Zero-Inflated NGINAR(1) process

In this paper, we develop a zero-inflated NGINAR(1) process as an alternative to the NGINAR(1) process (Risti?, Nasti?, and Bakouch 2009 Risti?, M. M., A. S. Nasti?, and H. S. Bakouch. 2009. A new geometric first-order integer-valued autoregressive (NGINAR(1)) process. Journal of Statistical Planning and Inference 139:2218–26.[Crossref], [Web of Science ®] , [Google Scholar]) when the number of zeros in the data is larger than the expected number of zeros by the geometric process. The proposed process has zero-inflated geometric marginals and contains the NGINAR(1) process as a particular case. In addition, various properties of the new process are derived such as conditional distribution and autocorrelation structure. Yule-Walker, probability based Yule-Walker, conditional least squares and conditional maximum likelihood estimators of the model parameters are derived. An extensive Monte Carlo experiment is conducted to evaluate the performances of these estimators in finite samples. Forecasting performances of the model are discussed. Application to a real data set shows the flexibility and potentiality of the new model.     

Using creative methods to research across difference. An introduction to the special issue

ABSTRACT

This special issue explores some of the methodological challenges that are brought into play when scholars deploy creative methods to research across difference. This introductory article defines what we mean by ‘creative methods’ and discusses some of the strengths and weaknesses of using this approach within social science research. It then outlines how creative methods can be used to research across difference, specifically, and introduces the seven articles that make up the special issue.     

Associations between Croatian Adolescents’ Use of Sexually Explicit Material and Risky Sexual Behavior: A Latent Growth Curve Modeling Approach

Objectives: The aim of this biobehavioral longitudinal study was to assess the association between sexually explicit material (SEM) use and risky sexual behavior among Croatian adolescents (n?=?577). Methods: The data were collected over the period of 15?months. Conditional dual-domain latent growth modeling was used. Results: Male adolescents’ initial SEM use, but not subsequent growth, was related to changes in sexual risk taking over the observed period. Among female adolescents, SEM use and sexual risk taking were significantly related only at baseline. Conclusions: Our findings point to gender-specific association between adolescents’ SEM use and risky sexual behavior.     

Predictors of Generative Action Among Adults in Two Transitional Countries

One of the widest elaborations of generativity today is the theoretical model proposed by McAdams and de St. Aubin. This model has not yet been tested completely, that is only some of its components and their relations have been tested. The main reasons for such an empirical status of the model are inadequately clear operationalizations of the components of the model. After our previous research, which include adaptation of scales for measuring of some key components of model, generative care and generative action (Lacković-Grgin et al., Suvremena Psihologija, 5, 9, 2002; Lacković-Grgin, Zbirka psihologijskih skala i upitnika, Zadar: University of Zadar, 2004; Tucak et al., Generativna briga i generativno djelovanje u odraslih osoba u Hrvatskoj i Sloveniji, XVII Dani Ramira i Zorana Bujasa, Summaries, 98, 2005), as well as operationalization of so called belief in species component (which is a component of Philosophy about human nature) (Ćubela Adorić et al., Philosophies of Human Nature in Adolescents and Adults, 7th Alps-Adria Conference in Psychology, Abstracts, 167, 2005), in this paper we have tried to evaluate life goals questionnaire. This questionnaire tried to measure the other component of the model—inner desire. In that way we could realize the main goal of this paper, research of how important are the evaluations in the prediction of generative action in Croatian and Slovenian adults. Generative action is under the strong influence of cultural demands and inner desires. There are more sociological and economical indications about the differences in expected social development in countries like Croatia and Slovenia. Because of the fact that in the last decade Slovenia has been developed more than Croatia, we could expect that this could also be manifested in assessment of importance of some areas of life, which are relevant for generative action (e.g., work, marriage, free time), for life goals of agency and communion, as well as for generative care as a possible predictor of generative action. The greater differences were obtained in some predictors of generative action (e.g. importance of job, importance of free time, goals of agency and communion), as well as in their predictive importance.     

Discontinuities in robust nonparametric regression with α-mixing dependence

The main idea of the paper is to introduce a robust regression estimation method under an α-mixing dependence assumption, staying free of any parametric model restrictions while also allowing for some sudden changes in the unknown regression function. The sudden changes in the model may correspond to discontinuity points (jumps) or higher order breaks (jumps in corresponding derivatives) as well. We firstly derive some important statistical properties for local polynomial M-smoother estimates and we will propose a statistical test to decide whether some given point of interest is significantly important for a change to occur or not. As the asymptotic distribution of the test statistic depends on quantities which are left unknown we also introduce a bootstrap algorithm which can be used to mimic the target distribution of interest. All necessary proofs are provided together with some experimental results from a simulation study and a real data example.     

Just how multi-level is leadership research? A document co-citation analysis 1980–2013 on leadership constructs and outcomes

The use of multi-level theories and methodologies in leadership has gained momentum in recent years. However, the leadership field still suffers from a fragmented and unclear evolution and practice of multi-level approaches. The questions of how and to what extent multi-level research has evolved in both leadership phenomena and leadership outcomes, and which informal research networks drove this evolution, remain vastly unexplored. In this study, the extent of literature published between 1980 and 2013 is analyzed using a document co-citation analysis and invisible colleges' framework. This allows us to map the evolution of the multi-level intellectual structure of the leadership field. Specifically, we identify a number of distinct colleges – their conceptualization of leadership and outcomes – and trace their evolution paths over thirty years. We find a considerable fragmentation of the field, with the usage of multi-level leadership conceptualization mostly embraced by more peripheral clusters. Finally we discuss implications for further research with regard to a set of distinct trajectories for the future evolution of multi-level approaches in the leadership domain.     

The Image of Ottomans in Croatian Historiography: Changing Narratives in Elementary School Textbooks in Croatia—1980s to 2000s

The author analyses the discourse on the Ottomans in Croatian history textbooks during the last decade of Socialist rule in the 1980s, the decade of nationalist revival in the 1990s and the decade of the normalization in 2000s and establishes the connections between dominant Croatian ideologies at that time, the historiography and the textbooks. The history textbooks in Croatia during the socialist period (1945–1990) in Yugoslavia continued the anti-Ottoman narrative defined as late as the end of nineteenth century by Croatian nationalist historiography. The discourse was mainly focused on the allegedly unfavourable economic position of Christians during the Ottoman rule and the common plight of Croats and other Southern Slavs. During the nationalistic period of the Franjo Tu?man regime in the 1990s the discourse in the history textbooks remained negative, concentrating on the damage that was inflicted by Ottoman expansion solely to Croatian nation, the state and Catholic faith. After the nationalist regime of Franjo Tu?man left power in 1999 and liberal democracy was finally introduced, Croatian textbooks started to present the Ottoman conquests in a more neutral language and Ottoman Muslim civilization received more nuanced treatment.     

COMMUNICATION AND COORDINATION IN A TWO‐STAGE GAME

We study the impact of communication on behavior in a two‐stage coordination game with asymmetric payoffs. We test experimentally whether individuals can avoid a head‐to‐head confrontation by means of coordinated strategies. In particular we analyze whether and how quickly a conflict‐avoidance take turn strategy can emerge. First, our results show that players learn to solve the conflict by choosing opposite options at both stages of the game. Second, many adopt a take turn strategy to sustain coordination over time and alleviate the inequality induced by the asymmetry of payoffs. Third, communication increases the likelihood of conflict resolution regardless of whether communication is unilateral or bilateral. (JEL C91, D74, L15, H71)     

Child Sexual Abuse News: A Systematic Review of Content Analysis Studies

Public knowledge and attitudes toward child sexual abuse are shaped through media depictions and coverage. Since the media are the main source of information about child sexual abuse, studies of child sexual abuse news can help us understand how news is created, how child sexual abuse is presented to the public, and what is the possible impact of such presentation and coverage on the audience. A systematic review of content analysis research is conducted using predefined criteria in order to identify quality studies, main findings, research gaps and to develop recommendations for future studies. International databases were systematically searched using keywords in September 2017. A total of 24 original quantitative content analysis studies published in the English language were included in the review and evaluated according to research methodology. The framework of child sexual abuse news media studies is developed and main findings are highlighted: (1) presentation and coverage of child sexual abuse (n = 7); (2) prevalence of coverage of CSA cases reported to the authorities (n = 2); (3) presentation and coverage of child abuse and sexual crimes where child sexual abuse is only a subtopic (n = 9); (4) presentation and coverage of specific child sexual abuse cases or issues (n = 6). Although studies represent valuable contribution, most did not meet content analysis design and reporting standards or both (e.g., calculating intercoder reliability), which seriously compromises validity and replicability requirements. Recommendation for future studies and most common errors in conducting content analysis are emphasized.