Featured Programs
Experiential Learning Opportunities
Claim up to $1,000 in flight credits!
Get up to $1,000 in flight credits or grants toward study or internship programs abroad when you apply by January 01, 2025. See our Official Rules for full details.
Quantitative Methods for Management
Engineering & Social Sciences Program
Madrid, Spain
Dates: 8/30/21 - 12/23/21
Quantitative Methods for Management
OVERVIEW
CEA CAPA Partner Institution: Universidad Carlos III de Madrid
Location: Madrid, Spain
Primary Subject Area: Management
Instruction in: English
Course Code: 14444
Transcript Source: Partner Institution
Course Details: Level 300
Recommended Semester Credits: 3
Contact Hours: 42
Prerequisites: All the previous courses in Statistics
DESCRIPTION
In this course, the fundamental concepts for being able to apply the regression to measure the relation between economic variables is taught. In particular, the following topics will be covered throughout the course.
1. Testing linear relationship between the variables contained in the model. These tests are of special interest to study whether the relation postulated by the economic theory is present in the actual data.
2. The use of dummy variables in order to introduce into the model the effect of quantitative explanatory variables or other effects that are difficult to measure.
3. Multicollinearity between the explanatory variable is a common problem in the econometric analysis. The standard techniques how to deal with this problems are covered.
4. The regression model in the presence of heteroskedasticity. It is common that the uncertainty about economic variables is not constant over time, which will be reflected in the empirical data. In these circumstances, the properties of the estimators change and it could be necessary to consider alternative estimation techniques to this problem into account.
5. Finally, the problem of endogeneity of variables is considered. In this case, the use of instrumental variables to obtain estimators with ¿nice¿ properties will be explained.
PROGRAMME
1. Inference in the multiple regression model
1.1 Basic concepts
1.2 Sampling distributions of the OLS estimators
1.3 Testing hypotheses about a single population parameter
1.4 Confidence intervals
1.5 Testing hypotheses about a single linear combination of parameters
1.6 Testing multiple linear restrictions: the F-test
2. Multiple regression with dummy variables
2.1 Describing qualitative information
2.2 A single dummy independent variable
2.3 Using dummy variables for multiple categories
2.4 Interactions involving dummy variables
2.5 A binary dependent variable: The linear probability model
3. Multicolinearity
3.1 Perfect colinearity
3.2 The effects of multicolinearity
3.3 Indicators of multicolinearity
4. Heteroskedasticity
4.1 Consequences of heteroskedasticity for the OLS estimator
4.2 Robust estimation of heteroskedasticity
4.3 Tests for heteroskedasticity
4.4 Generalized least squares estimation
5. Endogenous Regressors
5.1 Causes of endogeneity
5.2 Tests for endogeneity
5.3 Instrumental variables
1. Testing linear relationship between the variables contained in the model. These tests are of special interest to study whether the relation postulated by the economic theory is present in the actual data.
2. The use of dummy variables in order to introduce into the model the effect of quantitative explanatory variables or other effects that are difficult to measure.
3. Multicollinearity between the explanatory variable is a common problem in the econometric analysis. The standard techniques how to deal with this problems are covered.
4. The regression model in the presence of heteroskedasticity. It is common that the uncertainty about economic variables is not constant over time, which will be reflected in the empirical data. In these circumstances, the properties of the estimators change and it could be necessary to consider alternative estimation techniques to this problem into account.
5. Finally, the problem of endogeneity of variables is considered. In this case, the use of instrumental variables to obtain estimators with ¿nice¿ properties will be explained.
PROGRAMME
1. Inference in the multiple regression model
1.1 Basic concepts
1.2 Sampling distributions of the OLS estimators
1.3 Testing hypotheses about a single population parameter
1.4 Confidence intervals
1.5 Testing hypotheses about a single linear combination of parameters
1.6 Testing multiple linear restrictions: the F-test
2. Multiple regression with dummy variables
2.1 Describing qualitative information
2.2 A single dummy independent variable
2.3 Using dummy variables for multiple categories
2.4 Interactions involving dummy variables
2.5 A binary dependent variable: The linear probability model
3. Multicolinearity
3.1 Perfect colinearity
3.2 The effects of multicolinearity
3.3 Indicators of multicolinearity
4. Heteroskedasticity
4.1 Consequences of heteroskedasticity for the OLS estimator
4.2 Robust estimation of heteroskedasticity
4.3 Tests for heteroskedasticity
4.4 Generalized least squares estimation
5. Endogenous Regressors
5.1 Causes of endogeneity
5.2 Tests for endogeneity
5.3 Instrumental variables