Statistika: Statistics and Economy Journal - No. 1/2014

Great changes were happening in the economy of the Czech Republic during the last twenty years (1990–2011). One of the biggest was a huge increase of the foreign trade importance. The growing foreign trade then formed an aggregate demand as well as aggregate supply. If the economy in the beginning of the 90´s faced mostly the volatility of domestic demand, in 2011 the effect of domestic and foreign factor was comparable. As the economy in the 90´s was not capable to produce sufficient amount of products to satisfy domestic demand, at the end of last decade it had no problem to do so – the surplus of domestic supply over domestic demand was then situated to the foreign market.

Keywords
Aggregate demand, aggregate supply, domestic demand, domestic supply

Empiric analysis of the sector of non-financial corporations in the Czech Republic shows history of their terminations during the period 1995–2011. The purpose was to observe, what differences in the evolution of terminations (bankruptcies) of companies are connected with the predominant form of their ownership (only legal persons were analysed). Therefore, selected methods of the companies´ terminations were monitored according to a group of legal persons with prevailing domestic private capital and also group with predominance of the public capital. Also, the firms under foreign control were analysed. The companies with prevailing private domestic capital have dominated due to their largest number. However, the foreign-controlled companies have showed faster pace of the terminations during the analysed period and also their greater sensitivity to the economic cycle has been demonstrated. Liquidation was the most common method of the companies´ termination (roughly two-thirds of the total number of terminations in 2011). Dissolution without liquidation with successors represented one tenth of the terminations in the segment with predominance of priváte national capital and 15% in the segment of foreign-controlled companies.

Keywords
Non-financial corporations, ownership, liquidations, bankruptcy

Remittances represent transfers of earned money of foreigners to home country and they belong to often discussed topics in the connection with migration issues. The reason is the recent increase of the number of migrants and the amount of sent remittances. Since the Czech Republic became the immigration country, remittances have gained the importance. Many foreigners come to the Czech Republic because of work or study. However, many of them send earned money back to their country of origin, to their families and relatives. The information about the foreigners is crucial for describing their behaviour (incomes, consumption expenditures) and recording the transactions in national accounts and balance of payments. Permanent lack of data sources causes problems with such statistics. The aim of the paper is the description and interpretation of the issue of remittances. Procedures that are used for these estimates are briefly described with respect to the users’ needs. The description is mainly focused on the estimates of numbers and structures of foreigners, covering the length of stay, economic activity, their behaviour and estimation of sent remittances.

Keywords
Migration, remittances, national accounts

This paper suggested the ratio-type and product-type exponential estimators of the population mean
of a study variable through predictive approach using Bahl and Tuteja (1991) ratio-type and product-type exponential estimators as a predictor of the mean of the unobserved units of the population. Properties of the suggested estimators are studied up to first order of approximation in simple random sampling using information on an auxiliary variable. The theoretical conditions under which the suggested estimators are less besed and more efficient than the usual unbiased, ratio, product estimators and estimators due to Srivastava (1983) and Bahl and Tuteja (1991) have been obtained. In support of the theoretical study numerical illustration is also given and determined that the suggested estimators showed also an improvement over the classical estimators empirically.

Keywords
Predictive approach, auxiliary information, population mean, exponential estimators, bias, mean squared error

The main purpose of the paper is to empirically examine the aviation-led growth hypothesis for the Czech Republic by testing causality between aviation and economic growth. We resort to econometric tests such as unit root tests and test of cointegration purposed by Johansen (1988). Fully Modified OLS, Dynamic OLS and Conical Cointegration Regression are used to estimate the cointegration equation for time span of 42 years from 1970 to 2012. Empirical results reveal the existence of cointegration between aviation demand and economic growth. Graphic methods such as Cholesky impulse response function (both accumulated and non-accumulated) and variance decomposition have also been applied to render the analysis rigorous. The positive contribution of aviation demand to economic growth is similar in all three estimation techniques of cointegration equation. Finally, Granger causality test is also applied to find the direction of causal relationship. Findings help in lime-lighting the importance of aviation industry in economic growth for a developing country like the Czech Republic.

Keywords
Aviation, economic growth, Unit Root Tests, Fully Modified Ordinary Least Square (FMOLS), Dynamic Ordinary Least Square (DOLS), Conical Cointegration Regression (CCR), Aviation Multiplier

Missing covariate values is a common problem in a survival data research. The aim of this study is to Compaq the use of the multiple imputation (MI) and last observation carried forward (LOCF) methods for handling missing covariate values in the Cox proportional hazards (PH) regression model. The comparisons between the methods are based on simulated data. The missingness mechanism is assumed to be missing at random (MAR). Missing covariate values are generated under different missingness rates. The results from both methods are compared by assessing the bias, efficiency and coverage. The simulation results in general revealed that MI is likely to be the best under the MAR mechanism.

Keywords
Missing covariate values, multiple imputation (MI), Cox proportional hazard model, Last observation carried forward (LOCF), missing at random (MAR)

In the paper, some classical and recent approaches to cluster analysis are discussed. Over the last decades researchers focused mainly on categorical data clustering, uncertainty in cluster analysis and clustering large data sets. In this paper some of the recently proposed techniques are introduced, such as similarity measures for data files with nominal variables, algorithms which include uncertainty in clustering, and the method for data files with many objects.

Keywords
Cluster analysis, similarity measures, hierarchical clustering, k-clustering, fuzzy clustering, large data sets

Book Review

MAREK, L. Pravděpodobnost. Prague: Professional Publishing, 2012. ISBN 978-80-7431-087-4.