Sumários
lecture
10 Outubro 2023, 10:30 • Adriana Cornea-madeira
We discussed the p-value approach and the confidence level approach to hypothesis testing, as well as how to use the t-test to test for a linear combination of parameters restriction. We illustrated the new concepts through many examples.
lecture
9 Outubro 2023, 10:30 • Adriana Cornea-madeira
We starting discussing inference under the classical linear regression model assumptions. We focused on the one-sided and two-sided t-test and illustrated the approach through some examples.
lecture
3 Outubro 2023, 10:30 • Adriana Cornea-madeira
We discussed the interpretation of parameters in log-linear, linear-log and log-log models. We started to work in Stata by estimating a model for house log prices (as a linear function of the amount of pollution and the number of rooms), and a model for the CEO log salaries (as a function of log(sales), log(market value), age and tenure in the company), focusing on understanding the Stata output, on the interpretation of the parameter estimates and how are actually obtained the OLS estimates.
lecture
2 Outubro 2023, 10:30 • Adriana Cornea-madeira
We derived the variance of the OLS estimator for the slope in the linear regression model. We discussed the Gauss-Markov assumptions and showed that the OLS estimator is the most efficient (best) among all linear unbiased estimators under the Gauss-Markov assumptions. We showed the implications on the variance when we omit an important variable from the regression (discussing the bias-variance trade-off).