Renowned international experts in higher education financing have argued that, owing to large government deficits, tertiary education will not be able to open up and meet growing demand unless cost-sharing principles and efficient student financial aid programmes are introduced. Opponents of cost-sharing in higher education object that introducing tuition fees will raise inequality in access to higher education. Drawing on OECD data, and focusing on college expectations, the authors argue that the effects of ability, gender, and socio-economic background on college expectations are primarily shaped by the characteristics of secondary education systems, such as the degree of stratification and vocational specificity of secondary schools, while the principal characteristics of the tertiary education system, such as enrolment rates and the model of financing, play a much less important role. The results clearly show that, after controlling for the effects of secondary school system characteristics, cost-sharing, as such or by degree, does not affect the formation of college expectations by ability, gender, and socio-economic background as much as the selectivity of the secondary school system does.
The article explains the various errors that occur in the use of the concept of statistical significance. It points to the problem of census, nonprobability sampling, sampling of small populations and small samples. Another topic is the use of statistical methods on aggregated data files, especially from international research, and on weighted data. The authors point out that in many cases the use of statistical significance is not appropriate, and they warn against the incorrect use of traditional statistical methods. The article also presents methods that can be used to avoid the problems to which the authors have drawn attention.
The use of significance tests in social sciences is widespread mainly due to simple computation via statistical packages. Unfortunately the more social scientists use statistical significance estimates for making causal inferences the less they appear to understand about this influential concept. Statistical modelling results are usually presented in terms of their statistical significance and little other information is provided. The goal of this article is to show the limits of using statistical significance as a sole means of making inferences; and to present alternative statistical fit indicators readily available within frequentist approach to statistics: confidence intervals, minimum sample size and power analysis. Multiple working hypotheses are also explored together with two well known information criteria – AIC and BIC. This article provides practical information on how to undertake valid and reliable statistical analyses of social science data.
The use of significance tests in social sciences is widespread mainly due to simple computation via statistical packages. Unfortunately the more social scientists use statistical significance estimates for making causal inferences the less they appear to understand about this influential concept. Statistical modelling results are usually presented in terms of their statistical significance and little other information is provided. The goal of this article is to show the limits of using statistical significance as a sole means of making inferences; and to present alternative statistical fit indicators readily available within frequentist approach to statistics: confidence intervals, minimum sample size and power analysis. Multiple working hypotheses are also explored together with two well known information criteria - AIC and BIC. This article provides practical information on how to undertake valid and reliable statistical analyses of social science data., Petr Soukup., and Obsahuje bibliografii a bibliografické odkazy
The article briefly describes multilevel models and presents their simplest applications. After the methodological and statistical need for this procedure is explained, real data are used to demonstrate how a hierarchical linear model is constructed. The article presents models with a random intercept, models with random slopes, and models with explanatory variables measured at higher levels. In the conclusion, other possible applications of multilevel analysis are discussed, and the basic readings on multilevel analysis are presented.
Objectives. Due to the rise of depressive symptomatology especially among vulnerable populations such as young adults during the COVID-19 outbreak, a reliable measuring tool is needed. Because of the lack of such studies, the authors decided to validate the 8-item Center for Epidemiologic Studies Depression Scale (CES-D 8) among Czech university students capturing the beginning of lockdown experience. Statistical analyses. Confirmatory factor analysis was conducted and structural equation modelling with diagonally weighted least squares estimation using lavaan was employed. Different hypotheses about the dimensionality of the CES-D 8 scale were tested. The authors assessed the measurement equivalence of the CES-D 8 scale according to gender using multigroup confirmatory factor analysis. The effect of socio-demographic and COVID-19 issues variables on depression was examined. Results. One dimensional model with correlated errors showed sufficient validity and therefore, the best fit. Multigroup confirmatory factor analysis results revealed that the factor structure is invariant across gender. Women and those who reported financial distress and academic stress showed a higher level of depressive symptomatology. On the other hand, relationships proved to have a protective effect. Limitations. The sample came from an online survey, respondents were self-selected. There was a gender imbalance in the sample that cannot be explained by a higher number of women in the Czech university environment. Conclusions. The CES-D 8 proved to be a useful instrument for measuring depressed mood that opens further possibilities for depression research in the university environment and during pandemic situations. and Cíle. Vzhledem k nárůstu depresivní sympto-matologie během pandemie covid-19 zejména u zranitelných skupin, jako jsou mladí dospělí, narostla potřebnost spolehlivého nástroje na mě-ření depresivity. Z důvodu chybějící validizace se autoři rozhodli ověřit osmipoložkovou škálu Center for Epidemiologic Studies Depression Scale (CES-D 8) u českých vysokoškolských studentů v době samého počátku pandemie.Statistické analýzy. Byla provedena konfir-mační faktorová analýza za použití struktur-ního modelování metodou DWLS (diagonally weighted least squares) pomocí balíku laavan. Byly testovány různé hypotézy o dimenziona-litě škály CES-D 8. Pomocí MCFA (multigroup confirmatory factor analysis) autoři posuzovali ekvivalenci měření škály CES-D 8 podle po-hlaví. Byl zkoumán vliv sociodemografických proměnných a proměnných týkajících se pro-blematiky covid-19 na depresivní symptoma-tologii.Výsledky. Jednodimenzionální model s korelo-vanými reziduálními rozptyly u dvou položek prokázal dostatečnou validitu a nejlépe odpoví-dal datům. Výsledky MCFA ukázaly, že faktoro-vá struktura zvoleného modelu byla invariantní vzhledem k pohlaví. Ženy a osoby, které byly ve finanční nouzi nebo prožívaly zvýšený stres ze studia, vykazovaly vyšší úroveň depresivní symptomatologie. Naopak partnerský vztah se ukázal mít protektivní efekt.Limity práce. Vzorek pochází z online průzku-mu, respondenti byli vybráni samovýběrem. Nadreprezentaci žen-studentek v datech nelze zdůvodnit vyšším podílem žen na českých uni-verzitách.Závěr. CES-D 8 se ukázal být užitečným nástro-jem pro měření depresivity, jenž otevírá další možnosti pro výzkum deprese v univerzitním prostředí a během pandemických situací.
In this article it is argued that one of the main problems in data analysis is an over-emphasis on statistical rather than substantive significance. Statistical significance reports the improbability of specific outcomes from sample data using a null hypothesis. In contrast, substantive significance is concerned with the real-world meaning of data modelling results for a population, regardless of p value, where an effect size estimator is used for evaluation. The argument presented in this article begins with a consideration of how substantive significance may be defined. Thereafter, there is a summary of the literature on substantive significance and its measurement using a variety of effect size estimators, many of which are little known to researchers. This article also examines the topics of economic and clinical significance. In the conclusion, this study discusses attempts to synthesise different concepts of substantive significance and recommends some practical usage of these concepts.
In this article it is argued that one of the main problems in data analysis is an over-emphasis on statistical rather than substantive significance. Statistical significance reports the improbability of specific outcomes from sample data using a null hypothesis. In contrast, substantive significance is concerned with the real-world meaning of data modelling results for a population, regardless of p value, where an effect size estimator is used for evaluation. The argument presented in this article begins with a consideration of how substantive significance may be defined. Thereafter, there is a summary of the literature on substantive significance and its measurement using a variety of effect size estimators, many of which are little known to researchers. This article also examines the topics of economic and clinical significance. In the conclusion, this study discusses attempts to synthesise different concepts of substantive significance and recommends some practical usage of these concepts., Petr Soukup., and Obsahuje bibliografii
Objectives. The goal was to find out whether pu-blic policy attitudes to the preference of policy instruments in solving long-term unemployment are explained through a big-five factor model of personality or through political orientation. Participants and settings. Authors administered a questionnaire survey among 8,554 university students in the Czech Republic.Hypothesis. Public policy attitudes to individual policy instruments are most influenced by poli-tical orientation and the related personality traits of openness and conscientiousness. Authors as-sume that the personality traits of openness and conscientiousness correlate most significantly with the ideological predisposition, however, the political orientation directly influences pre-ferences for policy instruments.Statistical analysis. Correlation analysis, multi-ple linear regression, structural models.Results. Public policy attitudes to policy instru-ments were most influenced by political orien-tation and the related personality traits of ope-nness and conscientiousness. However, on the basis of structural models, not only the direct in-fluence of political orientation on preferences to policy instruments has been demonstrated; from the personality traits, it is again an openness of mind and conscientiousness.Study limitation. The use of a short version of BFI-10; the lack of theoretical and empirical studies dealing with the influence of personality traits on public policy making. and Cíle. Cílem je zjistit, zda může být preference opatření sloužících k řešení problému dlouhodo-bé nezaměstnanosti vysvětlena prostřednictvím pětifaktorového modelu osobnosti či prostřed-nictvím politické orientace.Participanti a procedura. Dotazníkové šetření mezi 8 554 studenty vysokých škol v České re-publice.Hypotéza. Základní hypotéza vychází z předpo-kladu, že veřejně politické postoje k jednotlivým opatřením nejvíce ovlivňuje politická orientace a s tím související osobnostní rys otevřenost a svědomitost. Předpokládáme, že osobnostní rysy otevřenost a svědomitost nejvýznamněji korelují s ideologickou predispozicí, nicméně přímý vliv na postoj k jednotlivým opatřením má právě politická orientace.Statistická analýza. Korelační analýza, mnoho-násobná lineární regrese, strukturní modely.Výsledky. Veřejně politické postoje k jednotli-vým opatřením nejvíce ovlivňuje politická ori-entace a s tím související osobnostní rysy ote-vřenost a svědomitost. Na základě strukturních modelů se však neprokázal pouze přímý vliv politické orientace na postoje k jednotlivým opatřením, ale také vliv dvou osobnostních rysů (otevřenost mysli a svědomitost).Omezení studie. Použití krátké verze BFI-10, nedostatek teoretických a empirických studií zabývajících se vlivem osobnosti na tvorbu veřejné politiky.