Pub Date : 2019-12-15DOI: 10.1285/I20705948V12N4P774
V. Genova, M. Tumminello, M. Enea, F. Aiello, M. Attanasio
The Italian public universities are subsidised within a competitive framework that awards excellence, efficiency, and the capacity of universities to attract students from Italian regions other than its own. However, repeated cuts to public spending has increased the well-known Italian North-South divide. The most important student mobility (SM) flow is from the Southern to the Central-Northern regions--a phenomenon that has been magnified by an increasing number of outgoing students from Sicily over the last decade. In this paper, we rely upon micro-data of university enrolment and students' personal records for three cohorts of freshmen, in order to investigate preferential patterns of SM from Sicily toward universities in other regions. Indeed, our main goal is to eventually reveal the existence of chain migrations, through which students from a particular geographical area move towards a particular destination. We consider 38 clusters aggregating the 390 Sicilian municipalities, based on geographical proximity and socio-economic criteria. The data from each cohort is represented as a tripartite network with three sets of nodes, namely, clusters of Sicilian municipalities, students, and universities. The tripartite network is projected in a bipartite weighted network of clusters and universities, which is, then, filtered, in order to obtain a statistically validated bipartite network (SBVN). The SBVNs of the three cohorts suggest the existence and evolution of chain migration patterns over time, which are also gender specific.
{"title":"Student mobility in higher education: Sicilian outflow network and chain migrations","authors":"V. Genova, M. Tumminello, M. Enea, F. Aiello, M. Attanasio","doi":"10.1285/I20705948V12N4P774","DOIUrl":"https://doi.org/10.1285/I20705948V12N4P774","url":null,"abstract":"The Italian public universities are subsidised within a competitive framework that awards excellence, efficiency, and the capacity of universities to attract students from Italian regions other than its own. However, repeated cuts to public spending has increased the well-known Italian North-South divide. The most important student mobility (SM) flow is from the Southern to the Central-Northern regions--a phenomenon that has been magnified by an increasing number of outgoing students from Sicily over the last decade. In this paper, we rely upon micro-data of university enrolment and students' personal records for three cohorts of freshmen, in order to investigate preferential patterns of SM from Sicily toward universities in other regions. Indeed, our main goal is to eventually reveal the existence of chain migrations, through which students from a particular geographical area move towards a particular destination. We consider 38 clusters aggregating the 390 Sicilian municipalities, based on geographical proximity and socio-economic criteria. The data from each cohort is represented as a tripartite network with three sets of nodes, namely, clusters of Sicilian municipalities, students, and universities. The tripartite network is projected in a bipartite weighted network of clusters and universities, which is, then, filtered, in order to obtain a statistically validated bipartite network (SBVN). The SBVNs of the three cohorts suggest the existence and evolution of chain migration patterns over time, which are also gender specific.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"774-800"},"PeriodicalIF":0.7,"publicationDate":"2019-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N4P774","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44379178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-15DOI: 10.1285/I20705948V12N4P720
F. Signore, A. Catalano, E. Carlo, Andreina Madaro, Emanuela Ingusci
In the current socio-economic scenario, affected by constant changes inthe labor market, employability found greater echo. Universities frequently adopt strategies aimed at improving the employability and usefulness of theareas of competence, motivation and interests of young graduates and workers. In this study a preliminary research was conducted on a sample of 84 university students who attended a consulting service at the University of Salento, the Career Service Office. The average age of the sample was 26.74 years (DS = 4.95), 63% women, 71.4% unemployed. The tool used was a questionnaire-interview. The aim of this research was to assess the role of employability and its influence on personal variables and active work behaviours, as job searching activities. Analyses were conducted through PLS-PM technique, a non-parametrical SEM modeling, and demonstrated that employability affects job search and personal efficacy, while personal efficacy had a non signicant relation with job search behaviours.
{"title":"The role of employability in students during academic experience: a preliminary study through PLS-PM technique","authors":"F. Signore, A. Catalano, E. Carlo, Andreina Madaro, Emanuela Ingusci","doi":"10.1285/I20705948V12N4P720","DOIUrl":"https://doi.org/10.1285/I20705948V12N4P720","url":null,"abstract":"In the current socio-economic scenario, affected by constant changes inthe labor market, employability found greater echo. Universities frequently adopt strategies aimed at improving the employability and usefulness of theareas of competence, motivation and interests of young graduates and workers. In this study a preliminary research was conducted on a sample of 84 university students who attended a consulting service at the University of Salento, the Career Service Office. The average age of the sample was 26.74 years (DS = 4.95), 63% women, 71.4% unemployed. The tool used was a questionnaire-interview. The aim of this research was to assess the role of employability and its influence on personal variables and active work behaviours, as job searching activities. Analyses were conducted through PLS-PM technique, a non-parametrical SEM modeling, and demonstrated that employability affects job search and personal efficacy, while personal efficacy had a non signicant relation with job search behaviours.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"720-747"},"PeriodicalIF":0.7,"publicationDate":"2019-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N4P720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48693467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-15DOI: 10.1285/I20705948V12N4P748
Gabriele Ruiu, N. Fadda, A. Ezza, Massimo Esposito
Migration is a permanent phenomenon rooted in history and recently involves high-skilled workers (HSWs). Among them, a crucial role is played by PhDs. HSWs face the risk to not find a job matching their skills and they can opt to accept to be overeducated for the job or move to another country or region. Mobility of HSW can be interpreted as a positive issue that can help to match jobs and skills. However, the emergence of a clear path between areas of countries or regions (e.g. from south to north Italy) highlights the risks of a drain of human capital from areas with low development to more developed ones. In this paper, we focus on a category of HSWs who have been almost neglected by the literature, the PhDs. The aim of the paper is to shed light on the mobility pattern of Italian PhDs, paying attention to PhDs from Southern Italy. This aim will be pursued by using microdata from the 2014 ISTAT Survey on the professional conditions of Italian PhDs at 4 and 6 years after the end of their studies.This work highlights that Southern PhDs have higher probability to move to other area of the countries, while Northern PhDs seem to prefer to move abroad thus confirming previous studies which identified a similar pattern for graduates. While the Northern part of the country compensate the drain of human capital with the mobility from the other part of Italy, the Southern face a relevant drain of ‘talents’.
{"title":"An investigation of mobility of Italian Ph. Doctors","authors":"Gabriele Ruiu, N. Fadda, A. Ezza, Massimo Esposito","doi":"10.1285/I20705948V12N4P748","DOIUrl":"https://doi.org/10.1285/I20705948V12N4P748","url":null,"abstract":"Migration is a permanent phenomenon rooted in history and recently involves high-skilled workers (HSWs). Among them, a crucial role is played by PhDs. HSWs face the risk to not find a job matching their skills and they can opt to accept to be overeducated for the job or move to another country or region. Mobility of HSW can be interpreted as a positive issue that can help to match jobs and skills. However, the emergence of a clear path between areas of countries or regions (e.g. from south to north Italy) highlights the risks of a drain of human capital from areas with low development to more developed ones. In this paper, we focus on a category of HSWs who have been almost neglected by the literature, the PhDs. The aim of the paper is to shed light on the mobility pattern of Italian PhDs, paying attention to PhDs from Southern Italy. This aim will be pursued by using microdata from the 2014 ISTAT Survey on the professional conditions of Italian PhDs at 4 and 6 years after the end of their studies.This work highlights that Southern PhDs have higher probability to move to other area of the countries, while Northern PhDs seem to prefer to move abroad thus confirming previous studies which identified a similar pattern for graduates. While the Northern part of the country compensate the drain of human capital with the mobility from the other part of Italy, the Southern face a relevant drain of ‘talents’.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"748-773"},"PeriodicalIF":0.7,"publicationDate":"2019-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N4P748","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41359635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P674
K. SureshChandra, S. Prabhakaran
Forecasting is an important exercise in Time series analysis. For a statio-nary time series, there are theoretically strong forecasting methods which canprovide most accurate forecasts for the future (Karlin and Taylor (1975)).For most non stationary time series Box Jenkins methodology is a usefulforecasting technique. Essentially, the Box Jenkins methodology assumesthat any non stationarity time series can be conveniently modeled as anAutoregressive Intregrated Moving Averages (ARIMA) model with sucientnumber of unit roots in the linear stochastic dierence equation generatingthe time series. The non stationarity in such time series is then removed bysuccessively dierencing of the series until one obtains a stationary series,for which optimal forecasts can be computed. The forecasts for the originalseries are then computed by `inverting' the dierence operators that wereused ( Makridakis et al. (1998)) on the forecasts computed for the statio-nary series. The main objective of this study is to demonstrate that the BoxJenkins methodology is not useful, especially in large time series, when thenon stationarity in the time series is due to `explosive' roots. An alternativemethod is proposed in such a situation and its performance is assessed bothon a simulated as well as on a real life data.
预测是时间序列分析中的一项重要工作。对于一个平稳的时间序列，有理论上强大的预测方法，可以提供最准确的预测未来(Karlin和Taylor(1975))。对于大多数非平稳时间序列，Box Jenkins方法是一种有用的预测技术。从本质上讲，Box Jenkins方法假设任何非平稳时间序列都可以方便地建模为自回归积分移动平均(ARIMA)模型，该模型具有线性随机差分方程中产生时间序列的单位根的数量。然后通过序列的连续差分去除这些时间序列中的非平稳性，直到得到一个平稳序列，从而可以计算出最优的预测。原始序列的预测然后通过“反转”对静态序列计算的预测所使用的差分算子(Makridakis et al.(1998))来计算。本研究的主要目的是证明BoxJenkins方法是无用的，特别是在大时间序列中，当时间序列的非平稳性是由于“爆炸”根时。在这种情况下，提出了一种替代方法，并对其性能进行了模拟和实际数据的评估。
{"title":"Forecasting an explosive time series","authors":"K. SureshChandra, S. Prabhakaran","doi":"10.1285/I20705948V12N3P674","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P674","url":null,"abstract":"Forecasting is an important exercise in Time series analysis. For a statio-nary time series, there are theoretically strong forecasting methods which canprovide most accurate forecasts for the future (Karlin and Taylor (1975)).For most non stationary time series Box Jenkins methodology is a usefulforecasting technique. Essentially, the Box Jenkins methodology assumesthat any non stationarity time series can be conveniently modeled as anAutoregressive Intregrated Moving Averages (ARIMA) model with sucientnumber of unit roots in the linear stochastic dierence equation generatingthe time series. The non stationarity in such time series is then removed bysuccessively dierencing of the series until one obtains a stationary series,for which optimal forecasts can be computed. The forecasts for the originalseries are then computed by `inverting' the dierence operators that wereused ( Makridakis et al. (1998)) on the forecasts computed for the statio-nary series. The main objective of this study is to demonstrate that the BoxJenkins methodology is not useful, especially in large time series, when thenon stationarity in the time series is due to `explosive' roots. An alternativemethod is proposed in such a situation and its performance is assessed bothon a simulated as well as on a real life data.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"674-690"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N3P674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42089196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P705
J. Subramani
The present paper deals with the linear systematic sampling with unequal sampling intervals in the presence of linear trend among the population values. As a result, explicit expressions for the linear systematic sample means with different random starts in a labelled population with linear trend for a pre-assigned fixed sample size and the population size together its variance are obtained. The efficiencies of the proposed linear systematic sampling with that of simple random sampling without replacement, linear systematic sampling and diagonal systematic sampling schemes are assessed algebraically and also for certain natural populations. It is observed that the proposed linear systematic sampling performs better than the sampling schemes mentioned above.
{"title":"Linear Systematic Sampling with Unequal Sampling Intervals in the Presence of Linear Trend","authors":"J. Subramani","doi":"10.1285/I20705948V12N3P705","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P705","url":null,"abstract":"The present paper deals with the linear systematic sampling with unequal sampling intervals in the presence of linear trend among the population values. As a result, explicit expressions for the linear systematic sample means with different random starts in a labelled population with linear trend for a pre-assigned fixed sample size and the population size together its variance are obtained. The efficiencies of the proposed linear systematic sampling with that of simple random sampling without replacement, linear systematic sampling and diagonal systematic sampling schemes are assessed algebraically and also for certain natural populations. It is observed that the proposed linear systematic sampling performs better than the sampling schemes mentioned above.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"705-719"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N3P705","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45033657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P619
Rola M. Musleh, Amal Helu, H. Samawi
In this article we consider the estimation of the stress-strength reliability parameter, R = P(X < Y ) when the stress (X) and the strength (Y ) are dependent random variables distributed as bivariate Lomax model. The maximum likelihood, moment and Bayes estimators are derived. We obtained Bayes estimators using symmetric and asymmetric loss functions via squared error loss and Linex loss functions respectively. Since there are no closed forms for the Bayes estimators, we used an approximation based on Lindley's method to obtain Bayes estimators under these loss functions. An extensive computer simulation is used to compare the performance of the proposed estimators using three criteria, namely, relative bias, mean squared error and Pitman nearness (PN) probability. Real data application is provided to illustrate the performance of our proposed estimators.
{"title":"Inference on P(X less than Y) in bivariate Lomax model","authors":"Rola M. Musleh, Amal Helu, H. Samawi","doi":"10.1285/I20705948V12N3P619","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P619","url":null,"abstract":"In this article we consider the estimation of the stress-strength reliability parameter, R = P(X < Y ) when the stress (X) and the strength (Y ) are dependent random variables distributed as bivariate Lomax model. The maximum likelihood, moment and Bayes estimators are derived. We obtained Bayes estimators using symmetric and asymmetric loss functions via squared error loss and Linex loss functions respectively. Since there are no closed forms for the Bayes estimators, we used an approximation based on Lindley's method to obtain Bayes estimators under these loss functions. An extensive computer simulation is used to compare the performance of the proposed estimators using three criteria, namely, relative bias, mean squared error and Pitman nearness (PN) probability. Real data application is provided to illustrate the performance of our proposed estimators.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"619-636"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N3P619","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43065586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P657
Norin Rahayu Shamsuddin, N. Mahat
Over the past 50 years, extensive research have been carried out to understand how clustering work in classifying data into meaningful groups. Various clustering algorithms and cluster validity indexes have been proposedand improvised to obtain the best clustering result. However, there is noclustering method that is able to give consistent results on similar structureof a dataset. An alternative mechanism to control the variation of resultsand improved the quality of traditional clustering is through consensus clustering. In this paper, we generate multiple partitions of consensus clusteringthrough a resampling method by employing q-fold cross-validation approach.q-fold cross-validation approach is able to speed-up the consensus partitionsprocedure with qth iterations. To encounter with different number of cluster labels occur in the partitions, we employed voting-based method in the second stage of consensus clustering to obtain optimal consensus partition.The performance of optimal consensus partitions is evaluated from Silhouetteplot
{"title":"Voting-based Approach in Consensus Clustering through q-fold cross-validation","authors":"Norin Rahayu Shamsuddin, N. Mahat","doi":"10.1285/I20705948V12N3P657","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P657","url":null,"abstract":"Over the past 50 years, extensive research have been carried out to understand how clustering work in classifying data into meaningful groups. Various clustering algorithms and cluster validity indexes have been proposedand improvised to obtain the best clustering result. However, there is noclustering method that is able to give consistent results on similar structureof a dataset. An alternative mechanism to control the variation of resultsand improved the quality of traditional clustering is through consensus clustering. In this paper, we generate multiple partitions of consensus clusteringthrough a resampling method by employing q-fold cross-validation approach.q-fold cross-validation approach is able to speed-up the consensus partitionsprocedure with qth iterations. To encounter with different number of cluster labels occur in the partitions, we employed voting-based method in the second stage of consensus clustering to obtain optimal consensus partition.The performance of optimal consensus partitions is evaluated from Silhouetteplot","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41650528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P604
S. Gubbi, Srikanth R. Seshadri, V. Kumara, K. SureshChandra
Understanding population parameters are important tools for wildlife management, and one of the key objectives of the ecological research. Motion sensor cameras are a widely used tool to estimate abundance and densities of species that are identifiable based on the natural markings on their bodies. Though camera trapping provides information such as count data, on species that are not individually identifiable, estimating population size using conventional capture-recapture methodologies is not possible hindering estimating population information of several wildlife species. However, recent methodologies help use camera trapping data to bridge this gap. Here we extend the model of Chandler and Royle (2013), with suitable modifications, and used camera trap detection data to estimate abundance and density of eight wild-prey, and five domestic prey species of leopards ( Panthera pardus fusca ). In this context, a new procedure has been proposed, based on grouping of the count data, which is useful in cases of large encounters. The current model should apply widely to a range of other unmarked wildlife species such as dholes, lions, golden jackal, Indian fox, ratel, to name a few, that could help understand prey-predator relationships, competition, trophic interactions, species interactions and other similar ecological questions. The methodology could also reduce costs, and maximise the utilisation of existing camera trapping data. The methodology helps understanding population parameters of several endangered, unmarked species to draw up conservation strategies whose estimates are currently largely based on educational guess.
{"title":"Counting the unmarked: Estimating animal population using count data","authors":"S. Gubbi, Srikanth R. Seshadri, V. Kumara, K. SureshChandra","doi":"10.1285/I20705948V12N3P604","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P604","url":null,"abstract":"Understanding population parameters are important tools for wildlife management, and one of the key objectives of the ecological research. Motion sensor cameras are a widely used tool to estimate abundance and densities of species that are identifiable based on the natural markings on their bodies. Though camera trapping provides information such as count data, on species that are not individually identifiable, estimating population size using conventional capture-recapture methodologies is not possible hindering estimating population information of several wildlife species. However, recent methodologies help use camera trapping data to bridge this gap. Here we extend the model of Chandler and Royle (2013), with suitable modifications, and used camera trap detection data to estimate abundance and density of eight wild-prey, and five domestic prey species of leopards ( Panthera pardus fusca ). In this context, a new procedure has been proposed, based on grouping of the count data, which is useful in cases of large encounters. The current model should apply widely to a range of other unmarked wildlife species such as dholes, lions, golden jackal, Indian fox, ratel, to name a few, that could help understand prey-predator relationships, competition, trophic interactions, species interactions and other similar ecological questions. The methodology could also reduce costs, and maximise the utilisation of existing camera trapping data. The methodology helps understanding population parameters of several endangered, unmarked species to draw up conservation strategies whose estimates are currently largely based on educational guess.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"604-618"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N3P604","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42035495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P691
S. Harini, M. Subbiah, M. R. Srinivasan, M. Gallo
Length of stay in hospitals are mostly characterized as asymmetric, right skewed and leptokurtic in nature. Earlier studies have considered parametric distributions like gamma, Pareto, lognormal for studying length of stay of patients in hospitals. However, in this study we have proposed transformed distributions to be the best choice for characterizing the length of stay. For this study, we have considered paediatric asthma dataset and identified that transformed Weibull-Pareto as the best fit. For a comparative purpose we have also provided the results of gamma, lognormal, and Pareto distribution. Maximum likelihood approach is considered to estimate the unknown parameters of the Transformed distribution followed by goodness of fit tests to examine the suitability of the fitted distributions. The results provide a direction for modelling the length of stay in hospitals due to different medical problems which require hospitalization.
{"title":"An Application of Transformed Distribution: Length of Stay in Hospitals","authors":"S. Harini, M. Subbiah, M. R. Srinivasan, M. Gallo","doi":"10.1285/I20705948V12N3P691","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P691","url":null,"abstract":"Length of stay in hospitals are mostly characterized as asymmetric, right skewed and leptokurtic in nature. Earlier studies have considered parametric distributions like gamma, Pareto, lognormal for studying length of stay of patients in hospitals. However, in this study we have proposed transformed distributions to be the best choice for characterizing the length of stay. For this study, we have considered paediatric asthma dataset and identified that transformed Weibull-Pareto as the best fit. For a comparative purpose we have also provided the results of gamma, lognormal, and Pareto distribution. Maximum likelihood approach is considered to estimate the unknown parameters of the Transformed distribution followed by goodness of fit tests to examine the suitability of the fitted distributions. The results provide a direction for modelling the length of stay in hospitals due to different medical problems which require hospitalization.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"691-704"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1285/I20705948V12N3P691","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44893135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.1285/I20705948V12N3P637
P. Sarnacchiaro, S. Scippacercola, Pasqualina Malafronte
Job Satisfaction is a set of favorable or unfavorable feelings and emotions linked to how employees view their work environment, and supervisors need to be attentive to employee satisfaction levels. If employees are not satisfied with their jobs, the overall progress of the entire system is affected. This paper reports on a teacher job satisfaction study that examined a sample of 362 teachers. The Common Assessment Framework & Education questionnaire was used to collect data. The aim of the study is to identify, by a Structural equation model, the factors that most influence Job Satisfaction taking into account age, total years of service and gender. The results underlines a significant difference between male/female in Job Satisfaction model.
{"title":"A Statistical Model for the Self-evaluation of Teacher Satisfaction in School Management: a Study in the Italian Secondary School","authors":"P. Sarnacchiaro, S. Scippacercola, Pasqualina Malafronte","doi":"10.1285/I20705948V12N3P637","DOIUrl":"https://doi.org/10.1285/I20705948V12N3P637","url":null,"abstract":"Job Satisfaction is a set of favorable or unfavorable feelings and emotions linked to how employees view their work environment, and supervisors need to be attentive to employee satisfaction levels. If employees are not satisfied with their jobs, the overall progress of the entire system is affected. This paper reports on a teacher job satisfaction study that examined a sample of 362 teachers. The Common Assessment Framework & Education questionnaire was used to collect data. The aim of the study is to identify, by a Structural equation model, the factors that most influence Job Satisfaction taking into account age, total years of service and gender. The results underlines a significant difference between male/female in Job Satisfaction model.","PeriodicalId":44770,"journal":{"name":"Electronic Journal of Applied Statistical Analysis","volume":"12 1","pages":"637-656"},"PeriodicalIF":0.7,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43273063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：