搜档网
当前位置:搜档网 › 计量经济学导论斯托克第二课和第三课课件

计量经济学导论斯托克第二课和第三课课件

斯托克,沃森计量经济学第七章实证练习stata

E7.2 E7.3 E7.4

-------------------------------------------- (1) (2) ahe ahe -------------------------------------------- age 0.605*** 0.585*** (15.02) (16.02) female -3.664*** (-17.65) bachelor 8.083*** (38.00) _cons 1.082 -0.636 (0.93) (-0.59) (表2)Robust ci in parentheses *** p<0.01, ** p<0.05, * p<0.1 -------------------------------------------- N 7711 7711 -------------------------------------------- t statistics in parentheses * p<0.10, ** p<0.05, *** p<0.01 (表1) (1) 建立ahe 对age 的回归。截距估计值是1.082,斜率估计值是0.605。 (2) ①建立ahe 对age ,female 和bachelor 的回归。Age 对收入的效应的估计值是0.585。 ② age 回归系数的95%置信区间: (0.514,0.657) (3) 设H 0:βa,(2)-βa,(1)=0 H1:βa,(2)-βa (1)≠0 由表3,得SE ,SE(βa,(2)-βa,(1))=√(0.0403)2+(0.0365)2=0.054 t=(0.605-0.585)/0.054=0.37<1.96 所以不拒绝原假设,即在5%显著水平下age 对ahe 的效应估计没有显著差异,所以(1)中的回归没有遭遇遗漏变量偏差。 (4) B ob’s predicted ahe=0.585×26-3.664×0+8.083×0-0.636=$14.574 Alexis ’s predicted ahe=0.585×30-3.664×1+8.083×1-0.636=$21.333 VARIABLES ahe age 0.585*** (0.514 - 0.657) female -3.664*** (-4.071 - -3.257) bachelor 8.083*** (7.666 - 8.500) Constant -0.636 (-2.759 - 1.487) Observations 7,711 R-squared 0.200

斯托克、沃森着《计量经济学》第九章

Chapter 9. Assessing Studies Based on Multiple Regression 9.1 Internal and External Validity Multiple regression has some key virtues: ?It provides an estimate of the effect on Y of arbitrary changes ΔX. ?It resolves the problem of omitted variable bias, if an omitted variable can be measured and included. ?It can handle nonlinear relations (effects that vary with the X’s)

Still, OLS might yield a biased estimator of the true causal effect. A Framework for Assessing Statistical Studies Internal and External Validity ?Internal validity: The statistical inferences about causal effects are valid for the population being studied.

?External validity: The statistical inferences can be generalized from the population and setting studied to other populations and settings, where the “setting” refers to the legal, policy, and physical environment and related salient features.

斯托克计量经济学课后习题实证答案

P ART T WO Solutions to Empirical Exercises

Chapter 3 Review of Statistics Solutions to Empirical Exercises 1. (a) Average Hourly Earnings, Nominal $’s Mean SE(Mean) 95% Confidence Interval AHE199211.63 0.064 11.50 11.75 AHE200416.77 0.098 16.58 16.96 Difference SE(Difference) 95% Confidence Interval AHE2004 AHE1992 5.14 0.117 4.91 5.37 (b) Average Hourly Earnings, Real $2004 Mean SE(Mean) 95% Confidence Interval AHE199215.66 0.086 15.49 15.82 AHE200416.77 0.098 16.58 16.96 Difference SE(Difference) 95% Confidence Interval AHE2004 AHE1992 1.11 0.130 0.85 1.37 (c) The results from part (b) adjust for changes in purchasing power. These results should be used. (d) Average Hourly Earnings in 2004 Mean SE(Mean) 95% Confidence Interval High School13.81 0.102 13.61 14.01 College20.31 0.158 20.00 20.62 Difference SE(Difference) 95% Confidence Interval College High School 6.50 0.188 6.13 6.87

斯托克,沃森计量经济学第四章实证练习stata操作及答案

E4.1 E4.2 E4.3 E4.4

E4.1 VARIABLES ahe age 0.605 (0.0245) Constant 1.082 (0.688) Observations 7,711 R-squared 0.029 Robust standard errors in parentheses *** p<0.01, ** p<0.05, * p<0.1 1. ① 截距估计值estimated intercept: 1.082 ② 斜率估计值estimated slope: 0.605 回归方程:ahe= 1.082+0.605*age ③ 当工人年长 1 岁,平均每小时工资增加0.605 美元。 2. Bob: 0.605*26+1.082=16.812 (美元) Alexis: 0.605*30+1.082=19.232 (美元) 答:预测Bob 的收入为每小时16.812美元,Alexis为19.232 美元。 3. 年龄不能解释不同个体收入变化的大部分。因为R-squared 反映了因变量的 全部变化能通过回归关系被自变量充分解释的比例,而分析得R-squared 的值为0.029,解释度低,说明年龄不能解释不同个体收入变化的大部分

E4.1 (0.0449) Observations 463 R-squared 0.036 Robust standard errors in parentheses *** p<0.01, ** p<0.05, * p<0.1 ① 截距估计值: 3.998 斜率估计值: 0.133 回归方程: Course_Eval=3.998+0.133*beauty lave_esruo 0a u ty a e 1. 答:两者看上去有微弱的正相关关系 2. VARIABLES course eval beauty Constant 0.133 (0.0550) 3.998

斯托克、沃森着《计量经济学》第六章

Chapter 6. Linear Regression with Multiple Regressors 6.1 Omitted Variable Bias(遗漏变量偏差) OLS estimate of the Test Score/STR relation: n TestScore= 698.9 – 2.28×STR, R2 = .05, SER = 18.6 (10.4) (0.52) Is this a credible estimate of the causal effect on test scores of a change in the student-teacher ratio? 1

No: there are omitted confounding factors (family income; whether the students are native English speakers) that bias the OLS estimator: STR could be “picking up” the effect of these confounding factors. 2

Omitted Variable Bias The bias in the OLS estimator that occurs as a result of an omitted factor is called omitted variable bias. For omitted variable bias to occur, the omitted factor “Z” must be: 1.a determinant of Y; and 2.correlated with the regressor X. 3

斯托克、沃森着《计量经济学》第八章

Chapter 8. Nonlinear Regression Functions 8.1 A General Strategy for Modeling Nonlinear Regression Functions ?Everything so far has been linear in the X’s ?The approximation that the regression function is linear might be good for some variables, but not for others.

?The multiple regression framework can be extended to handle regression functions that are nonlinear in one or more X.

The TestScore – STR relation looks approximately linear…

But the TestScore – average district income relation looks like it is nonlinear.

If a relation between Y and X is nonlinear: ?The effect on Y of a change in X depends on the value of X – that is, the marginal effect of X is not constant ?A linear regression is mis-specified – the functional form is wrong ?The estimator of the effect on Y of X is biased – it needn’t even be right on average. 遗漏高次项会带来遗漏变量偏 差。例如: () 2 012 Y X X u βββ =+++,显然X与2 X相关。

计量经济学教材推荐

各类计量经济学教材评析与推荐: 【计量经济学的内容体系】 古扎拉蒂《计量经济学基础》 白砂堤津耶《通过例题学习计量经济学》 伍德里奇《计量经济学导论:现代观点》 斯托克、沃森《计量经济学导论》 威廉·格林《计量经济分析》 林文夫(Fumio Hayashi)《计量经济学》 雨宫健(Takeshi Amemiya )《高级计量经济学》 李子奈、潘文卿编著《计量经济学》 【计量经济学的内容体系】 狭义的计量经济学以揭示经济现象中的因果关系为目的,主要应用回归分析方法。广义的计量经济学是利用经济理论、统计学和数学定量研究经济现象的经济计量方法,除了回归分析方法,还包括投入产出分析法、时间序列分析方法等。 把计量经济学分为初级、中级、高级三个层次,初级计量经济学一般包括计量经济学所必须的基础数理统计只是和矩阵代数只是、经典的线性计量经济学模型理论与方法(以单一方程模型为主)、单方程模型的应用等内容;中级计量经济学以经典的线性计量经济学模型理论与方

法及其应用为主要内容,包括单一方程模型和联立方程模型。在应用方面,主要讨论计量经济 学模型在生产、需求、消费、投资、货币需求和宏观经济系统等传统领域的应用,注重于应用过程中实际问题的处理。在描述方法上普遍运用矩阵描述;高级计量经济学以扩展的线性模型理论与方法、非线性模型理论与方法和动态模型理论与方法,以及它们的应用为主要内容。 从研究对象和侧重点的角度讲,理论计量经济学侧重于理论与方法的数学证明与推导,与 数理统计联系极为密切;应用计量经济学则以建立与应用计量经济学模型为主要内容,强调应用模型的经济学和统计学基础,侧重于建立与应用模型过程中实际问题的处理。 纵观计量经济学发展史,20世纪70年代之前发展并广泛应用的计量经济学称为经典计量经济学,其理论特征是:以经济理论为导向建立因果分析的随机模型,模型具有明确的形式和参数,模型变量之间的关系多表现为线性关系,或者可以化为线性关系,以时间序列数据或者截面数据为样本,采用最小二乘方法或者极大似然方法估计模型。其应用方面的特征是:在生产、消费、投资以及宏观经济等传统的应用领域进行结构分析、政策评价、经济预测和理论检验。20世纪70年代之后发展的计量经济学理论、方法及应用模型称为现代计量经济学,主要包括微观计 量经济学、非参数计量经济学、时间序列计量经济学和动态计量经济学等。 古扎拉蒂《计量经济学基础》 【作者简介】达摩达尔·N·古扎拉蒂于1960年获孟买大学工商学硕士学位,1963年获芝加哥大学工商行政硕士学位,并于1965年获芝加哥大学博士学位。在执教于纽约市立大学28年多之后,现在是纽约州西卢美国军事学院社会科学系的经济学教授。古扎拉蒂博士现任多种期刊和

詹姆斯·斯托克,马克·沃森计量经济学第三章实证练习stata答案

一、 Two-sample t test with equal variances Group Obs Mean Std.Err. Std.Dev. 95% Conf. Interval 1992 7,612 11.62 0.0644 5.619 11.49 11.74 2012 7,440 19.80 0.124 10.69 19.56 20.04 combined 15,052 15.66 0.0770 9.442 15.51 15.81 diff -8,183 0.139 -8.455 -7.911 diff = mean(1992) - mean(2012) t = -58.9871 Ho: diff = 0 degrees of freedom = 15050 Ha: diff < 0 Ha: diff != 0 Ha: diff > 0 Pr(T < t) = 0.0000 Pr(|T| > |t|) = 0.0000 Pr(T > t) = 1.0000 二、 Two-sample t test with equal variances Group Obs Mean Std.Err. Std.Dev. 95% Conf. Interval 1992 7,612 15.64 0.0867 7.564 15.47 15.81 2012 7,440 19.80 0.124 10.69 19.56 20.04 combined 15,052 17.69 0.0772 9.471 17.54 17.85 diff -4.164 0.151 -4.459 -3.869 diff = mean(1992) - mean(2012) t = -27.6423 Ho: diff = 0 degrees of freedom = 15050 Ha: diff < 0 Ha: diff != 0 Ha: diff > 0 Pr(T < t) = 0.0000 Pr(|T| > |t|) = 0.0000 Pr(T > t) = 1.0000

斯托克、沃森着《计量经济学》第五章

Chapter 5. Regression with a Single Regressor: Hypothesis Tests and Confidence Intervals 5.1 Testing Hypotheses about One of the Regression Coefficients(对单一系数的假设检验) Suppose a skeptic suggests that reducing the number of students in a class has no effect on learning or, specifically, test scores. The skeptic thus asserts the hypothesis, 1

H0: β1 = 0 We wish to test this hypothesis using data – reach a tentative conclusion whether it is correct or incorrect. Null hypothesis and two-sided alternative: H0: β1 = 0 vs. H1: β1≠ 0 or, more generally, 2

H0: β1 = β1,0 vs. H1: β1≠β1,0 where β1,0 is the hypothesized value under the null(β1,0是一个具体的数). Null hypothesis and one-sided alternative: H0: β1 = β1,0 vs. H1: β1 < β1,0 In economics, it is almost always possible to come up with stories in which an effect could “go either way,” so it is 3

斯托克,沃森计量经济学第四章实证练习stata操作及答案

E4.1 E4.2 E4.3 E4.4

VARIABLES ahe age 0.605 (0.0245) Constant 1.082 (0.688) Observations 7,711 R-squared 0.029 Robust standard errors in parentheses *** p<0.01, ** p<0.05, * p<0.1 1.①截距估计值estimated intercept:1.082 ②斜率估计值estimated slope:0.605 回归方程:ahe= 1.082+0.605*age ③当工人年长1岁,平均每小时工资增加0.605美元。 2.Bob: 0.605*26+1.082=16.812(美元) Alexis: 0.605*30+1.082=19.232(美元) 答:预测Bob的收入为每小时16.812美元,Alexis为19.232美元。 3.年龄不能解释不同个体收入变化的大部分。因为R-squared反映了因变量的 全部变化能通过回归关系被自变量充分解释的比例,而分析得R-squared的值为0.029,解释度低,说明年龄不能解释不同个体收入变化的大部分。

1. 答:两者看上去有微弱的正相关关系 2. VARIABLES course_eval beauty 0.133 (0.0550) Constant 3.998 (0.0449) Observations 463 R-squared 0.036 Robust standard errors in parentheses *** p<0.01, ** p<0.05, * p<0.1 ①截距估计值:3.998 斜率估计值:0.133 回归方程:Course_Eval=3.998+0.133*beauty

斯托克计量经济学第十章第十一章实证练习stata

∕?E10.1?∕ USe w C:?Us?ε≡?asus?D^9?top?Guns.dta w set BlOXe OrC Xwet scateid yrar ∕a HP/ GCn InViC e ln(ViO) reg InViO ShaIl r X eat a tore CII reg InViO Shail incarc rate density avginc POP pblO64 PMlO^4 FnlO2$ λ X C3t >torc n2 /?(2>*/ ×τx?q InVIO shall InCarC e raτe αe∏8ity avgιnc FOP 匸Q1064 PV丄034 FlIUJ20. r? ι (scaτ?i3) eσt StOre ∏3 ∕?(3M∕ xτxeσ InVXo □?all incarcerate dcn□ιty arcme rop rb丄064 rv!061 匸nu」29, tc ι(Vear) est StOre ?4 κcxeg InVlo shall incarcerate density avcxnc FOP FbIO64 E乜丄064 FlrL B J29 ι.yea∑ 工?ataceιd r Ie VCe(XObUSO eat 3tore m3 catcab XInUn3 Di4i 比5 U0ing IIVIPaaI9iC3t?zzι,JC∑2 a∑2(?> /*(4>*/ gen InXCt=In(XCO) reσ InXCt shall, Z est store al reσ InXCt SnalI incarcerate avαιno PCr Dr丄064 pxl064 r<ιl029, X est store a2 XCXeg Inrob □nall InCarC e raZe αcnaιty avgιnc FOP pi>lD64 丄064 FBUJ29. re ι(0CaZeIaI eat atore a3 ×τx?g InrOb SnalI InCarC e raτe α?naιty avgιnc FOP pi>1064 PVIOe4 FBU^29 f r? ι(y?ar) eat 3tore d£ ×LX?9 InXOb Shall InCarC xaZe ClenslLy avginc POP fI>1064 PVlO€4 PMLL929 丄?year !.?SLazeld r Xe VCe(XQbUSCl e□t StOre aS estcab al ?2 a3 a4 aS USlng soaad.rtf Se r2 ar214> gen InnUr^丄二(EIUr) reg InnUC 9hall, r t>t ?tor? DX reg InnUr shall incarc rate density avginc pop DbIo64 PXIO6? ral029 # T 37?>t sror? b2 38xτrcg InirUr 3bdll incarc - raτe density avjinc POP rιbl064 pwl0€4 rml029, fe i (ata^cid) 39?β‰ 8LOX? b3 40xτrcσ 丄ΠXUH ShaIL InCaXC e xcτc αcnsιt5* avjιnc POP rb-061 PW(1064 Zm-O29#fc ι (year) 41esr a^ore b4 42xτxeg .nxux shall InCaXC_xaτe αensιty avgιnc POP Fb-O64 PW丄064 PlrUo29 工?year 工?staτexd r f e VCe (XCbXIsx? 43est StOre b5 44?fttaD bl b2 Q3 D4 匕5 UBXng sorrow?rcr?■冷∑2a∑2(4) 铝∕?E10.2t∕ 4€us? n CAuSVXsXasusXC^skcopVSeacBelus.ατα? 47 ×zscz firs year 45/<(1)*/ 49gen In^n□oas=-n(xnocine) 50reg fatalityrate sperd65 5peed*0 be08 drinkβgc IninCOBr βoe, r 5丄*st ιror?CI 52/?(2)*/ 53×zxeg XazallLyxaze ?t> -u?vαg* βρ? est store c3 Se ∕? (5??/ 59 San vwτ €0∕?(?)?/ 61XCa nb β u□ecσe PXXriary 3econdary 0ceed6S opeed70 baO8 dr3∏teσc2丄丄mr:COaLC a?c, r 62esr S^Ore c4 €3 Xtreg Sb S Udeage PrIXaXy secondary GPCea65 apcεd70 ba J8 e∑xnkage2丄InXnCCiae age 丄.year 丄.±ιps r ±e VCe(robust! C4 est Store c5 CS ??ttΛD CI C2 C3 C4 CS UBLna cn??xupi?r = i■■芒r2 ?∑2 (?) 66/?E11.1*/ 67us? M CΛus*/ £9Suin IC sxtt>an≡=l 70t ZeSZ 9ΛZ ke∑ x± 3n3^er≡=?r by ιe≡Jccan)丄evel(9S> 71IogOUt r nd化(1) VOreI IePleCe: Ctest 3≡0ker if 3Λckrr-JΛ by (3t1kban) IeVel (95)

斯托克,沃森计量经济学第五章第六章实证练习stata操作及答案

E5.2 E5.3

E6.2 E6.3

(1) VARIABLES ahe age 0.605*** (1.40e-09) Constant 1.082 (0.150) Observations 7,711 R-squared 0.029 Robust pval in parentheses *** p<0.01, ** p<0.05, * p<0.1 Robust t-statistics in parentheses *** p<0.01, ** p<0.05, * p<0.1 a. 在对双边备择检验中,系数的t 统计量为24.70>2.58,与系数对应的p 值是0.0000000014 趋近于0<0.01,所以可以在1%显著水平下拒绝原假设,自然可以在5%、10%水平下拒绝 原假设。 (1) VARIABLES ahe age 0.605*** (0.550 - 0.660) Constant 1.082 (-0.473 - 2.638) Observations 7,711 R-squared 0.029 Robust ci in parentheses *** p<0.01, ** p<0.05, * p<0.1 b. 斜率系数95%的置信区间是(0.550,0.660) m1 VARIABLES ahe age 0.605*** (24.70) Constant 1.082 (1.574) Observations 7,711 R-squared 0.029 Ajusted R2 0.0289

(1) m2 VARIABLES ahe age 0.298*** (7.513) Constant 6.522*** (5.585) Observations 4,002 R-squared 0.012 Ajusted R2 0.0117 Robust t-statistics in parentheses Robust pval in parentheses *** p<0.01, ** p<0.05, * p<0.1 *** p<0.01, ** p<0.05, * p<0.1 只利用高中毕业生的数据,系数的t 统计量为7.513>2.58,与系数对应的p 值是0.0000364趋近于0<0.01,所以可以在1%显著水平下拒绝原假设,自然可以在5%、10%水平下拒绝原假设。 d. Robust pval in parentheses *** p<0.01, ** p<0.05, * p<0.1 Robust t-statistics in parentheses *** p<0.01, ** p<0.05, * p<0.1 只利用大学毕业生的数据,系数的t 统计量为21.67>2.58,与系数对应的p 值是0.00000000448趋近于0<0.01,所以可以在1%显著水平下拒绝原假设,自然可以在5%、10%水平下拒绝原假设。 (1) VARIABLES ahe age 0.298*** (3.64e-05) Constant 6.522*** (0.000341) Observations 4,002 R-squared 0.012 (1) m3 VARIABLES ahe age 0.925*** (21.67) Constant -4.439*** (-3.383) Observations 3,709 R-squared 0.059 Ajusted R2 0.0589 (1) VARIABLES ahe age 0.925*** (4.48e-09) Constant -4.439*** (0.00808) Observations 3,709 R-squared 0.059

斯托克、沃森着《计量经济学》第二章

Chapter 2. Review of Probability 2.1 Random Variables and Probability Distributions 概率Probability: 在大量重复实验下,事件发生的频率趋向的某个稳定值。例如,记事件“下雨”为A,其发生的概率为P()A。

条件概率Conditional Probability : 例:已知明天会出太阳,下雨的概率有多大? 记事件“出太阳”为B 。则在出太阳的前提条件下降雨的“条件概率”(conditional probability )为, P() P()P()A B A B B ∩≡ 其中,“∩”表示事件的交集(intersection ),故P()A B ∩为“太阳雨”的概率,参见图2.1。条件概率是计量经济学的重要概念之一。

图2.1、条件概率示意图

独立事件Independence : 如果条件概率等于无条件概率,即P()P()A B A =,即B 是否发生不影响A 的发生,则称,A B 为相互独立的随机事件。此 时,P() P()P()P()A B A B A B ∩≡=,故 P()P()P()A B A B ∩= 也可以将此式作为独立事件的定义。

全概公式 如果事件组{}12,,,(2)n B B B n ≥ 两两互不相容, ()0(1,,) i P B i n >?= ,且12n B B B ∪∪∪ 为必然事件(即在 12,,,n B B B 中必然有某个i B 发生,“∪”表示事件的并集, union ),则对任何事件A 都有(无论A 与{}12,,,n B B B 是否有任何关系), 1P()P()P()n i i i A B A B ==∑ 全概公式把世界分成了n 个可能的情形,再把每种情况下的条件概率“加权平均”而汇总成无条件概率(权重

相关主题