On behalf of Prof Di Serio I am sharing the following announcement
———————-
The Statistical Network Science committee of the Bernoulli Society invites you to an online talk this week Thursday:
Thursday May 16
2-3 pm UK time
Title: Bayesian network structural learning from complex survey data
Statistical Network Science Seminar Series- Bernoulli Society
Speaker: Paola Vicard (Department of Economics, Università Roma Tre, Rome, Italy)
Abstract: The association structure of a Bayesian network can be known in advance by subject matter knowledge or have to be learned from a database. One of the most widely used procedures is the PC algorithm consisting in carrying out several independence tests on the available data set and in building a Bayesian network according to the tests results. In case of data driven learning, the PC algorithm is based on the irremissible assumption that data are independent and identically distributed. Unfortunately, official statistics data are generally collected through complex sampling designs, then the aforementioned assumption is not met. In such a context the PC algorithm fails in learning the structure. To avoid this, the sample selection must be taken into account in the structural learning process. A modified version of the PC algorithm is proposed for inferring causal structure from complex survey data. It is based on resampling techniques for finite populations. A simulation experiment showing the robustness with respect to departures from the assumptions and the good performance of the proposed algorithm is carried out. (Joint work with Daniela Marella, Sapienza Università di Roma)
Zoom link
https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fzoom.us%2F...https://zoom.us/j/99820613967
Meeting ID: 998 2061 3967
Passcode: 850644
All welcome Clelia Di Serio and Gesine Reinert