thi Bich Ngoc 14  Test: Durbin-Watson statistic:  (e  e d e i i 1 ) 2 i 2 , for n and K -1 d.f Positive Zone of No Autocorrelation Zone of Negative autocorrelation indecision indecision autocorrelation | _| | _| _| | _| 0 d-lower d-upper 2 4-d-upper 4-d-lower 4 Autocorrelation is clearly evident Ambiguous – cannot rule out autocorrelation... all variation between individuals and uses only variation over time within an individual yit  yi  a0i  a0i  a1 ( xit  xi )  (uit  ui )  yit  yi  a1 ( xit  xi )  uit STATA: xtreg … , fe June 14 - Dr Pham Thi Bich Ngoc 26 Random Effects Estimation: RE >< FE? FE assumes that each group (firm) has a non-stochastic group-specific component to y RE treats these unobservable effects as being stochastic... f(y|x) x1 x2 E(y|x) = b0 + b 1x x3 x June 14 - Dr Pham Thi Bich Ngoc 11     This provides an estimator of the variance of which is consistent The square root of this can be used as a ˆ bj standard error for inference Typically call these robust or heteroscedasticity-consistent standard errors [Or White standard errors or Huber standard errors…] June 14 - Dr Pham Thi Bich Ngoc 12   Important... independen t of regressor) (independe nce of two components ) STATA: xtreg … , re June 14 - Dr Pham Thi Bich Ngoc 28 Choosing between Fixed Effects (FE) and Random Effects (RE) 1 With large T and small N there is likely to be little difference, so FE is preferable as it is easier to compute 2 With large N and small T, estimates can differ significantly If the cross-sectional groups are a random sample... RE is more efficient than FE June 14 - Dr Pham Thi Bich Ngoc 29 June 14 - Dr Pham Thi Bich Ngoc 30 Hausman test: Tests for the statistical significance of the difference between the coefficient estimates obtained by FE and by RE, under then null hypothesis that the RE estimates are efficient and consistent, and FE estimates are inefficient STATA: hausman FE RE (LM test: xttest0 after xtreg , re) June . |_______________|__________________|_____________|_____________|__________________|___________________| 0 d-lower d-upper 2 4-d-upper 4-d-lower 4 Autocorrelation is clearly evident Ambiguous – cannot rule out autocorrelation Autocorrelation in not evident June 14 - Dr. Pham Thi. heteroskedastic June 14 - Dr. Pham Thi Bich Ngoc 11 . x x 1 x 2 f(y|x) Picture of Heteroskedasticity x 3 . . E(y|x) = b 0 + b 1 x June 14 - Dr. Pham Thi Bich Ngoc 12  This provides. lead to overestimates in succeeding years. 14  Test: Durbin-Watson statistic: d  (e i  e i 1 ) 2  e i 2  , for n and K-1 d.f. Positive Zone of No Autocorrelation Zone of Negative autocorrelation
- Xem thêm -