THE IMPLICATION OF DEMOGRAPHICS ON THE ROMANIAN PENSION SYSTEM

This paper aims to analyse the influence of the demographical factors on the short-term sustainability of the pension system from Romania. The data used for econometric modelling consisted of panel data for the period 2009-2019 for 8 European Union member states, together with time series data for autoregressive modelling. The following econometrical models were used: random-effects GLS regression and Box-Jenkins (ARIMA). The results emphasize an increasing demographical pressure on the Romanian pension system and the need of pension system reform.

Quantifying Dynamic Resilience using First-process Autoregressive Modelling: An Empirical Study

Dynamic resilience is a temporal process that reflects individuals’ capability to overcome task-induced stress and sustain their performance during task-related events. First-order autoregressive (AR(1)) modelling is posited for measuring individuals’ dynamic resilience over time. The current research investigated this by testing 30 adults in a dynamic decision-making task. AR(1) modelling was conducted on the data, and was compared against a modified seismic resilience metric for concurrent validity purposes. Results revealed that AR(1) modeled parameters are applicable in assessing participants’ dynamic resilience, with analyses supporting their use to distinguish between individuals that can overcome task-induced stress and those that cannot, as well as, in the classification of individuals’ dynamic resilience.

Investigating an Optimal Signal Epoch Length for Cardiotocographic Classification

This work focuses on investigating an optimal foetal heart rate (FHR) signal segment to be considered for automatic cardiotocographic (CTG) classification. The main idea is to evaluate a set of signal segments of different length and location based on their classification performance. For this purpose, we employ a feature extraction operation based on two signal processing techniques, such as the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and time-varying autoregressive modelling. For each studied segment, the features are extracted and evaluated based on their performance in CTG classification. For the proposed evaluation, we make use of real CTG data extracted from the CTU-UHB database. Results show that the classification performance depends considerably on the selected FHR segment. Likewise, we have found that an optimal FHR segment for foetal welfare assessment during labour corresponds to a segment of 30 minutes long.

Inter-individual differences in multivariate time series: Latent class vector-autoregressive modelling

Theories of emotion regulation posit the existence of individual differences in emotion dynamics. Current multi-subject time-series models account for differences in dynamics across individuals only to a very limited extent. This results in an aggregation that may poorly apply at the individual level. We present the exploratory method of latent class vector-autoregressive modelling (LCVAR), which extends the time-series models to include clustering of individuals with similar dynamic processes. LCVAR can identify individuals with similar emotion dynamics in intensive time-series, which may be of unequal length. The method performs excellently under a range of simulated conditions. The value of identifying clusters in time-series is illustrated using affect measures of 410 individuals, assessed at over 70 time points per individual. LCVAR discerned six clusters of distinct emotion dynamics with regard to diurnal patterns and augmentation and blunting processes between eight emotions.