Opiniones y comentarios de aprendices correspondientes a The Classical Linear Regression Model por parte de Universidad de Londres Queen Mary
Acerca del Curso
In this course, you will discover the type of questions that econometrics can answer, and the different types of data you might use: time series, cross-sectional, and longitudinal data.
During the course you will:
– Learn to use the Classical Linear Regression Model (CLRM) as well as the Ordinary Least Squares (OLS) estimator, as you discuss the assumptions needed for the OLS to deliver true regression parameters.
– Look at cases with only one independent variable for one dependent variable, before progressing to regression analysis by generalising the bivariate model to multiple regression.
– Explore different model-building philosophies, with particular focus on the general-to-specific approach, and learn how to use goodness-of-fit statistics as the measures of “how well your model explains variations in the dependent variable”.
Throughout this course, you will see examples to help clarify which kind of relationship is of interest, and how we can interpret it. You will also have the opportunity to apply your learning to estimating the Capital Asset Pricing Model using real data with R.
The course is for beginners, so little prior knowledge is required, but you will benefit from an ability to graph two variables in the xy framework, an understanding of basic algebra and taking derivatives. Knowledge of matrix algebra is not a requirement but will also provide you with an advantage.
By the end of this course, you will be able to:
– Describe the problems that econometrics can help addressing and the type of data that should be used
– Explain why some hypotheses are needed for the approach to produce an estimate
– Calculate the coefficients of interest in the classical linear regression model
– Interpret the estimated parameters and goodness of fit statistics
– Estimate single and multiple linear regression models with R....
1 - 2 de 2 revisiones para The Classical Linear Regression Model