|
|
Essays on Data-driven, Non-parametric Modelling of Time-series
Hanus, Luboš ; Vácha, Lukáš (advisor) ; Witzany, Jiří (referee) ; Ellington, Michael (referee) ; Trimborn, Simon (referee)
This thesis consists of four contributions to the literature on data-driven and non-parametric modelling of time series. In the first paper, we study the synchronisation of business cycles and propose a multivariate co-movement measure based on time-frequency cohesion. We suggest that economic inte- gration may lead to increased co-movement of business cycles, which may reflect the benefits of convergence and coordination of economic policies. The second paper presents a new methodology for identifying persistence in macroeconomic variables. Using time-varying frequency response func- tions, we identify heterogeneous persistence effects in US macroeconomic variables. The third and fourth papers propose data-driven techniques for probabilistic forecasting of time series using deep learning. We introduce a multi-output neural network that selects the most appropriate distribution for the data. The distributional neural network is valuable for modelling data with non-linear, non-Gaussian and asymmetric structures. The third paper demonstrates the usefulness of the method by estimating information-rich macroeconomic fan charts and distributional forecasts of asset returns. In the last paper, we present the distributional neural network to obtain the proba- bility distribution of electricity price...
|
|
|
rDeterminants of Sales and Attendance of Shopping Centre
Kadlec, Martin ; Bolcha, Peter (advisor) ; Koubek, Ivo (referee)
The thesis analyses determinants of shopping centre sales and its attendance demand; it is based on data of the specific shopping centre from the years 2007 -- 2011. Based on a five-year monthly time series, two sales models are created. One model tracks sales per customer, the other deals with the shopping centre sales which are compared with the sales index of retailers. On the other hand, a model of the shopping centre attendance demand uses figures of a five-year daily time series. Independent variables with significant effect on dependent variables are identified in the theoretical part. The models are estimated using the Ordinary Least Squares estimation. In all models, seasonal influences proved to be a significant determinant. In the sales models, hypotheses of the competition effect have been verified. Furthermore, in case of the attendance demand model, weather and marketing effects were estimated as important. Surprisingly, the economic variables proved themselves to be insignificant, which could be caused by the relatively short observation period. The limiting factor of all models is also the fact that the dataset consists of one shopping centre only. It prevents the author from conducting a comprehensive examination of other important determinants of shopping centre sales and attendance.
|
guest ::
