Kurtosis is routinely taught in introductory statistics courses, where it is sometimes still wrongly interpreted as "peakedness" even though the statistical profession has dismissed that notion. Furthermore, the internet abounds with wrong illustrations of kurtosis. Moreover, our literature search found only two actual published practical applications of the kurtosis statistic. To assess the merits of kurtosis, or lack thereof, we review the definition of kurtosis and present simulations that demonstrate extreme instability of kurtosis estimates, especially when viewed jointly with skewness. The main simulations were conducted with 100,000 draws of samples of size 30, 100 and 1000 from standard normal, standard uniform, lognormal, arcsine and standard triangular distributions. Results are presented graphically for the marginal and joint distributions of the skewness and kurtosis estimates. With the lognormal distribution, which is highly skewed, the vast majority of skewness-kurtosis pairs fell very far from the theoretical population values even in samples of size 1000. At the same time, high asymmetry of the sampling distribution of kurtosis when sampling from a symmetric distribution was observed for the arcsine and the standard triangular distribution. In addition, graphical assessment of the coverage of confidence intervals for the studied distributions based on 1000 samples of size 100 revealed several problems. We also made two sets of didactic simulations with data from standard normal distribution to illustrate the huge sampling variability of kurtosis estimates as compared to estimates of lower moments. Hence, we believe that kurtosis should be avoided in non-specialist introductory statistics courses, it should not be routinely calculated as part of numerical data description (whereby its standard error is particularly misleading), and it should not serve routinely as criterion for assessing appropriateness of using the normal distribution as the model for an empirical dataset.
The article proposes a resource model of a social community developed by the authors. Aim the study was the definition of theoretical aspects that allow predicting the main directions of the transformation of social community, which determine the formation of social request for professional self-development of the individual, as a manifestation of the activity of the social lift. The scientific novelty of the work is the structure of social society that reflects the resource approach, the basic principles of its change and the main criteria that allow the formation of forecast estimates transformation of the social hierarchy. The social community is considered by the authors as self-regulating system that is in competitive interaction with other similar systems. The main idea of the proposed resource model is the possibility of transforming social society under the influence of changes in the system of social hierarchy of managing resource flows. The main principles of the proposed resource model of social community are shown in relation to the organization of the education system. The main participants of the education system are singled out, the possibility of predicting, depending on the shift in the resource exchange between them, the education system's transformations are substantiated. In the proposed resource model, ensuring the stability of the social system is realized by the processes of social lift, to which the authors include the professional self-development of the individual. The proposed resource model of a social society makes it possible to implement a set of social planning measures for the development of society, minimizing the risks of critical surges and social transformations.
When researchers design survey questions, they must, among other things, ensure the comparability of responses from different respondents. This means that all respondents are expected to understand the question in the same way. Precisely how the respondents understand the survey question and how they formulate the answer to it is the subject of this article. Here, we tackle this kind of problem using the example of a survey question about subjective social status (SSS) used in the International Social Survey Program (ISSP). We used a mixed methods design, specifically a sequential exploratory design, where qualitative analyses of data from cognitive interviews were supplemented with quantitative analyses of survey data. Firstly, we conducted a qualitative study in the form of cognitive interviews using the thinking-aloud technique. We conducted a qualitative analysis using open coding to identify general categories that should capture the content of the interviewees' think-aloud process. Secondly, we used regression analysis to check the correspondence between (objective) socioeconomic status and subjective social status on the data of the ISSP 2019 survey. The results of the regression analyses show that the respondents do take into account their (actual) socio-economic position when self-ranking on the social scale such as education and income. Cognitive interviews show that the respondents differ regarding which dimension of the socio-economic situation they relate to when answering the question on SSS. Furthermore, explanations of self-classification that go beyond the actual socio-economic position are possible as well.
In the paper we cast serious doubt on the usefulness of the index of concordance (C-index) and the coefficient of determination for survival models. The index of concordance is known for not being useful when selecting the best of several competing models because of its nonsensitivity. We show that it can even go down when a significant covariate is added to a correctly specified model, including cases when there is no censoring and no tied event times or covariate values, meaning that the usual suspects are not responsible. The coefficient of determination was originally suggested because its formula gives the usual R2 when used in linear regression. But, the analogy with the linear model is gone when we use survival analysis models, since it crucially depends on the null model which changes with the change in the fitted model. We illustrate the expected behaviour of such measures and compare with an alternative Schemper–Henderson measure.
The research paper investigates the impact of raking on survey estimates in the context of a Croatian senior population survey conducted in January 2022. Raking is a statistical technique used to improve the accuracy and precision of survey estimates by adjusting the survey sample to match known characteristics of the population. The main objective of the paper is to determine whether applying raking to a survey is beneficial when the survey sample has already been adjusted to match certain population characteristics. In this case, the survey sample was initially adjusted using quota sampling based on the 2011 census data, considering gender and NUTS2 region as variables. An important factor in this study is that a new census was conducted in 2021, which provided updated population characteristics. The research aims to compare survey point estimates using both the 2011 and 2021 population data. The research conducted raking analyses using a variety of combinations of variables, including age, gender, county, and NUTS2 region. A total of 11 different combinations of these variables were used in the raking analyses. The study also examined the impact of the different number of iterations in the raking process, specifically observing results for 5, 10, and 20 iterations. The research included statistical tests to compare point estimates derived from the survey sample to those derived from raking using different sets of population data. In almost all cases, no statistically significant differences in point estimates were found. However, statistically significant differences did emerge when comparing sample point estimates to raking point estimates based on the 2021 census data, particularly when the number of estimated raking weights was the highest.
Dementia poses a specific risk to the expression of identity due to the progressive decline of cognitive abilities and the general negative image of people with dementia. Prejudice and negative beliefs often lead to stigma and discrimination, which can depersonalise people with dementia and make it impossible for them to express their identity. The socially constructed image of people with dementia points to the need to explore the concept of identity of people with dementia. Based on qualitative research conducted in an old people's home and narrative interviews with residents with dementia, we demonstrate the possibilities of asserting the identity of people with dementia in an institutional setting. The paper highlights various factors that have a significant impact on the identity formation of residents with dementia. Among the most highlighted are appearance, physical abilities, social environment, activities, emotions, and religion. Residents with dementia develop different strategies to cope with the changes brought about by dementia and ageing (accepting change, redirecting negative thoughts, and maintaining skills through activities and employment). The paper presents the ability of residents with dementia to maintain or even transform their identity in an institutional setting, which has a strong impact on the expression and assertion of the individual's identity.
This paper is an attempt to deconstruct, formally decode the notion of responsibility frequently appearing in the process of deinstitutionalisation and long-term care provision. It is a Kafkian predicative category of subordination. Its value is determined by its two objects. "For what" we are responsible constitutes the substance of responsibility, "to what" constitutes its form and sense. By examining the substance of responsibility—for acts, things and people, we have derived the basic parameters, conditions constitutive of responsibility: loss (negative consequences), alienation, reification, removal of will and ascribing. Investigating the form of responsibility, of that to which we are responsible, we have schematically divided instances of responsibility into hierarchic and horizontal, as well as into reflexive and transient. Intricacies of responsibility to authorities, public, community as well as to near ones and the self are explored in their action and contemplative properties. Deinstitutionalisation on the one hand restores civic responsibility to the service users, on the other it transmutes its very conditions. The imperative is to restore their will capacity, not to ascribe acts to stigma, allow reappropriation and humanisation and to put the emphasis on achievement and success. In the case of the key worker, we demonstrate a new pattern of professional responsibility, in which acts are actors' responsibility, while helpers are responsible for service delivery, their own acts and for teamwork that will uphold the user's emancipation. In the transition to community, subordinative responsibility is being transformed into everyday responsiveness and common responsibility for humanity.
Social work is constantly evolving and theoretically enriched to meet people's needs in new social situations. Informal carers must balance care with other demands while facing a range of obstacles. Despite research on what informal carers require, a specific typology of their needs has yet to be formulated. The research question considered is "What are the (groups of) needs of individuals who provide informal care for people with dementia?". As part of the research project Long-term Care for People with Dementia in Social Work Theory and Practice, we interviewed a non-random convenience sample of 20 relatives acting as informal carers of people with dementia. The results are presented as a typology of needs on the micro level (personal health—emotional health, physical health), mezzo level (care tasks—support from formal care, planning—information, counselling) and macro level (legislation, system changes). Most obstacles and needs identified were on the micro and mezzo levels. More than on the system (macro level), informal carers see the responsibility and burden of care as lying on the individual (micro level) and institutions and the community (mezzo level).
Long-term care for people with dementia has been studied using the Rapid Assessment of Needs and Services method, which has been used to map long-term care needs in order to stimulate the development of care that effectively meets the needs of people with dementia. In this paper, we present the results of three focus groups with key stakeholders in long-term care for people with dementia in three selected communities, involving 29 people from a variety of organisations: social work centres, homes for the older people, health centres, general and psychiatric hospitals, municipalities and non-governmental organizations. Qualitative analysis of the empirical material showed that the following problems are prevalent in the communities: (i) acute and unmet needs of informal caregivers, (ii) a multi-tiered system of long-term care that puts people in an unequal position, (iii) a lack of community-based long-term care, and inadequate responses to the needs of people with dementia. Even in communities where there are various forms of support, both institutional and community-based, available across all service sectors, long-term care for people with dementia is based on informal care. We propose the development of a national strategy for family caregivers, with special attention to informal caregivers of people with dementia. The support offered by existing facilities is inadequate, poorly accessible, or nonexistent. Homes for older people are overcrowded, and people with dementia wait months or years to be admitted to a home. Home-based assistance is not evenly distributed across communities, and its scale (20 hours per week) in particular is insufficient to meet the needs of people with dementia. There is a lack of alternative forms of care that enable people with dementia to remain in their own home environment for as long as possible, for example in the form of personal assistance. We suggest that the development of long-term care for people with dementia should be based on the proposed research methodology.
Ageing in place has for many years been at the forefront of political goals for care provision for older people in Europe. The organization of care in terms of the national governing structure must therefore be continually observed to better understand the care actually offered and then used by older people. In this study, we examined the organization of social home care and institutional care across municipalities and administrative units in terms of what is offered to older people as formal care. Variation across municipalities and administrative units is observed with explorative cluster analysis and analysis of means of key dependent variables across clusters to better understand the variability in the care offered to older people in those municipalities and administrative units. The results show that while social home care is temporally available across several clusters of municipalities, and the affordability of social home care is also stable across clusters of municipalities, there are still municipalities where social home care has a limited time availability and municipalities where the out-of-pocket contribution to social home care delivery is nearly the twice the average of such contributions. In terms of institutional care, one can find administrative units with either a deficit or a surplus of placements of such care available.
Moral foundations theory describes a complex space of human morality along five moral foundations: care/harm, fairness/cheating, loyalty/betrayal, and sanctity/degradation. The first aim of this study is to explore the role of socio-demographic variables in endorsing the five moral foundations and to provide insight into the role of moral foundations in attitudes towards homeless people. The second objective of the study is to provide an example of employing the Bayesian statistical approach. There were 162 participants in our study (27% male, mean age 36 years). Convenience sampling method was used. Age and education found to be the most important predictors of moral foundations, with Bayesian factors showing the strongest evidence for age as a positive predictor of moral foundations. Gender, political affiliation, care and authority were found to be important predictors of attitudes towards homeless people, with Bayesian factors showing much stronger evidence for moral foundations than sociodemographic variables. This study lays the groundwork for research on moral foundations in Slovenian samples and provides a practical example of Bayesian approach application in social science.
The article presents a pilot study based on intervention conducted in Croatia in 2022. Despite intensive peacebuilding efforts, ethnic tensions in post-conflict societies remain high, suggesting that current strategies may be missing critical components. This experiment integrated recent neurophysiological findings, particularly polyvagal theory, into peacebuilding intervention. The intervention involved a two-day seminar in Zagreb, where trauma-informed, body-based techniques were used to address post-war trauma. Participants learnt to recognise and manage trauma reactions by promoting their interoceptive awareness and a felt sense of safety. The seminar included both theoretical and experiential components, focusing on the impact of trauma on the autonomous nervous system and interpersonal dynamics. The study used an experimental design with intervention and control group to investigate the effects of the seminar. Measures included interoceptive awareness, autonomic reactivity, ethnic distance, perspective taking and mental well-being. The results showed that the participants in the intervention group showed significant improvements in interoceptive awareness, particularly in not worrying and emotional awareness subscales compared to the control group. However, ethnic distance scores did not decrease as expected, highlighting the complexity of changing deep-rooted attitudes. The study faced some challenges, including participant recruitment and the short duration of the intervention, which may have limited its effectiveness. Despite these limitations, the findings suggest that integrating trauma-informed approaches into peacebuilding efforts holds promise for improving interethnic relations. Future research should focus on longer interventions and diverse participant groups to better understand the potential of these methods in various contexts.
In this note, we propose a parametric inferential procedure for predicting future order statistics, based on record values, which takes inter-record times into account. We utilize the additional information contained in inter-record times for predicting future order statistics on the basis of observed record values from an independent sample. The two parameter exponential distribution is assumed to be the underlying distribution.
The effect of systematically altering the value of a single observation within a paired differences design is considered. A paradox is observed for the paired samples t-test, where increasing the value of an observation in the direction of the true mean difference results in a higher p-value. Using simulation, deviations from robustness of the paired samples t-test is demonstrated, and is contrasted with Yuen’s paired samples t-test and the Wilcoxon signed rank sum test.
In statistical quality control, X-bar control chart is extensively used to monitor a change in the process mean. In this paper, X-bar control chart for non-normal symmetric distributions is proposed. For chosen Student, Laplace, logistic and uniform distributions of quality characteristic, we calculated theoretical distribution of standardized sample mean and fitted Pearson type II or type VII distributions. Width of control limits and power of the X-bar control chart were established, giving evidence of the goodness of fit of the corresponding Pearson distribution to the theoretical distribution of standardized sample mean. For implementation of X-bar control chart in practice, numerical example of construction of a proposed chart is given.
In this paper we consider inference regarding the ratio of two normal and the ratio of two t-distributed random variables, using both the popular Fieller interval, as well as, exact distributions. We apply these methods to a historical dataset regarding the shape of the Earth, and estimate the Earth's flatness coefficient as a ratio of regression coefficients. We demonstrate the equivalence of the inference using the exact density of this ratio with that using the Fieller interval.
Ph.D. education is a key element in innovation and the generation of new knowledge. Nevertheless, in Italy, the share of doctoral graduates is still lower than the average for OECD member countries. This paper investigates the effectiveness of doctoral education and the extent to which the Italian labour market properly absorbs the rising flow of Ph.D. holders. The effectiveness is assessed from the twofold perspective of the formal relevance of a Ph.D. qualification in the labour market and the substantial applicability of skills acquired to different occupations inside and outside university. Logit models enable sketches of the main determinants of overeducation and overskilling among Italian Ph.D.'s, whereas log-earnings equations allow assessment of the role of educational and skills mismatches in terms of wage penalties. Oaxaca-Blinder decompositions help analyse some causes of these mismatches. The different patterns of overeducation and overskilling among Ph.D. holders working inside and outside academe lead to different degrees of pay penalties.
In case of web surveys, researchers struggle to achieve satisfactory response rates and to collect data of good quality. Those two problems could be mitigated by a thorough approach to the questionnaire design and by changing questionnaire elements that could have an impact on the questionnaire length and complexity levels. In the paper, the questionnaire length and complexity are quantified by observing survey times or the times that respondents need to complete the provided questionnaire. The questionnaire length and complexity levels have an impact on survey times and consequently on response rates. The aim of the paper is to investigate how different questionnaire lengths and complexity levels influence survey times. The selected questionnaire length and complexity determinants are observed using the case of two different questionnaire versions. Those questionnaire versions have been used in a business web survey of Croatian enterprises. The results have shown that on average the long questionnaire version is twice longer and 142% more complex than the short questionnaire version. However, due to the interaction effect of length and complexity determinants, the long questionnaire version has on average 119% higher questionnaire length and complexity level than the short questionnaire version. The analysis has shown that this increase of the questionnaire length and complexity had a different impact on enterprises with different characteristics. Furthermore, the increase of the questionnaire length and complexity level did not lead to a proportionate increase in survey time at the overall enterprises level.
Although leadership theory recognises the importance of leaders in a team, research has mostly focused on various personal characteristics of leaders or leadership style, while less attention has been paid to the social relationships in which leaders are embedded. We therefore examine both internal and external social ties of leaders with the aim of identifying variations in the network patterns of team leaders. We hypothesise that leaders' relationship patterns lead to different network structures, which in turn create differences in leadership roles. By examining the social networks of team leaders from Slovenian and Finnish organisations between 2009 and 2012, we empirically identify variations in leaders' social networks. The results suggest four distinct social structures within which team leaders perform their leadership roles. We have shown that leadership roles can be distinguished from teams and team leaders based on the characteristics of social networks.
