TITLE OF COURSE : Introduction to Econometrics
CODE NUMBER OF COURSE : PS. 407
CREDIT : 3 Sks
SEMESTER :
BRIEF DESCRIPTION OF THE COURSE :
This course explains the basic principles of econometrics and expertise in estimating standard (general) econometrics models to present a variety of real problems. Topics covered include correlation analysis; regression analysis using Ordinary Least Square (OLS) estimation methods, Weighted Least Square (WLS), Indirect Least Square (ILS), and Two-Stage Least Square (2-SLS), Simple Regression, Multiple Regression, assumptions of Linear Regression Model Classic, Estimated Interval, Hypothesis Testing, Multicollinearity, Heteroscedasticity, Autocorrelation, forecasting, and Simultaneous Equations.
GENERAL LEARNING OBJECTIVES: After completing this course, students can understand and use regression models in research to represent a variety of real problems, as well as knowledge in the use of econometric software (Minitab / SPSS / Eviews).
No. Specific Learning Objectives Main Subject Subjects Estimated
Time
References
1. Students can understand and explain the understanding and methodology of econometric modeling, various patterns of relationships, and correlation analysis.
Introduction 1.1 What is Econometrics?
1.2 Why is Econometrics a separate discipline of science?
1.3 Several types of relationship patterns are examined in econometrics in predicting economic relations.
3 x 50 minute PR: Chapter 1 R : Chapter 1
1.4 Correlation Analysis: understanding and testing.
1.5 Criteria for causal relations: Consistency, Mechanistic.
1.6 Econometric Modeling Methodology:
specification, estimation, and verification of the model.
1.7 The role of computer equipment 1.8 Questions for Exercise
2. Students can understand and explain the analysis of simple linear regression models:
interpretation and estimation of the model coefficients by the OLS method, testing hypotheses related to the coefficients, and assumptions of the linear regression model.
Linear Regression Model Analysis:
simple (Simple Linear Regression Model Analysis)
2.1 Definition of the Model and Modeling Objectives
2.2 Analysis of the Simple Linear Regression Model
2.3 Interpretation of the Model Coefficient 2.4 Regression vs. Causal: Use of Non-Free
Variable (response, effect) and Free Variable (explanatory, cause).
2.5 Estimation Method (number) Squares (remaining) Least – OLS
2.6. Population vs. Example Regression Model 2.7 Assumptions of the Classical Linear
Regression Model
2.8 Nature of the OLS Estimator
2.9 Statistical Review of Inference: Normal Distribution, Confidence Interval, p-Value and Real Level of Testing (α)
3 x 50 minute PR: Chapter 2, 3 R : Chapter 2, 3
2.10 Hypothesis Testing: Model Coefficient Test 2.11 Some Examples of Regression Coefficient
Hypotheses and Their Testing
2.12 Analysis of Variations in Regression Models and Coefficient of Determination (R2)
2.13 Estimation of Variance (error)
2.14 Interval of Confidence and Testing the Model Coefficient Hypothesis
2.15 T-Test and F-Test 2.16 Residual Analysis
2.17 Forecasting or Estimating for Y 2.18 Questions for Exercise
3. Students can understand and explain the analysis of multiple linear regression models with two or more independent variables: interpretation and estimation of the model
coefficients by the OLS method, hypothesis testing.
Analysis of Multiple
Regression Model (Multiple
Regression Model Analysis)
3.1 Analysis of the Multiple Linear Regression Model (with 2 independent variables) 3.2 Interpretation of the Model Coefficient 3.3 The Model Coefficient Formula is based on
the OLS Method
3.4 Assumptions of the Classical Linear Regression Model
3.5 Distribution of Regression Model Coefficient Opportunities
3.6 Analysis of the Variance of Regression Models, Determination Coefficients, and Estimating Variance Remaining.
3.7 Overall Model Test (F-Test) and Partial
3 x 50 minute PR: Chapter 4 R : Chapter 6
Coefficient Test (T-Test)
3.8 Interpretation of Outputs from Analysis Results
3.9 Some Examples of Regression Coefficient Hypotheses and Their Testing, and Intervals of Trust
3.10 Goodness of Fit
3.11 Modeling for forecasting
3.12 Analysis of the Multiple Common Linear Regression Model (more than 2 independent variables)
3.13 Use of Matrix Notation in Regression Models
3.14 Selection of the Best Model (Main and Auxiliary Hypotheses Testing)
3.15 Partial Correlation and Stepwise Regression 3.16 R2 and R2 Corrected
3.17 Standard Coefficients and Elasticity 3.18 Presenting the Analysis Results of the
Regression Model in Scientific Writing 3.19 Questions for Exercise
1st Competency Examination (CE-1) 4. Students can develop various
forms of functions of linear regression models to represent various realities of economic
Variations of the Multiple Variable Regression Model
4.1 Function Forms of Regression Models 4.2 Modeling of Information on Marginal Effects
and Elasticity
3 x 50 minute PR: Chapter 5 R : Chapter 6
problems 4.3 Regression Model through the Origin Point 4.4 Log-linear model
4.5 Semilog Models 4.6 Reciprocal Models
4.7 Polynomial Regression Model 4.8 Pseudo nonlinearity
4.9 Tests that involve more than one parameter coefficient
5.0 Questions for Exercise 5. Students can construct models
with qualitative free variables (nominal or ordinal scale)
Regression Model with Qualitative Free Variable (Dummy)
5.1 Measurement Scale
5.2 Models with Qualified Free Variants with 2 Categories (Without Interacting with Other Free Variables)
5.3 Regression Model with Qualitative Free Variable with 2 Categories (Which Interact with Other Free Variables)
5.4 Interaction Model between dummy variables and other free variables
5.5 Merging of Cross-Section Data and Time Series (Panel Data)
5.6 Piecewise Linear Regression Model 5.7 Questions for Exercise
3 x 50 minute PR: Chapter 5 R : Chapter 7
6. Students can understand the problem of multicollinearity, explain the consequences, detect and overcome them in the regression equation model
Multiple Colliearity (multicollinearity)
6.1 Violation of the Classical Assumptions of the Linear Regression Model: Perfect Linear Relations between Variables Free
6.2 Linear Relationship between Variable Free (multicollinearity) and its Consequences
3 x 50 minute PR: Chapter 4 R : Chapter 5
6.3 Estimating OLS in the Perfect State of Collinearity
6.4 Estimating OLS in a State of High but Not Perfect Collinearity
6.5 Ways to Detect Multicollinearity 6.6 Ways to Overcome Double Colinearity
(Multicollinearity) 6.7 Questions for Exercise 2nd Competency Examination (CE-2) 7. Students can understand the
problem of Heteroscedasticity, explain the consequences, detect, and overcome them in the regression equation model.
Heteroskedasticity 7.1 The nature of heteroscedasticity
7.2 Estimation of OLS in the Occurrence of Heteroscedasticity
7.3 As a result of using OLS in a state of heteroscedasticity
7.4 Detecting heteroscedasticity: Goldfeld-Quandt Test, Breusch-Pagan Test, White Test.
7.5 Overcoming heteroscedasticity
7.6 Weighted Least Square (WLS) method, the difference between OLS and WLS.
7.7 Questions for Exercise
3 x 50 minute PR : Chapter 6 R : Chapter 8
8. Students can understand the autocorrelation problem, explain its consequences, detect and overcome it in the regression equation model.
Autocorrelation 8.1 The nature of autocorrelation
8.2 Estimation of OLS in the presence of Autocorrelation
8.3 Effects of using OLS in the presence of Autocorrelation
3 x 50 minute PR : Chapter 6 R : Chapter 9
8.4 Detecting Autocorrelation 8.5 Overcoming Autocorrelation 8.6 Questions for Exercise 9. Students can understand the
approach of the GLS
(Generalized Least Squares) method, explain the procedure of the GLS method, explain the WLS (Weighted Least Squares) method as a special form, Understand the maximum likelihood estimation approach, the maximum likelihood estimation method.
Alternative Estimation Methods
9.1 GLS (Generalized Least Squares) Method for Heteroscedasticity and Autocorrelation Problems:
9.1.1 Consequences for OLS Estimators 9.1.2 Declining Alternative Estimators with GLS
9.1.3 Example of the GLS Method for the Heteroscedasticity Problem
9.2 Estimating the Maximum Possible Methods 9.3 Method of Estimating Instrumental Variables 9.4 Model Specifications and Econometric
Modeling Stages 9.5 Questions for Exercise
3 x 50 minute
3rd Competency Examination (CE-3) 10. Students can understand and
construct models with qualitative response variables (nominal or ordinal scale)
Qualitative Choice Model
10.1 Qualitative Choice Models 10.2 Linear Opportunity Models 10.3 Probit Models
10.4 Logit Model: Estimating and Testing Parameters
10.5 Interpretation of the Logit Model Coefficient 10.6 Examples of Logit Model Applications 10.7 Questions for Exercise
3 x 50 minute PR : Chapter 5 R : Chapter 7
11. Students can understand and explain the need for time (lag) on the emergence of a response due to action and represent it in a model, and develop a model to represent expectations.
Time Difference Model (Distributed Lags Model)
11.1 Distributed Lags Model
11.2 Estimating the Model of Time Difference with the Ad-Hoc Approach
11.3 Estimating the Geometrical Lags Model with the Koyck Approach
11.3.1 Adaptive Expectation Model 11.3.2 Stock Adjustment Model
11.4 Estimating the Lag Geometric Model with Self Regression Model (Autoregressive) 11.5 Causality Test
11.6 Questions for Exercise
3 x 50 minute PR : Chapter 9 R : Chapter 10
12. Students can understand, explain, and develop
simultaneous equation models to represent the interdependence relationships between variables.
Simultaneous Equation Model
12.1 Simultaneous Equation Models 12.2 Identification Problems
12.3 Consumption of Consistent Parameters:
Instrument and Indirect Variables (ILS) 12.4 Estimation of Over-Identified Models: Two-
Stage Least Square Method
12.5 Methods of Estimating Equation Systems;
SUR and 3 SLS
12.6 Examples of Applications of Simultaneous Equation Models
12.7 Comparison of Alternative Estimation Methods
12.8 Questions for Exercise
3 x 50 minute PR : Chapter 11 R : Chapter 13
4th Competency Examination (CE-4)
