|
Diffusion MCMC for Mixture Estimation
Reichl, Jan ; Dedecius, Kamil
Distributed inference of parameters of mixture models by a network of cooperating nodes (sensors) with computational and communication capabilities still represents a challenging task. In the last decade, several methods were proposed to solve this issue, predominantly formulated within the expectation-maximization framework and with the assumption of mixture components normality. The present paper adopts the Bayesian approach to inference of general (non-normal) mixtures via the Markov chain Monte Carlo simulation from the parameter posterior distribution. By collaborative tuning of node chains, the method allows reliable estimation even at nodes with significantly worse observational conditions, where the components may tend to merge due to high variances. The method runs in the diffusion networks, where the nodes communicate only with their adjacent neighbors within 1 hop distance.
|
|
Global Economy Outlook - January 2016
Česká národní banka
This year’s first issue of Global Economic Outlook presents the regular monthly overview of recent and expected developments in selected territories, focusing on key economic variables: inflation, GDP growth, leading indicators, interest rates, exchange rates and commodity prices. In this issue, we also focus on the life cycle of foreign direct investment (FDI) on both the theoretical and empirical level. Our article presents an empirically derived general profile of the FDI profitability life cycle and then applies it to create scenarios for the probable future evolution of total FDI earnings on the example of the Czech Republic.
Fulltext: PDF; PDF
|
| |
| |
| |
| |
| |
|
Security Threats for the Czech Republic in View of Public - December 2015
Tuček, Milan
In December 2015, respondents had to assess security threats related to selected groups in the Czech Republic and they were also expressing views on threats by war, epidemics, natural disasters, economic crisis or resource crisis. These two questions were amended with an open question trying to find out, which countries represent a security threat for the Czech Republic. The survey also focused on expectations concerning the future of the personal life of citizens, the future of the Czech society and the future of the whole humankind.
|
|
Taxation in View of Public Opinion - November 2015
Červenka, Jan
According to November 2015 survey of the Public Opinion Research Centre 13% of citizens regard taxation on high-income earners as high, 27% say it is adequate and 50% think it is low. Taxation on average-income earners is considered to be high by 39% of respondents, adequate by 50% and low by 3% of citizens. Taxation on low-income earners was supposed to be high by 60%, adequate by 28% and low by 3%. 64% of respondents think that tax rate should be higher for high-income earners than for low-income earners.
|
|
Does prison overcrowding loom again? Predicting the prison population in the Czech Republic
Dušek, Libor
The study presents a projection of the prison population in the Czech Republic based on a\nnewly developed simulation model. It also points out the main trends in the criminal justice\npolicy and quantifies their impact on the past growth in the prison population.\nCzech prisons currently house 18,609 sentenced inmates. Unless crime rates and criminal\njustice policy change, we estimate that by the end of 2016 this number will reach 20,000 and\nthen level off at 20,360 inmates. If the current trends in the crime rates and criminal justice\npolicy continue, the sentenced prison population will steadily grow and will surpass 21,740\nby 2024.
|