Studying hurricane preparedness among the Resident Assistants (RAs) and Residence Life Coordinators (RLCs) at Louisiana State University (LSU) is imperative to assure that the university housing staff is fully equipped when faced with an oncoming threat. This study seeks to fill a gap in research by investigating the influences of preparedness on student housing employees. A survey was developed and the measures were found to be coherent and internally reliable through the use of factor analysis. Based on theory and previous literature, a linear regression model was developed that quantified the relationship between the independent variable of preparedness and general knowledge, past experience, preparation anxiety, threat anxiety, amount of time as a housing employee, amount of time living in Baton Rouge, location of primary address, gender, ethnicity, and car access. Only general knowledge and preparation anxiety were found to influence the preparedness construct significantly (at the 5 percent level). Demographic factors did not influence hurricane preparedness levels of housing staff employees. Results suggest that the university acts as a buffer to student populations from typical vulnerabilities that the regular population experiences in disaster scenarios. This research could be applicable to other university housing staff employees who work at a university that may be frequently impacted by hurricanes.

The abilities of life insurers can be divided and measured from various aspects. Through the use of structural equation modeling, we investigate the relations among solvency, operation ability and profitability in year 1994, 1995 and 1996. After within-year analysis and longitudinal data analysis, we found that operation ability has a positive influence on the size and income of life insurers and has a slight negative effect on the return on capital during these years. While the effect of solvency, asset risk and product risk on return on capital is not significant. / text

No description available.

In the master work there is a scientific problem raised and worked out: what are application possibilities of one factor method analysis and how this statistic method could be used to ascertain six class pupils‘ mathematical achievements at secondary school in Lithuania. The aim of this work is to establish applying one factor analysis the main factors, which destine mathematical achievements and taking them into consideration to make conclusions and recomendations how those achievements to improve. To achieve this aim there are such tasks raised, as to analyse the quality possibilities and exactness of one factor method by establishing the factors destined by mathematical achievements, to estimate exterior and interior factors on which depend mathematical achievements and to present conclusions and recomendation. By analysing and generalizing scientific literature and statistical data it was established that one factor analysis is good to process for ranked data, when the variable of sample are independable and they are distributed according to normal law and their dispersion are similar (do not differ more than three times) this method allowed the indications of measured objects to change by a smaller number of generalizing indications without losing its main information. By investigating the mathematical achievements of six – grade pupil‘s statistically significant differences according to ANOVA method it was estasblished, that the factors which destine it are the... [to full text]

Model-based clustering allows for the identification of subgroups in a data set through the use of finite mixture models. When applied to high-dimensional microarray data, we can discover groups of genes characterized by their gene expression profiles. In this thesis, a mixture of skew-t factor analyzers is introduced for the clustering of high-dimensional data. Notably, we make use of a version of the skew-t distribution which has not previously appeared in mixture-modelling literature. Allowing a constraint on the factor loading matrix leads to two mixtures of skew-t factor analyzers models. These models are implemented using the alternating expectation-conditional maximization algorithm for parameter estimation with an Aitken's acceleration stopping criterion used to determine convergence. The Bayesian information criterion is used for model selection and the performance of each model is assessed using the adjusted Rand index. The models are applied to both real and simulated data, obtaining clustering results which are equivalent or superior to those of established clustering methods.

The Chinese insurance industry has been growing substantially, and this provides a motivation to examine the insurance market in China. This study used survey data to identify key determinants related to Chinese consumers’ ownership of life insurance, by using a probit model. The results revealed that several groups of variables influence Chinese consumers’ life insurance purchases, including knowledge and trust, consumer profile and investment preferences, importance of product attributes, and socio-demographics. Also, this study applied factor analysis to investigate factors that are important for Chinese consumers regarding life insurance. Factor analysis results indicated that four factors are identified including importance of product attributes, consumers’ financial strength, consumers’ attitude and trust toward the life insurance industry, and consumer attributes. Lastly, to better understand Chinese consumers regarding life insurance, consumers were segmented into three main groups through applying cluster analysis. Each cluster shows distinct differences in purchasing criteria and socio-demographic characteristics.

Ethnic identity is a significant psychological variable for the study of African Americans in the United States and often associated with psychological health. However, the nature of this relationship is sometimes unclear. One reason for the confusion may be that ethnic identity is often confounded with acculturation as they are sometimes used interchangeably in research. Because of this confounding problem, it is not clear whether the relationship between ethnic identity and psychological health is really a reflection of ethnic identity or of ethnic identity confounded with acculturation. Thus, the aim of this study was to use factor analysis to separate ethnic identity and acculturation at the measurement level and examine the unique impact of each on both positive and negative psychosocial functioning among African Americans. Two ethnic identity measures (MEIM and the MIBI) and two acculturation measures (AfAAS and the MASPAD) were administered to 173 (65 males and 118 females) African American students attending a historically Black university (mean age = 21, SD = 2.7). The 96 items from these measures were factor analyzed using principal components analysis. Findings support the hypothesis of confounding in existing measures. However, results indicate that acculturation and ethnic identity are differentiable at the item level and are multidimensional. Eight internally reliable factors emerged representing different dimensions of these constructs. Three of the factors (ethnic pride, ethnic belonging, and public regard) were consistent with existing definitions of ethnic identity. The remaining five factors (out-group comfort, in-group rejection, assimilationist ideology, traditional behaviors/beliefs, and in-group preference) were consistent with the bi-dimensional definition of acculturation. These ethnic identity and acculturation factors predicted some outcomes similarly but differentially predicted others. Several implications follow from this study. First, in order to better understand the relationship between ethnic identity and psychosocial functioning, researchers need to use measures that are not confounded with other related but different constructs. Future research should focus on the dimension level rather than the overall construct level. Focusing more narrowly on the dimension level may produce research that can more accurately inform interventions with African Americans.

The postmodern ultra-competitive global marketplace makes it difficult for companies to hold on to customers. This is especially true for industries that are driven by commodity products, and the South African fertilizer industry is not excluded from this statement. It is therefore important that companies not only operate to create loyal customers, but also increase and maintain a high level of engagement with their customers. This study measures customer engagement for a South African fertilizer company. In doing so, the study makes use, firstly, of a proposed customer engagement model, secondly, a customer engagement questionnaire and, thirdly, factor analysis as a statistical tool to identify the underlying construct embedded within the data. The results show that only five factors Trust, Involvement, Integrity, Repurchase and Loyalty are antecedents for customer engagement. These factors explain 76% of the variance. Furthermore, it is important to note that all the antecedents were regarded as important by the respondents, and all but one exceed the required 75% level of excellence. The data were tested for reliability and showed excellent reliability in excess of 0.90, as measured by Cronbach alpha. The main finding of the study is that a new model for customer engagement in the fertilizer industry is proposed. This model can be used by future researchers in the fertilizer industry, as well as other agriculture related industries. / MBA, North-West University, Potchefstroom Campus, 2014

The postmodern ultra-competitive global marketplace makes it difficult for companies to hold on to customers. This is especially true for industries that are driven by commodity products, and the South African fertilizer industry is not excluded from this statement. It is therefore important that companies not only operate to create loyal customers, but also increase and maintain a high level of engagement with their customers. This study measures customer engagement for a South African fertilizer company. In doing so, the study makes use, firstly, of a proposed customer engagement model, secondly, a customer engagement questionnaire and, thirdly, factor analysis as a statistical tool to identify the underlying construct embedded within the data. The results show that only five factors Trust, Involvement, Integrity, Repurchase and Loyalty are antecedents for customer engagement. These factors explain 76% of the variance. Furthermore, it is important to note that all the antecedents were regarded as important by the respondents, and all but one exceed the required 75% level of excellence. The data were tested for reliability and showed excellent reliability in excess of 0.90, as measured by Cronbach alpha. The main finding of the study is that a new model for customer engagement in the fertilizer industry is proposed. This model can be used by future researchers in the fertilizer industry, as well as other agriculture related industries. / MBA, North-West University, Potchefstroom Campus, 2014

This study researches the topic customer service of convenience sores. Two objectives are set, namely to measure the customer service levels of convenience stores, and then to determine if any differences exist between customer perceptions and customer expectations. The literature review covers two models of service quality, namely the Kano model and the SERVQUAL model. Both the Kano model and the SERVQUAL model are client service models that currently exist in practice. The Kano model provides insights into the dynamics of customer preferences and their needs, which ensures the delivery of successful products and services. The SERVQUAL method is a technique that can be used for performing a gap analysis of an organisation's service quality performance against customer service quality needs. Because of SERVQUAL's strong empirically based methodology and popularity amongst services organisations who aims to improve their service quality, SERVQUAL is the research methodology of choice. The empirical research was done by collecting primary data from a selected group, using the SERVQUAL questionnaire to measure customer expectation and customer perception. The sample size is 65 respondents, and they all responded by completing the structured SERVQUAL questionnaires. A seven-point Likert scale was used in the questionnaire. A "1" was labelled as "strongly disagree" while a "7" was labelled as "strongly agree". The reliability of the data was confirmed by means of Cronbach alpha and a-values of 0.879 (customers' perceptions) and 0.906 (customers' expectations) showed satisfactory reliability. Descriptive statistical analysis was used to calculate mean values of the criteria while principle factor analyses were employed to extract factors from both groups of data. The factors pertaining to the perceived service has been identified as Employee Mind-Set (explaining the variance of 29.72%), Excellent Service (19.14%) and Display (8.92%). Regarding the factor analysis of the expected levels of service, the factors identified are: Employee Mindset (35.78%), Service Reputation (25.22%) and Transactions (5.90%). From the research it became evident that the three major recommendations to managers of convenience stores who aims to improve their service quality are managerial actions focussed at: *Internal training. *Induction programmes *Surveys (further research and monitoring). / Thesis (M.B.A.)--North-West University, Potchefstroom Campus, 2009.