ECON 3102 - Econometrıc Analysıs II

Basic Information

Course Code:

ECON 3102

Course Name:

Econometrıc Analysıs II

Language of Instruction:

English

Course Type:

Class

Course Level:

Bachelor

ECTS:

5.00

Instructor:

Prof. Dr. NİLÜFER KAHRAMAN

Course Objectives

The aim of this course is to enable students to understand advanced econometric methods and apply appropriate econometric models to economic data using R/RStudio. The course covers model specification, heteroskedasticity, time-series regressions, serial correlation, stationarity and persistence, dynamic models, endogeneity, instrumental variables, two-stage least squares, and limited dependent variable models. Students are expected to estimate econometric models, test model assumptions, apply appropriate corrective methods, and interpret empirical findings from an economic perspective.

Course Content

Review of econometric modelling and multiple regression; model specification and functional form; heteroskedasticity and robust standard errors; characteristics of time-series data; static and dynamic time-series regressions; trends and seasonality; lagged variables and distributed lag models; stationarity, persistence, and first differences; detection and correction of serial correlation; HAC and serial-correlation-robust standard errors; endogeneity; instrumental variables estimation; two-stage least squares (2SLS); validity of instruments and exogeneity tests; introduction to simultaneous equation models; binary dependent variable models, the linear probability model, logit and probit; estimation of econometric models, diagnostic testing, and interpretation of results using R/RStudio.

Prerequisites / Corequisites

There is no formal prerequisite. However, students are expected to have basic knowledge of statistics, regression analysis, and econometrics and to be familiar with multiple linear regression, hypothesis testing, and basic R/RStudio applications.

Course Books / Materials / Recommended Resources

Heiss, F. (2020). Using R for Introductory Econometrics (2nd ed.). Independently Published.

Learning Outcomes

Code	Description
LO1	Ability to specify and estimate time-series regression models using R/RStudio and interpret the resulting econometric findings.
LO2	Ability to identify econometric problems such as heteroskedasticity and serial correlation using diagnostic tests and apply appropriate robust standard errors or corrective methods.
LO3	Ability to evaluate trend, seasonality, persistence, and stationarity issues in time-series data and apply lagged-variable and first-difference models.
LO4	Ability to explain endogeneity, apply instrumental variables and two-stage least squares methods, and evaluate the validity of instruments.
LO5	Ability to estimate binary dependent variable models, interpret model results and marginal effects, and compare alternative econometric models.

Weekly Course Content

Week	Content
1	Introduction to Econometric Analysis II; review of multiple linear regression and econometric model estimation using R/RStudio
2	Model specification, functional form, model selection, and evaluation of specification errors using R
3	Heteroskedasticity; detection methods, the Breusch-Pagan test, and heteroskedasticity-robust standard errors
4	Introduction to time-series data; the time dimension, lags, organization of time-series data, and time-series data structures in R
5	Static time-series regression models; trends, seasonality, and seasonal dummy variables
6	Dynamic regression models; lagged explanatory variables and finite distributed lag models
7	High persistence, stationarity, first differences, and econometric inference in time-series regressions
8	Midterm
9	Serial correlation in time-series regressions; tests for serial correlation, FGLS, and HAC robust standard errors
10	The endogeneity problem; omitted variables, simultaneity, measurement error, and the logic of instrumental variables
11	Instrumental variables estimation; relevance and exogeneity conditions, IV estimation in R, and interpretation of results
12	Two-stage least squares (2SLS); multiple instruments, weak instruments, and tests of exogeneity
13	Introduction to simultaneous equation models; structural and reduced forms, identification, and econometric estimation
14	Binary dependent variable models; the linear probability model, logit and probit models, and marginal effects
15	Integrated econometric application using R/RStudio; model estimation, diagnostic testing, comparison of alternative models, and interpretation of empirical findings

Workload Calculation

Activity	Count	Duration (Hours)	Total
Attendance	15	3.00	45.00
Pre-Class Individual Study	15	4.00	60.00
Post-Prectice Individual Study	1	30.00	30.00
Midterm Exam/Preparation	1	15.00	15.00
Total Workload (Hours)			150
ECTS Credit (Workload / 25)			5

Assessment

#	Assessment Type	Contribution (%)
1	Midterm Exam	%40
2	Final Exam	%60
TOTAL		%100

PO - LO Matrix

PO \ LO	LO1	LO2	LO3	LO4	LO5
PO-1
PO-2
PO-3
PO-4
PO-5
PO-6
PO-7
PO-8
PO-9
PO-10
PO-11
PO-12

1

Low Contribution

2

Medium Contribution

3

High Contribution

Teaching and Learning Methods

#	Method Name	Description	Tools
1	Lecture (expository teaching), interactive discussion	Listening and taking notes.	Standard classroom technologies, multimedia tools (projector, computer, digital presentations)

Academic Integrity and Artificial Intelligence

Students are expected to comply with the principles of academic integrity in all examinations, coursework, and other academic activities. Information, data, tables, figures, code, and ideas obtained from external sources must be properly acknowledged. Plagiarism, manipulation of data or results, completing work on behalf of another student, and unauthorized collaboration are considered violations of academic integrity. Artificial intelligence tools may be used, when permitted by the course instructor, to clarify econometric concepts, assist with R coding, or explore alternative analytical methods. Students are responsible for verifying the accuracy of AI-generated code, econometric results, and interpretations. AI tools may not replace students' own econometric analysis, model selection, or economic interpretation.

Sustainable Development Goals