Sumários

lecture

19 Outubro 2026, 10:00 • Adriana Cornea-Madeira

We briefly looked at the plots of each mps series built by each group. Then we discussed about stationarity of time series processes and introduced the Wold Representation Theorem. We stopped at slide 30 of Lecture 3.

lecture

12 Outubro 2026, 10:00 • Adriana Cornea-Madeira

We discussed about the PCA and based on it we mentioned the extensions for time series. The first part of the project has been discussed (apply the PCA on the OIS data for the monetary policy event; the data is from Altavilla et al. paper mentioned at the end of the slides, take the first PC as a proxy for the monetary policy shock).  

lecture

28 Setembro 2026, 10:00 • Adriana Cornea-Madeira

We did a recap of OLS, the slides covered are those from the Recap folder.

lecture

21 Setembro 2026, 10:00 • Adriana Cornea-Madeira

We finished slide L1_trends_seasonality.pdf. in particular, we discussed about different other methods to remove trends (aside including a deterministic trend) such as the Hodrick-Prescott filter. We the discuss the dummy variable approach about removing seasonality, and mentioned about the existing of other methods. We also discussed the R code that produced the results from the slides (which included other filters for removing trends such as Baxter and King, Christiano and Fitzgerald). 


We just briefly introduced the PCA (first slide of L2_PCA) and asked the students to read for next time the following two papers (which are the basis for the first part of the project), see also slide 34: 

Altavilla, C., Brugnolini, L., Gürkaynak, R. S., Motto, R., and Ragusa, G. (2019). Measuring euro area monetary policy. Journal of Monetary Economics, 108:162–179.

Bauer, M. D. and Swanson, E. T. (2023). A reassessment of monetary policy surprises and high-frequency identification. NBER Macroeconomics Annual, 37(1):87–155. 

lecture

14 Setembro 2026, 10:00 • Adriana Cornea-Madeira

We discussed about the assumptions needed to validate the OLS estimation and inference within the framework of static models and finite distributed lags models. We discussed how to do inference on the long-run propensity. We started to discuss about deterministic trends and detrending (including FWL theorem implication for detrending). We illustrated the ideas on real data in R.