Darling-Erdös-type test for change detection in parameters and variance for stationary VAR models

The aim of this article is the construction of the test statistic for the detection of changes in vector autoregressive (AR) models where both AR parameters and the variance matrix of the error term are the subjects of a change. The approximating distribution of the proposed statistic is the Gumbel distribution. The proof stands on the approximation of weakly dependent random vectors by independent ones and by application of Horváth’s extension of Darling-Erdös extremal result for random vectors, see Darling and Erdös (1956) Darling, D.A., Erdös, P. (1956). A limit theorem for the maximum of normalized sums of independent random variables. Duke Math. J. 23:143–155.[Crossref], [Web of Science ®] , [Google Scholar] and Horváth (1993) Horváth, L. (1993). The maximum likelihood method for testing changes in the parameters of normal observations. Ann. Stat. 21(2):671–680.[Crossref], [Web of Science ®] , [Google Scholar]. The test statistic is a modification of the likelihood ratio.     

Evaluation of the location of cities in terms of land cover on the example of Poland

Urban Ecosystems - The increasing availability of remote sensing materials of varying spatial resolution inclines to look for methods enabling their use, both at planning the spatial structure of...     

Flow and stock analysis of Polish unemployment: January 1990-June 1991*

Abstract. Unemployment is and will be for the foreseeable future one of the major issues of economies in transition. Not onIy is unemployment in post-communist economies a socially explosive problem; what happens on the unemployment front allows us to also make inferences about the state of the transition process in general. In this paper we look at Polish unemployment as it evolved from January 1990 to June 1991. A framework is developed which allows us to discuss flows into and out of unemployment. In analyzing the determinants of the various flows we discuss the macroeconomic environment brought about by the reforms and the role of prices and wages. However, we stress above all institutional and structural factors which have an impact on labour flows in the Polish post-communist economy. The stocks of several variables are also analyzed. We relate the trends of some unemployment stocks (especially the stocks of school leavers and group layoffs) to the trend of the overall stock of unemployment. We also look at the trends of vacancies and of various UIV ratios and touch upon the short run and long run trends of employment by sector. The main conclusion of the paper is that the high level of unemployment in Poland is neither due to the elimination of hidden unemployment (it actually increased in 1990!) nor a result of restructuring. The level of unemployment is high because of large inflows from outside the labour force and because hirings have been much fewer than in previous years while separations have only been slightly greater.     

Bootstrapping the conditional copula

This paper is concerned with inference about the dependence or association between two random variables conditionally upon the given value of a covariate. A way to describe such a conditional dependence is via a conditional copula function. Nonparametric estimators for a conditional copula then lead to nonparametric estimates of conditional association measures such as a conditional Kendall's tau. The limiting distributions of nonparametric conditional copula estimators are rather involved. In this paper we propose a bootstrap procedure for approximating these distributions and their characteristics, and establish its consistency. We apply the proposed bootstrap procedure for constructing confidence intervals for conditional association measures, such as a conditional Blomqvist beta and a conditional Kendall's tau. The performances of the proposed methods are investigated via a simulation study involving a variety of models, ranging from models in which the dependence (weak or strong) on the covariate is only through the copula and not through the marginals, to models in which this dependence appears in both the copula and the marginal distributions. As a conclusion we provide practical recommendations for constructing bootstrap-based confidence intervals for the discussed conditional association measures.     

Multiple belongings: transnational mobility,social class,and gendered identities among Polish migrants in Norway

ABSTRACT

Using ethnographic research in Norway and in Poland, this article focuses on the dynamics of multiple belongings of Polish migrants. It explores their experiences of belonging in relation to social class, gendered identities, and their different strategies of transnational mobility between Poland and Norway. By approaching belonging ‘from below’, we posit that it is a dynamic, processual, and socially and culturally constructed attachment to places, times, and communities, which includes experiential, practical, and affective dimensions. Considering the importance of questions of belonging and home-making in migrants’ lives, always contextually produced and read through performative reiterations, we focus on migrants’ daily routines and migratory practices, and argue that belonging is a multifaceted process, which takes on diverse forms and meanings of ‘who’ belongs to ‘what’, ‘where’ and ‘when’. Following intersectional perspective, the article aims at problematizing dependencies between mobility, gender, class, and migrants’ multiple belongings, and thereby, enhancing the understanding of the notion of belonging and its embeddedness in the inter-related social, cultural, economic, and political realms.     

Kognitive Prozesse und Antwortverhalten in einer Internet-Befragung

So far, certain problems of web surveys have received great attention: Coverage problems, sampling issues and response rates as well as screen design and usability issues. With some of the disadvantages mentioned diminishing, web surveys are increasingly adopted by survey researchers. In terms of the validity of web surveys early studies suggested that — controlling for other sources of survey error — little differences are to be expected in terms of response distributions. However, little insight is available regarding the cognitive processes at work in a respondent’s mind when answering a survey question on the internet. We assume that the cognitive capacity available when answering a survey question is impaired by the respondent’s navigational efforts when working through the questionnaire. Comparing the navigational tasks in a paper and pencil survey and a web survey, the later is considered to be more demanding compared with a paper questionnaire. Reading and flipping through pages is a task that can be done with little distraction from the question answer process. By contrast, browsing through an online form using mouse and buttons while reading is more demanding and distracting for the respondent. Thus, working through an online survey reduces the respondent’s attention for the question answer process. In this paper we present results from a large scale field experiment (n = 5,000) on measurement error in mixed mode survey (p&p and online) among the German youth conducted in spring of 2001. In this survey, 5 experiments on measurement error were incorporated: 1 experiment on question order, 2 experiments on response categories, and 1 experiment on response order in long lists and 1 experiment on social desirability. The results suggest that measurement effects are generally smaller in the web portion of the survey. In the conclusions the paper discusses the question whether or not we need to worry about the respondent’s redued atteniton to the survey questions under web conditions.     

Estimation of a Copula when a Covariate Affects only Marginal Distributions

This paper is concerned with studying the dependence structure between two random variables Y₁ and Y₂ in the presence of a covariate X, which affects both marginal distributions but not the dependence structure. This is reflected in the property that the conditional copula of Y₁ and Y₂ given X, does not depend on the value of X. This latter independence often appears as a simplifying assumption in pair‐copula constructions. We introduce a general estimator for the copula in this specific setting and establish its consistency. Moreover, we consider some special cases, such as parametric or nonparametric location‐scale models for the effect of the covariate X on the marginals of Y₁ and Y₂ and show that in these cases, weak convergence of the estimator, at ‐rate, holds. The theoretical results are illustrated by simulations and a real data example.     

Replik Auf Den Diskussionsbeitrag Von Rolf Becker

In a previous article in this journal (Fuchs/Sixt 2007) based on an analysis with the Socio-Economic Panel (SOEP) we have argued that children of educational climbers do not have educational opportunities similar to the typical educational opportunities of children on the newly achieved educational level. Even though we could demonstrate that the climbers’ children are subject to an increase of their educational opportunities compared to the level from which their parents originate, they do not reach the average of the destination level. Based on the theoretical reasoning provided by Bourdieu we argue that this educational disadvantage is caused by the lower furnishing of their families with social, cultural, and economic capital, by climbers’ employment position which is less advantageous, and also by the lower educational level of the climbers’ partners. In his detailed discussion of our analysis Rolf Becker has identified conflicting findings compared to his previous analysis based on the data of the German Lebensverlaufsstudie. In response to his critical discussion we will solve this ostensible caveat. Using again data from the SOEP we demonstrate that his seemingly contradictious findings are due to the specifics of his analytical approach. While Becker shows that the climbers’ children reach educational opportunities that are higher compared to the opportunities of children from the climbers’ level or origin (positive effect of climbing), our results indicate that their educational opportunities do not reach the level that is typically seen on the higher level of education that the educational climbers have reached for the first time (negative effect of climbing).