ERF Training Workshop Panel Data 1 Raimundo Soro - Catholic University of Chile
- 1. 3 Warnings Chileans speak very fast. I speak even faster slow me down if I rush or dont finish sentences I am very informal. My teaching is informal ask, reply and participate as much as possible. We all learn from this. I am politically incorrect. Stop me if you feel offended.
- 2. ERF Training Workshop Panel Data 1 Raimundo Soto Instituto de Econom鱈a, PUC-Chile
- 3. MENU INTRODUCTION STATIC MODELS FOR CONTINUOUS VARIABLES STATIC MODELS FOR DISCRETE VARIABLES DYNAMIC MODELS FOR CONTINUOUS VARIABLES DYNAMIC MODELS FOR DISCRETE VARIABLES 3
- 4. INTRODUCTION Considerthe followingstatement : Participationratesfor womeninthelabor marketis 25%(WorldBank,2018) How do youreadthis information? Case1:onequarterofthewomenparticipatesinthe labormarketall ofthetime,therestneverdoes Case2:ineveryinstant,womenhave25%chanceof beinginthelabormarketand75%ofbeingoutof thelabormarket 4
- 5. INTRODUCTION Case1:onequarterof thewomenparticipatesin the labor marketallof thetime, therestneverdoes Women are heterogeneous No turnover in the labor market for females The best predictor of future labor market status is her current status 5
- 6. INTRODUCTION Case2:in everyinstant,womenhave25%chanceof being inthelabor marketand75%of being outof the labor market Women are homogeneous Very high turnover in the labor market for females The best predictor of future labor market status is her expected value: 村, if being in the labor force is 1 and 0 otherwise 6
- 7. INTRODUCTION Obviouslyitisneithercase1 norcase2exclusively A betterwaytomodelthe phenomenonisasthe probability of awomenof certaincharacteristicsto participateinthemarketateveryinstantof time Forthis weneedpaneldata,i.e.,informationon the statusinthelabormarketofeverywomaniandher characteristicsattimet 7
- 8. INTRODUCTION Panel Data Repeated observations of the same individual in time Repeated cross-sections and synthetic panels 8
- 9. INTRODUCTION Advantages of Panel Data True but not very relevant: Increase in the degrees of freedom, improve on estimation precision, inferences and predictions. True and very relevant: Better management of heterogeneity and its evolution Account for unobservable characteristics of the individuals that can potentially bias econometric results 9
- 10. INTRODUCTION Consider the following true model = 腫 + 署 + Since 腫 cannot be observed, the estimated model is: = 署 + Where = 腫 + If (, 腫) 0, then and the estimator is inconsistent (biased) 10
- 11. INTRODUCTION Why is 腫 unobserved? It cannot be truly observed (measured) There are no data 11
- 12. INTRODUCTION Case when it cannot be observed Consider the microeconomic case of school performance (cross section) = + 1 + 2 ＄ +3 乞 + Missing: natural ability of individuals 基巨 (unobservable) But 基 could correlate with: Parents Education, cov 乞, 基 > 0 School quality, cov , 基 > 0 Study effort, cov 諮, 基 < 0 12
- 13. INTRODUCTION Case when data are not available Consider macroeconomic case of consumption (time series) consumers that consume according to permanent income hypothesis, 駒腫諮 = 0 + 1 腫 + where 腫 = + (乞 +, ) and = consumers under liquidity constraints, 駒瑞 = 0 + 1 + 13
- 14. INTRODUCTION Data refers to aggregate consumption, i.e. 駒 = 駒腫諮+ 駒瑞 But the number of individuals in each group changes in time (heterogeneity) according to: Business cycle Financial sector development Human capital levels Hence, there will be selection bias 14
- 15. Type of Models An ignorant estimator (pooled) Individual effects estimator (fixed effects) Sample-determined estimator (random effects) Choice of models: Hausman-Wu Test Poolability Test Practical examples in Stata 15
- 16. Consistency Recall the OLS estimator of model = ヰ + : = モ 1 モ = (, ) ｐ() Then = モ 1 モ ヰ + = + モ 1 モ介 OLS estimator is consistent (unbiased) iff モ = 0 16