Στο πλαίσιο του Π.Μ.Σ. «Στατιστική και Αναλογιστικά - Χρηματοοικονομικά Μαθηματικά», και των εργαστηρίων «Στατιστικής και Ανάλυσης Δεδομένων» και «Αναλογιστικών και Χρηματοοικονομικών Μαθηματικών», οργανώνεται σεμιναριακή διάλεξη η οποία θα πραγματοποιηθεί από τον κ. Κουντζάκη Χρήστο, Επίκουρο Καθηγητή του Τμήματος Στατιστικής και Αναλογιστικών - Χρηματοοικονομικών Μαθηματικών, με τίτλο:
"VECTOR LATTICE LINEAR REGRESSION ANALYSIS: FITTING AND MODEL UNCERTAINTY"
Η σεμιναριακή διάλεξη θα πραγματοποιηθεί την Τρίτη 13 Ιανουαρίου και ώρα 20:00 και είναι ανοικτή σε οποιονδήποτε ενδιαφερόμενο.
💻 Σένδεσμος Διαδικτυακής Αίθουσας:
https://aegean-gr.zoom.us/j/97072796812?pwd=7tJZHGMSw4Ga92imW9bwknVDWGFYoQ.1
Meeting ID: 970 7279 6812
Passcode: 392102
Παραθέτουμε το abstract της σεμιναριακής διάλεξης:
Functional data analysis (FDA) is a popular research area of data analysis that is well-suited for modeling complex data structures such as time series data and images. In Linear Regression models, the random variables are often described using a finitedimensional vector space, under the assumption that the random variables are represented by a finite set of parameters. The random variables, however, are more complex in many real-world applications and cannot be adequately modeled by a finite set of parameters. In order to more accurately express complex random variables, FDA allows us to model random variables as functions. This can lead to a more flexible and expressive approach to the statistical model. Within FDA, this study investigates the potential of vector lattices to enhance model flexibility and address model uncertainty. The limitations of finite-dimensional vector spaces in capturing the complexities of real-world random variables are discussed. The theoretical framework of vector lattices, which provides a rich structure for modelling and analysis, is provided as a promising approach for functional data. An investigation is conducted into the concept of Vector Lattice Linear Regression Models (VLLM), highlighting their ability to effectively handle model uncertainty, which is an important component that is often ignored in standard regression methods.
