Joint Statistics and Econometrics Seminar Series with Daniel Pena

Hosted by the Department of Statistics

Leverhulme Library, 6th floor of Columbia House


Daniel Pena

Daniel Pena


The next seminar in the LT 2018 Joint Statistics and Econometrics Seminar Series will be with Daniel Pena who is a Professor at Universidad Carlos III de Madrid. You can find details of Daniel's talk below:

Title: Forecasting Multiple Time Series with One-Sided Dynamic Principal Components

Abstract: We define one-sided dynamic principal components (ODPC) for time series as linear combinations of the present and past values of the series that minimize the reconstruction mean squared error. Previous definitions of dynamic principal components depend on past and future values of the series. For this reason, they are not appropriate for forecasting purposes. On the contrary, it is shown that the ODPC introduced in this paper can be successfully used for forecasting high-dimensional multiple time series. An alternating least squares algorithm to compute the proposed ODPC is presented. We prove that for stationary and ergodic time series the estimated values converge to their population analogues. We also prove that asymptotically, when both the number of series and the sample size go to infinity, if the data follows a dynamic factor model, the reconstruction obtained with ODPC converges, in mean squared error, to the common part of the factor model. Monte Carlo results shows that forecasts obtained by the ODPC compare favourably with other forecasting methods based on dynamic factor models.

Twitter and Facebook

You can get immediate notification on the availability of an event podcast by following LSE public lectures and events on Twitter, which will also inform you about the posting of transcripts and videos, the announcement of new events and other important event updates. Event updates and other information about what's happening at LSE can be found on LSE's Facebook page.

WIFI Access

LSE has now introduced wireless for guests and visitors in association with 'The Cloud', also in use at many other locations across the UK. If you are on campus visiting for the day or attending a conference or event, you can connect your device to wireless. See more information and create an account at Join the Cloud.

Visitors from other participating institutions are encouraged to use eduroam. If you are having trouble connecting to eduroam, please contact your home institution for assistance.
The Cloud is only intended for guest and visitor access to wifi. Existing LSE staff and students are encouraged to use eduroam instead.

 From time to time there are changes to event details so we strongly recommend checking back on this listing on the day of the event if you plan to attend.


LSE Statistics StatsDeptLSE

There has never been a more significant time to work in #DataScience and #AI so have a read of this piece by the Al……

2 hours ago

Reply Retweet Favorite

LSE Statistics StatsDeptLSE

Join us for our next Joint Risk & Stochastics and Financial Mathematics seminar taking place on Thursday featuring……

2 days ago

Reply Retweet Favorite

You have succesfully subscribed
Email entered is invalid, please try again.
An error occured while subscribing, please try again.

Sign up for events news