计量经济学导论chapter13.ppt

《计量经济学导论chapter13.ppt》由会员分享，可在线阅读，更多相关《计量经济学导论chapter13.ppt（8页珍藏版）》请在课桌文档上搜索。

1、Chapter 13,Pooling Cross Sections across Time:Simple Panel Data Methods,Wooldridge:Introductory Econometrics:A Modern Approach,5e,需磁长挖号梗军紫硝脖初莽裁茧锣铂坝掖抄燎相社驮钮抚方免坯亥戒旺地计量经济学导论chapter 13计量经济学导论chapter 13,Policy analysis with pooled cross sectionsTwo or more independently sampled cross sections can be used

2、to evaluate the impact of a certain event or policy changeExample:Effect of new garbage incinerator on housing pricesExamine the effect of the location of a house on its price before and after the garbage incinerator was built:,After incinerator was built,Before incinerator was built,Pooled Cross Se

3、ctions and Simple Panel Data Methods,姜绊撮吝逻咳虹窖懈瞧描染柞栅绣署扭累佩杖梢扬辑恃隧游炬粗免邪亚益计量经济学导论chapter 13计量经济学导论chapter 13,Example:Garbage incinerator and housing prices(cont.)It would be wrong to conclude from the regression after the incinerator is there that being near the incinerator depresses prices so stronglyOn

4、e has to compare with the situation before the incinerator was built:In the given case,this is equivalent toThis is the so called difference-in-differences estimator(DiD),Incinerator depresses prices but location was one with lower prices anyway,Pooled Cross Sections and Simple Panel Data Methods,籽佣

5、戒砖及嘻躁膀皇浸巡渺震殿躁堑湿验荷伏鸯恫织殊塌遗瞅屿波嘉前酚计量经济学导论chapter 13计量经济学导论chapter 13,Difference-in-differences in a regression frameworkIn this way standard errors for the DiD-effect can be obtainedIf houses sold before and after the incinerator was built were sys-tematically different,further explanatory variables sho

6、uld be includedThis will also reduce the error variance and thus standard errorsBefore/After comparisons in natural experiments“DiD can be used to evaluate policy changes or other exogenous events,Differential effect of being in the location and after the incinerator was built,Pooled Cross Sections

7、and Simple Panel Data Methods,圃豁辗锐郝钉敖验匪蝶源惦弗瘫碘肋溶惹茵嗡健典舔乡挂滑钡擅佬若攀驼计量经济学导论chapter 13计量经济学导论chapter 13,Policy evaluation using difference-in-differences,Compare the difference in outcomes of the units that are affected by the policy change(=treatment group)and those who are not affected(=control group)bef

8、ore and after the policy was enacted.For example,the level of unemployment benefits is cut but only for group A(=treatment group).Group A normally has longer unemployment durations than group B(=control group).If the diffe-rence in unemployment durations between group A and group B becomes smaller a

9、fter the reform,reducing unemployment benefits reduces unemployment duration for those affected.Caution:Difference-in-differences only works if the difference in outcomes between the two groups is not changed by other factors than the policy change(e.g.there must be no differential trends).,Compare

10、outcomes of the two groups before and after the policy change,Pooled Cross Sections and Simple Panel Data Methods,中滥巳粤肃弱踩忱蝴召篮汕案傲跪挣褐纬氯岔腮谅清积篮烧铆多摇旧乐搭计量经济学导论chapter 13计量经济学导论chapter 13,Two-period panel data analysisExample:Effect of unemployment on city crime rateAssume that no other explanatory variabl

11、es are available.Will it be possible to estimate the causal effect of unemployment on crime?Yes,if cities are observed for at least two periods and other factors affecting crime stay approximately constant over those periods:,Unobserved time-constant factors(=fixed effect),Other unobserved factors(=

12、idiosyncratic error),Time dummy for the second period,Pooled Cross Sections and Simple Panel Data Methods,武尚属语袁资鸦屑症整该拉括绞槽郡匈闰畴家宽拭滇沿阀缕莎扰枷匙剖位计量经济学导论chapter 13计量经济学导论chapter 13,Example:Effect of unemployment on city crime rate(cont.)Estimate differenced equation by OLS:,Subtract:,Secular increase in cri

13、me,+1 percentage point unemploy-ment rate leads to 2.22 more crimes per 1,000 people,Fixed effect drops out!,Pooled Cross Sections and Simple Panel Data Methods,旺煞所繁似乔蹋揍规糊二窟状炮嚏柱迸沙辟苑咏谈瞥思穆筋逢存泣固孔满计量经济学导论chapter 13计量经济学导论chapter 13,Discussion of first-differenced panel estimatorFurther explanatory varia

14、bles may be included in original equationNote that there may be arbitrary correlation between the unobserved time-invariant characteristics and the included explanatory variablesOLS in the original equation would therefore be inconsistentThe first-differenced panel estimator is thus a way to consist

15、ently estimate causal effects in the presence of time-invariant endogeneityFor consistency,strict exogeneity has to hold in the original equationFirst-differenced estimates will be imprecise if explanatory variables vary only little over time(no estimate possible if time-invariant),Pooled Cross Sections and Simple Panel Data Methods,凛究筷溯癣瘩划踌殴绰喇喂呼骚舅呀宴续衙愉枢装撕虑邮债毛呕荧蚕第幻计量经济学导论chapter 13计量经济学导论chapter 13,