Big-data science is recently developed in quantity, of course, but also expanding to the time-series direction and to spatial dimensions. This multi-dimensionalization can be treated efficiently with tools of matrix algebra and matrix differentiation. In this lecture, we first study these matrix tools, and then, choosing spatial econometrics among fields towards which economics and econometrics are challenging, we study frontier techniques and knowledge in the field.
First of all, by studying matrix algebra and matrix differentiation in statistics and econometrics, we acquire maneuvering technique to handle spatial data. Then, we study various models and methods for count data analysis to handle spatial interaction dta such as international trade and inter-regional migration. Finally we study spatial autocorrelation models and their applications to spatial data and spatial interaction data.
Matrix Algebra, Matrix Differentiation, Spatial Datam Count Data, Gravity Model, International Trade, Inter-regional Migration, Spatial Interaction Data, Spatial Autocorrelation Model
|Intercultural skills||Communication skills||Specialist skills||Critical thinking skills||Practical and/or problem-solving skills|
Scheduled contents are then lectured with reference documents handed out. Exercises and quizes are given as homeworks Answers to these homeworks are explained in the following class.
|Course schedule||Required learning|
|Class 2||Matrix Algebra and Matrix Differentials||Exercises of Matrix Differentials(1)|
|Class 3||Count data analysis: Regression with Single-variate discrete distribution (Binomial and Poisson distribution)||Exercises of Matrix Differentials(2)|
|Class 4||Count data analysis: Expansion of Regression with Single-variate discrete distribution||Related Exercises (1)|
|Class 5||Count data analysis: Regression with Multivariate discrete distributions|
|Class 6||Count data analysis: Model Identification||Related Exercises (2)|
|Class 7||Spatial Interaction Data analysis: Trade and Migration|
|Class 8||Spatial Interaction Data analysis: Structure and Characteristics of Spatial Intraction Models||Related Exercises (3)|
|Class 9||Spatial Interaction Data analysis: Application of Linear Regression|
|Class 10||Spatial Interaction Data analysis: Application of Single-variate Discrete Distribution||Related Exercises (4)|
|Class 11||Spatial Interaction Data analysis: Application of Multivariate Discrete Distribution|
|Class 12||Spatial Interaction Data analysis: Model Identification||Related Exercises (5)|
|Class 13||Spatial Econometrics: Spatial Autocorrelation Model|
|Class 14||Spatial Econometrics: Spatial Autoregression Model||Related Exercises (6)|
|Class 15||Application of Spatial Econometric Models to Spatial Interaction Analysis|
No particular textbook
Documents are distributed when necessary。
Giuseppe Arbia(2014), A Primer for Spatial Econometrics, with Applications in R. Palgrave MacMillan.
70% by Short tests and homeworks, and 30% by Final Report
IEE.B207 ： Econometrics I IEE.B301 ： Econometrics II IEE.B336 ： Applied Econometrics IEE.B405 ： Advanced Econometrics
Graduate students must have acquired units of IEE.B405