Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Lecture One Methodology of Econometrics. 2 立论?结论?  立论 : 要求给出求论的路径。  结论 : 要求说明结论的来源。  自以为是的东西并不见得是真  我们不是上帝!

Similar presentations


Presentation on theme: "1 Lecture One Methodology of Econometrics. 2 立论?结论?  立论 : 要求给出求论的路径。  结论 : 要求说明结论的来源。  自以为是的东西并不见得是真  我们不是上帝!"— Presentation transcript:

1 1 Lecture One Methodology of Econometrics

2 2 立论?结论?  立论 : 要求给出求论的路径。  结论 : 要求说明结论的来源。  自以为是的东西并不见得是真  我们不是上帝!

3 3 我们的习惯是这样的吗?  结论来自感觉(象上帝)  宏观思考(象战略家)  习惯地提出政策建议(象顾问)  得争取把一个个的大、小问题搞明白再 说吧!

4 4 Mainstream Analysis Approaches Normative Analysis Positive Analysis (empirical analysis)

5 5 The Writer D.N.Gujarati  Professor of econometrics at the Military Academy at West Point  Master of Commerce  MBA  Editorial referee  Author  Visiting Professor

6 6 What is Econometrics  Empirical support to the models  Quantitative analysis of actual economic phenomena  Social science in which the tools of economic theory, mathematics, and statistical inference are applied to the analysis.  Positive help  Economic theory _____ measurements

7 7 Methodology of Econometrics  Statement of theory or hypothesis  Obtaining the data  Specification of the mathematical model  Specification of the econometric model  Estimation of the parameters of the econometric model  Hypothesis testing  Forecasting or prediction  Using the model for control or policy purposes

8 8 Statement of Theory or Hypothesis  Postulate ( give some examples )  Statement  Note: hypothesis is not the same as an assumption

9 9 Obtaining the Data  Nature  Sources  Limitations

10 10 Types of Data Time series data: quantitative,qualitative (dummy variable) (SATIONARY) Cross-sectional data: (HETEROGENEITY) Pooled data: (Panel data)

11 11 Sources  www.whitehouse.gov/fsbr/esbr.htm www.whitehouse.gov/fsbr/esbr.htm  www.nber.org www.nber.org (National bureau of economic research)  www.census.gov www.census.gov  Stats.bls.gov  www.jstor.gov www.jstor.gov

12 12 Accuracy of Data  Non-experimental in nature  Round-offs and approximations  Non-response  Selectivity bias  Aggregate level  Confidentiality  The results of research are only as good the quality of the data.

13 13 Specification of the mathematical model  Yi=b1+b2*Xi 0<b2<1  Yi consumption expenditure  Xi income  Parameters b1 b2, b1 intercept,b2 slope  Consumption function  Single equation model  Multiple equation model

14 14 Terminology Yi  Dependent variable  Explained variable  Predictand  Regressand  Response  Endogeous  Target variable Xi  Independent variable  Explanatory variable  Predictor  Regressor  Stimulus variable  Exogenous variable  Control variable

15 15 Specification of the econometric model Yi=b1+b2*Xi + u i  Ui disturbance, error term, random (stochastic variable)  Econometric model  Linear regression model

16 16 Significance of Disturbance: ui  Surrogate for all omitted variables  Vagueness of theory  Unavailability of data  Core variables VS. peripheral variables  Intrinsic randomness in human behavior  Poor proxy variables  Principle of parsimony  Wrong functional form

17 17 Linear Relationship  Linearity in the variables E(y|xi)=b1+b2*xi*xi  Linearity in the parameters E(y|xi)= b1+root(b2)*xi*xi LRM : linear regression model NLRM: non-linear regression model

18 18 Regression Relationships  Regression analysis is concerned with the study of the dependence of Yi with one or more Xi. Xi is known or fixed, predicting the mean of Yi of total.  Statistical vs. deterministic relationships  Regression vs. causation  Regression vs. correlation

19 19 Estimation of the econometric model  Numerical estimates of the parameters  Regression analysis is the main tool used to obtain the estimates  The hat on Y indicates that it is an estimate

20 20 Hypothesis Testing  Sample->sample parameter->estimate- >estimator distribution->population parameter->population characteristics  Confirmation or refutation of economic theories on the basis of sample evidence  The basement is statistical inference (Hypothesis testing)

21 21 Forecasting or Prediction  Hypothesis or theory be confirmed  Known or predictor variable X  Predict the future values of the dependent

22 22 Use of the Model for Control or Policy Purposes  Control variable X  Target variable Y  Yi=b1+b2*Xi  Manipulate the control variable X to produce the desired level of the target variable Y

23 23 Anatomy of Classical Econometric Modeling  Economic theory  Mathematical model of theory  Econometric model of theory  Data  Estimation of econometric model  Hypothesis testing  Forecasting or prediction  Using the model for control or policy purposes

24 24 第1章第1章计量经济学研究的方法论 4 第 2-3 章基本统计概念,概率分布 4 第4章第4章估计与假设 4 第5章第5章双变量模型的基本思想 4 第6章第6章双变量模型的假设检验 4 第7章第7章多元回归:估计与假设检验 4 第8章第8章回归方程的函数形式 4 第9章第9章虚拟变量的回归模型 4 第 10 章多重共线性 4 第 11 章异方差性 4 第 12 章自相关性 4 第 13 章模型选择:标准与检验 4 实验实验 1-6 6

25 25 Please Give Some Suggestions Z3-W@163.COM 027-62082852 Thank you.


Download ppt "1 Lecture One Methodology of Econometrics. 2 立论?结论?  立论 : 要求给出求论的路径。  结论 : 要求说明结论的来源。  自以为是的东西并不见得是真  我们不是上帝!"

Similar presentations


Ads by Google