Categorical data analysis

This study examines the impact of wages on productivity by examining US domestic airlines. Current literature places emphasis on jobs conducted in-flight, specifically pilots and cabin crew. This paper considers all job titles involved in the operations of the airline, including executives and management. Existing research focuses on factors such as governance, domestic economic level, and personal attributes such as intrinsic motivation, gender, and age. There is insufficient research regarding the relationship between wage and productivity. Thus, it is uncertain if high wage leads to high productivity. Preliminary findings suggest higher wage equates to higher productivity.

At heart every trader loves volatility; this is where return on investment comes from, this is what drives the proverbial "positive alpha." As a trader, understanding the probabilities related to the volatility of prices is key, however if you could also predict future prices with reliability the world would be your oyster. To this end, I have achieved three goals with this dissertation, to develop a model to predict future short term prices (direction and magnitude), to effectively test this by generating consistent profits utilizing a trading model developed for this purpose, and to write a paper that anyone with basic knowledge of markets and finance can readily understand. To address my first goal a well-quoted and tradable asset was required. To create a model that traders can use to make money it needed to be volatile with significant short and longer-term price swings. After some analysis, a review of macroeconomic impacts, and drawing in some part on experience, oil emerged as a fitting test, in particular Brent Crude Oil. For simplicity, and to further my third goal, "Oil" as used within this paper will represent Brent Crude Oil unless otherwise specified. While some dissertations and other scholarly works set out to discern theoretical truths this dissertation is much simpler, this is all about the money. Though I am certainly interested, as I am sure many traders are, in discovering the "Holy Grail" of how to trade any type of asset, the scope of my analysis will be confined to Brent Crude Oil prices within a sampling period of January 2002 thru May 2016. The findings indicate that there are factors that are predictive of Table of Contents Abstract .

Crosses were made between Fanny (highly susceptible to blast) and 11 cultivars differing in blast resistance. Using the pedigree method (PM) segregating generations were evaluated and selected for blast resistance. Via anther culture (AC), doubled-haploids were obtained from F 1 plants and from F 2 blast-susceptible plants. Pedigree and anther culture-derived lines were planted together and evaluated for blast resistance under rainfed conditions at the Santa Rosa Experiment Station, Villavicencio, Colombia. The principal objective was to compare PM and AC in terms of their efficiency in producing rice lines resistant to blast. Results of a stratified analysis showed an association between method and blast resistance. Results of the logit-model analysis showed that AC produced a significantly (P=0.0001) higher proportion of lines with initial blast resistance (leaf-and neck-blast reaction <4) than did PM across all cross types. Stable blast resistance was assessed based on field performance over 3 years. AC was superior to PM in generating stable resistance for only some cross types. Consequently, with a few exceptions, AC can be used as effectively as PM to develop rice cultivars resistant to blast, with savings in time and labor. Additionally, blast-resistant lines were obtained either by the pedigree method or by anther culture from crosses between blast-susceptible cultivars (Fanny/CICA4 and Fanny/Colombia 1). This excludes somaclonal variation as a possible mechanism responsible for this resistance and suggests that a recombination of minor genes could have occurred and was fixed through either method. However, the stability of the resistance was greater in pedigree-derived lines. The implications of these findings for rice blast-resistance breeding are discussed.

Computer viruses pose an increasing risk to computer data integrity. They cause loss of valuable data and cost an enormous amount in wasted effort in restoration/duplication of lost and damaged data. Each month many new viruses are reported. As the problem of viruses increases, we need tools to detect them and to eradicate them from our systems. This paper describes a virus detection tool: a generic virus scanner in C ++ with no inherent limitations on the file systems, file types, or host architectures that can be scanned. The tool is completely general and is structured in such a way that it can easily be augmented to recognize viruses across different system platforms with varied file types. The implementation defines an abstract C ++ class, VirInfo, which encapsulates virus features common to all scannable viruses. Subclasses of this abstract class may be used to define viruses that infect different machines and operating systems. The generality of the mechanism allows it to be used for other forms of scanning as well.

Cortical abnormalities are considered a neurobiological characteristic of schizophrenia. However, the pattern of such deficits as they progress over the illness remains poorly understood. The goal of this project was to assess the progression of cortical thinning in frontal and temporal cortical regions in schizophrenia, and determine whether relationships exist between them and neuropsychological and clinical symptom profiles. As part of a larger longitudinal 2-year follow-up study, schizophrenia (n=20) and healthy participants (n=20) group-matched for age, gender, and recent-alcohol use, were selected. Using MRI, estimates of gray matter thickness were derived from primary anatomical gyri of the frontal and temporal lobes using surface-based algorithms. These values were entered into repeated-measures analysis of variance models to determine group status and time effects. Change values in cortical regions were correlated with changes in neuropsychological functioning and clinical ...

In particular engineering applications, such as reliability engineering, complex types of data are encountered which require novel methods of statistical analysis. Handling covariates properly while managing the missing values is a challenging task. These type of issues happen frequently in reliability data analysis. Specifically, accelerated life testing (ALT) data are usually conducted by exposing test units of a product to severer-than-normal conditions to expedite the failure process. The resulting lifetime and/or censoring data are often modeled by a probability distribution along with a life-stress relationship. However, if the probability distribution and life-stress relationship selected cannot adequately describe the underlying failure process, the resulting reliability prediction will be misleading. To seek new mathematical and statistical tools to facilitate the modeling of such data, a critical question to be asked is: Can we find a family of versatile probability distri...

Background: In the past years, there has been a growing concern in designing physical activity (PA) programmes for elderly people, because evidence suggests that such health promotion interventions may reduce the deleterious effects of the ageing process. Quality is an important issue when designing a PA programme for older people. Some studies support the Excellence Model of the European Foundation for Quality Management (EFQM) as an operational framework for evaluating the quality of an organization. Within this context, the aim of this study was to characterize the quality management models of the PA programmes developed by Portuguese Local Administration to enhance quality of life for elderly people, according to the criteria of the EFQM Excellence Model. Methods: A methodological triangulation was conducted in 26 PA programmes using questionnaire surveys, semistructured interviews and document analysis. We used standard approaches to the statistical analysis of data including frequencies and percentages for the categorical data. Results: Results showed that Processes (65,38%), Leadership (61,03%), Customer results (58,46) and People (51,28%) had high percentage occurrences of quality practices. In contrast, Partnerships and resources (45,77%), People results (41,03%), Policy and strategy (37,91%), Key performance results (19,23%) and Society results (19,23%) had lower percentage occurrences. Conclusions: Our findings suggest that although there are some good practices in PA programmes, there are still relevant areas that require improvement.

There is a lot of interest in the development and characterization of new biomarkers for screening large populations for disease. In much of the literature on diagnostic testing, increased levels of a biomarker correlate with increased disease risk. However, parametric forms are typically used to associate these quantities. In this article, we specify a monotonic relationship between biomarker levels with disease risk. This leads to consideration of a nonparametric regression model for a single biomarker. Estimation results using isotonic regression-type estimators and asymptotic results are given. We also discuss confidence set estimation in this setting and propose three procedures for computing confidence intervals. Methods for estimating the receiver operating characteristic (ROC) curve are also described. The finite-sample properties of the proposed methods are assessed using simulation studies and applied to data from a pancreatic cancer biomarker study.

Clustering a set of objects into homogeneous groups is a fundamental operation in data mining. Recently, many attentions have been put on categorical data clustering, where data objects are made up of non-numerical attributes. For categorical data clustering the rough set based approaches such as Maximum Dependency Attribute (MDA) and Maximum Significance Attribute (MSA) has outperformed their predecessor approaches like Bi-Clustering (BC), Total Roughness (TR) and Min-Min Roughness(MMR). This paper presents the limitations and issues of MDA and MSA techniques on special type of data sets where both techniques fails to select or faces difficulty in selecting their best clustering attribute. Therefore, this analysis motivates the need to come up with better and more generalize rough set theory approach that can cope the issues with MDA and MSA. Hence, an alternative technique named Maximum Indiscernible Attribute (MIA) for clustering categorical data using rough set indiscernible relations is proposed. The novelty of the proposed approach is that, unlike other rough set theory techniques, it uses the domain knowledge of the data set. It is based on the concept of indiscernibility relation combined with a number of clusters. To show the significance of proposed approach, the effect of number of clusters on rough accuracy, purity and entropy are described in the form of propositions. Moreover, ten different data sets from previously utilized research cases and UCI repository are used for experiments. The results produced in tabular and graphical forms shows that the proposed MIA technique provides better performance in selecting the clustering attribute in terms of purity, entropy, iterations, time, accuracy and rough accuracy.

Although cloud computing offers elastic computation and storage resources, it poses challenges on verifiability of computations and data privacy. In this work we investigate verifiability for privacy-preserving multi-keyword search over outsourced documents. As the cloud server may return incorrect results due to system faults or incentive to reduce computation cost, it is critical to offer verifiability of search results and privacy protection for outsourced data at the same time. To fulfill these requirements, we design a Verifiable Privacy-preserving keyword Search scheme, called VPSearch, by integrating an adapted homomorphic MAC technique with a privacy-preserving multi-keyword search scheme. The proposed scheme enables the client to verify search results efficiently without storing a local copy of the outsourced data. We also propose a random challenge technique with ordering for verifying top-k search results, which can detect incorrect top-k results with probability close to 1. We provide detailed analysis on security, verifiability, privacy, and efficiency of the proposed scheme. Finally, we implement VPSearch using Matlab and evaluate its performance over three UCI bag-of-words data sets. Experiment results show that authentication tag generation incurs about 3 percent overhead only and a search query over 300,000 documents takes about 0.98 seconds on a laptop. To verify 300,000 similarity scores for one query, VPSearch costs only 0.29 seconds.

The DedA family is a conserved membrane protein family found in most organisms. A Burkholderia thailandensis DedA family protein, named DbcA, is required for high-level colistin (polymyxin E) resistance, but the mechanism awaits elucidation. Modification of lipopolysaccharide lipid A with the cationic sugar aminoarabinose (Ara4N) is required for colistin resistance and is dependent upon protonmotive force (PMF) dependent transporters. B. thailandensis ΔdbcA lipid A contains only small amounts of Ara4N, likely leading to colistin sensitivity. Two B. thailandensis operons are required for lipid A modification with Ara4N, one needed for biosynthesis of undecaprenyl-P-Ara4N and one for transport of the lipid linked sugar and subsequent lipid A modification. Here, we directed overexpression of each arn operon by genomic insertion of inducible promoters. We found that overexpression of arn operons in ΔdbcA can partially, but not completely, restore Ara4N modification of lipid A and colist...

The Japanese government has recently set an ambitious target to reduce its CO 2 emissions by expanding renewables and nuclear power plants (NPPs). Perception about nuclear power, however, has always been an issue in Japan. This research reports the results of a survey regarding public acceptance of NPPs in three community groups and associations with some of its influencing factors. The samples are taken from one site near a plant under construction (Kaminoseki), another near a plant in operation (Hamaoka) and one without plants nearby (Kyoto). Among the findings, the preference to expand nuclear power was 28 percent, while that to decrease it was 11 percent. In addition, the community acceptance may shift from 28 to 65 percent in a special case of constrained acceptance. People living near the planning and the consumption sites had the highest acceptance rates and the least polarised view towards NPPs expansion. Among the analysed factors of influence, "Inclusion in the decision process" had significant correlation with both cases of acceptance ( b =0.22). Some measures to improve community acceptance before plans for NPPs expansion are included as recommendations.

Background: Hypotension or bradycardia after spinal anesthesia for cesarean section remain common and are serious complications. The current study evaluated factors associated to the incidences of hypotension or bradycardia in this context. Material and method: A prospective cross sectional study from November 1, 2004 to July 31, 2005 was conducted on 722 parturients undergoing cesarean section under spinal anesthesia. T-test and Chi-square test were used in univariate analysis to compare continuous data and categorical data respectively. Multivariate logistic regression was performed on the variables hypotension (systolic pressure decrease > 30% of baseline value) and bradycardia (heart rate < 60 bpm) p-value < 0.05 was considered significant. Results: Incidence of hypotension and bradycardia were 52.6% and 2.5%. The probability of hypotension increased with estimated blood loss 500-1000 mL (odds ratio [OR] = 1.86; 95% CI 1.30-2.67, p = 0.001), estimated blood loss > 1000 mL (OR = 5.31; 95% CI 1.47-19.19, p = 0.011), and analgesia level > T4 (OR = 1.94; 95% CI 1.18-3.19, p = 0.009). Hypotension occurred despite left uterine displacement (OR = 1.56; 95% CI 1.11-2.19, p = 0.01). Risk factors associated with bradycardia were adding intrathecal morphine 0.2 mg (0.2 mL) (OR = 4.61; 95% CI 1.31-16.19, p = 0.017) to local anesthetics. Conclusion: The present results indicated that the incidence of hypotension after spinal anesthesia for cesarean section increased with amount of estimated blood loss > 500 mL and analgesic level > T4. Adding intrathecal morphine 0.2 mg (0.2 mL) to local anesthetics increased incidence of bradycardia.

Clustering is widely used to explore and understand large collections of data. In this thesis, we introduce LIMBO, a scalable hierarchical categorical clustering algorithm based on the Information Bottleneck (IB) framework for quantifying the relevant information preserved when clustering. As a hierarchical algorithm, LIMBO can produce clusterings of different sizes in a single execution. We also define a distance measure for categorical tuples and values of a specific attribute. Within this framework, we define a heuristic for discovering candidate values for the number of meaningful clusters. Next, we consider the problem of database design, which has been characterized as a process of arriving at a design that minimizes redundancy. Redundancy is measured with respect to a prescribed model for the data (a set of constraints). We consider the problem of doing database redesign when the prescribed model is unknown or incomplete. Specifically, we consider the problem of finding structural clues in a data instance, which may contain errors, missing values, and duplicate records. We propose a set of tools based on LIMBO for finding structural summaries that are useful in characterizing the information content of the data. We study the use of these summaries in ranking functional dependencies based on their data redundancy. We also consider a different application of LIMBO, that of clustering software artifacts. The majority of previous algorithms for this problem utilize structural information in order to decompose large software systems. Other approaches using non-structural iniii formation, such as file names or ownership information, have also demonstrated merit. We present an approach that combines structural and non-structural information in an integrated fashion. We apply LIMBO to two large software systems, and the results indicate that this approach produces valid and useful clusterings. Finally, we present a set of weighting schemes that specify objective assignments of importance to the values of a data set. We use well established weighting schemes from information retrieval, web search and data clustering to assess the importance of whole attributes and individual values.

This paper presents an approach for knowledge discovery in texts extracted from the Web. Instead of analyzing words or attribute values, the approach is based on concepts, which are extracted from texts to be used as characteristics in the mining process. Statistical techniques are applied on concepts in order to find interesting patterns in concept distributions or associations. In this way, users can perform discovery in a high level, since concepts describe real world events, objects, thoughts, etc. For identifying concepts in texts, a categorization algorithm is used associated to a previous classification task for concept definitions. Two experiments are presented: one for political analysis and other for competitive intelligence. At the end, the approach is discussed, examining its problems and advantages in the Web context.

The contribution of mathematics and its allied sciences is central to sustainable economic development of every nation. Students' performance in mathematics/statistics at tertiary level of education leaves much to be desired. This paper seeks to investigate academic performance of students of students of mathematics and statistics of a tertiary institution in Ghana. It examines students' performance in mathematics/statistics with respect to; gender, the period from 2000 to 2012, and the nature of relationship in terms of mathematics/statistics achievement between the various semesters of the study. The study made use of data on academic records of ten (10) cohorts of 617 Higher National Diploma, (HND) statistics students who were admitted to and graduated from the Mathematics and Statistics Department of the institution. The study revealed that, although males far outnumbered females, their performances are the same; students' performance differed among the various years of study. In general, students' performance increased across the study period. Further, students' performances in some of the semesters were found to be related to other semesters. It was recommended that; more females enroll into mathematics and mathematics related programmes to ensure a balanced representation of gender, students' CGPA be monitored persistently for appropriate advice, and the research work be replicated in other tertiary institutions to give a broader picture of students' achievement in mathematics/statistics

The contribution of mathematics and its allied sciences is central to sustainable economic development of every nation. Students’ performance in mathematics/statistics at tertiary level of education leaves much to be desired. This paper seeks to investigate academic performance of students of students of mathematics and statistics of a tertiary institution in Ghana. It examines students’ performance in mathematics/statistics with respect to; gender, the period from 2000 to 2012, and the nature of relationship in terms of mathematics/statistics achievement between the various semesters of the study. The study made use of data on academic records of ten (10) cohorts of 617 Higher National Diploma, (HND) statistics students who were admitted to and graduated from the Mathematics and Statistics Department of the institution. The study revealed that, although males far outnumbered females, their performances are the same; students’ performance differed among the various years of study.  ...

Clustering is a widely used technique in data mining application for discovering patterns in underlying data. Most traditional clustering algorithms are limited in handling datasets that contain categorical attributes. However, datasets with categorical types of attributes are common in real life data mining problem. For these data sets, no inherent distance measure, like the Euclidean distance, would work to compute the distance between two categorical objects. In this article, we have described two algorithms based on genetic algorithm and simulated annealing in the field of crisp and fuzzy domain. The performance of the proposed algorithms has been compared with that of different well known categorical data clustering algorithms in crisp and fuzzy domain and demonstrated for a variety of artificial and real life categorical data sets. Also statistical significance tests have been performed to establish the superiority of the proposed algorithms.

Recently, categorical data clustering has been gaining significant attention from researchers, because most of the real life data sets are categorical in nature. In contrast to numerical domain, no natural ordering can be found among the elements of a categorical domain. Hence no inherent distance measure, like the Euclidean distance, would work to compute the distance between two categorical objects. In this article, genetic algorithm and simulated annealing based categorical data clustering algorithms have been proposed. The performances of the proposed algorithms have been compared with that of different well known categorical data clustering algorithms and demonstrated for a variety of artificial and real life categorical data sets. Keywords: Genetic Algorithm based Clustering (GAC), Simulated Annealing based Clustering (SAC), K-medoids Algorithm, Minkowski score.

Bireysel finansman ihtiyacinin karsilanmasina yardimci olan kredi karti, ozellikle bankacilik alaninda, bireysel hizmetler dâhilinde yer almaktadir. Kredi karti en yaygin, hizli ve kolay kullanima sahip, nakit yerine gecen bir odeme aracidir. Ayni zamanda goreli uygun maliyetli fon saglama fonksiyonu ile gunumuz ekonomik hayatin - da vazgecilmez bir finansal arac olarak karsimiza cikmaktadir. Bu calisma, bireysel tuketicilerin kredi karti kullaniminda etkili olan faktorleri belirlemeye yonelik olarak yapil - mistir. Oncelikle kredi karti hakkinda genel bilgiler verilmis, Dunya ve Turkiye finansal sistemindeki tarihsel seyri ele alinmistir. Uygulama bolumunde ise Yozgat ve Kayseri illerinde yapilan 500 kisilik anket calismasi sonucunda olusturulan hipotezler isiginda degerlendirilmistir.

This work in progress paper attempts to uncover the links between incoming student ACT (math and reading/writing scores) and performance in first year engineering and compositions courses. Statistically significant differences were found, with incoming students possessing greater math than reading/writing abilities (as measured by ACT exams). However, average performance in first year composition and engineering classes displayed the opposite relationship.

Background Neck pain is a common and costly condition for which pharmacological management has limited evidence of effi cacy and side-eff ects. Low-level laser therapy (LLLT) is a relatively uncommon, non-invasive treatment for neck pain, in which non-thermal laser irradiation is applied to sites of pain. We did a systematic review and metaanalysis of randomised controlled trials to assess the effi cacy of LLLT in neck pain. We searched computerised databases comparing effi cacy of LLLT using any wavelength with placebo or with active control in acute or chronic neck pain. Eff ect size for the primary outcome, pain intensity, was defi ned as a pooled estimate of mean diff erence in change in mm on 100 mm visual analogue scale. We identifi ed 16 randomised controlled trials including a total of 820 patients. In acute neck pain, results of two trials showed a relative risk (RR) of 1•69 (95% CI 1•22-2•33) for pain improvement of LLLT versus placebo. Five trials of chronic neck pain reporting categorical data showed an RR for pain improvement of 4•05 (2•74-5•98) of LLLT. Patients in 11 trials reporting changes in visual analogue scale had pain intensity reduced by 19•86 mm (10•04-29•68). Seven trials provided follow-up data for 1-22 weeks after completion of treatment, with short-term pain relief persisting in the medium term with a reduction of 22•07 mm (17•42-26•72). Side-eff ects from LLLT were mild and not diff erent from those of placebo. Interpretation We show that LLLT reduces pain immediately after treatment in acute neck pain and up to 22 weeks after completion of treatment in patients with chronic neck pain. Funding None.

We study this question in the context of a French reform which reduced the standard workweek from 39 to 35 hours, at constant earnings. Our empirical analysis exploits variation in the adoption of this shorter workweek across employers, which is mainly driven by institutional features of the reform and thus arguably exogenous to workers' health. Difference-in-differences and lagged dependent variable regressions reveal a positive effect of working hours on smoking and a negative effect on self-reported health. Results are robust to accounting for endogenous job mobility and differ by workers' occupations.

Consider a 2 Â J contingency table under the product multinomial model when the J categories are ordered. We compare the two distributions by deciding among the following four choices: (i) distributions are the same; (ii) distribution 1 is stochastically larger than distribution 2; (iii) distribution 2 is stochastically larger than distribution 1; (iv) neither (i), (ii), or (iii). A four action problem is posed and two procedures are considered. One ad hoc and the second procedure is a conditional Bayes procedure, where the conditioning is on the marginal row and column totals. The problem was motivated by a data set comparing survey methods dealing with economic damage to farms by deer.

Missing  data  is  a  pervasive  challenge  in  real-world  evidence  (RWE)  studies,  arising  from incomplete or inconsistent data collection. Proper handling of missing data is critical to ensure the validity  and  reliability  of  study  outcomes.  This  paper  explores  strategies  to  address missingness, focusing on mechanisms, methods, and tools available to researchers.Understanding the underlying mechanism of missingness—Missing Completely at Random (MCAR), Missing at Random (MAR), or Missing Not at Random (MNAR)—is the foundation of effective data management. Methods such as complete case analysis and single imputation are  suitable  for  MCAR  scenarios  but  may  introduce  bias  or  underestimate  variability. Advanced approaches, like multiple imputation and maximum likelihood estimation, better address  MAR  data,  preserving  uncertainty  and  improving  robustness.  For  MNAR  cases, sensitivity analyses are essential to evaluate the impact of missingness on study conclusions.Innovative  tools  in  R,  including  mice,  missForest,  VIM,  and  naniar,  enable  effective imputation,  visualization,  and  modeling  of  missing  data.  Machine  learning  techniques  and Bayesian approaches offer promising alternatives for complex datasets. Combining methods, such as multiple imputation followed by sensitivity analysis, ensures more reliable inferences.Best  practices  emphasize  assessing  missingness  patterns,  transparent  documentation  of assumptions,  and  thorough  reporting  of  strategies  used to  address  missing  data. Adopting these  approaches  minimizes  bias  and  enhances  the  credibility  of  RWE  studies,  ultimately supporting better-informed healthcare decisions. This paper underscores the importance of a systematic, informed approach to handling missing data in RWE.

The Konstanz Information Miner (KNIME) is being developed by the Nycomed Chair for Bioinformatics and Information Mining at the University of Konstanz since 2004. KNIME is open source and available under a dual licensing scheme. Usage of KNIME is free for everyone providing ...

Abstract—This paper aims on addressing the issue of irrelevant news content and information overloading among users
by providing a personalized summarization model. To achieve
this we have developed a personalized news summarization
system which provides concise summaries of news articles by
extracting keywords according to the user preference, this process
analyses the user specific interest like preferred topics, categories
and keywords .The summarization system uses NewsAPI to
fetch real time data (i.e recent news articles) and uses trained
Natural Language Processing(NLP) that contains a hugging face
transformers library for text summarization which ensures that
the content remains up to date and relavent to the user preference
.The architecture of this system is designed to be modular and
scalable which enables integration of various components such
as data collection, preprocessing, personalization, summarization,
and keyword extraction. This system in this research is efficient, reliable and user-friendly which provides a concise and
personalised summarization with extracted keywords for user
personalized news topics. This research reduces users’ burden
by making news consumption more efficient and relevant. This
also ensures that the user gets focused, personalised and easy to
understand summaries by connecting the gap between too much
information and the need for their simplicity.
Index Terms—Personalized news summarizer, Keyword extraction, News API.

All over the world, education of the girl child has been of primary concern in the past two decades. Females are particularly encouraged to pursue educational programs which eventually lead to careers in so called male dominated fields of science and engineering. According to a UNESCO Institute for Statistics report, the international community pledged to eliminate gender disparities at all levels of education by 2015 as part of the Millennium Development Goals. The question one may ask is the extent to which this particular MDG has been achieved. Educational institutions like the Technical and Vocational training centres have a major role to play in achieving this goal. Polytechnics offer a wide variety of programs with the objective of giving its students practical oriented training to provide manpower, largely, for the middle level. Accra Polytechnic runs at least five programs each in the fields of Science and Engineering. This paper looks at the differentials in gender in the e...

In this paper we propose a new type of distance-based classifier. Traditionally, these classifiers are instancebased: they classify a test instance by computation of a similarity measure between that instance and the instances in the training-set and assigning it the same class of the most similar k instances. This method is simple but has some disadvantages, among which there is the greater sensitivity to the local presence of noise in the training-set, the need to compute many similarity measures and the difficulty to decide ...

Background: In the past years, there has been a growing concern in designing physical activity (PA) programmes for elderly people, because evidence suggests that such health promotion interventions may reduce the deleterious effects of the ageing process. Quality is an important issue when designing a PA programme for older people. Some studies support the Excellence Model of the European Foundation for Quality Management (EFQM) as an operational framework for evaluating the quality of an organization. Within this context, the aim of this study was to characterize the quality management models of the PA programmes developed by Portuguese Local Administration to enhance quality of life for elderly people, according to the criteria of the EFQM Excellence Model. Methods: A methodological triangulation was conducted in 26 PA programmes using questionnaire surveys, semistructured interviews and document analysis. We used standard approaches to the statistical analysis of data including frequencies and percentages for the categorical data. Results: Results showed that Processes (65,38%), Leadership (61,03%), Customer results (58,46) and People (51,28%) had high percentage occurrences of quality practices. In contrast, Partnerships and resources (45,77%), People results (41,03%), Policy and strategy (37,91%), Key performance results (19,23%) and Society results (19,23%) had lower percentage occurrences. Conclusions: Our findings suggest that although there are some good practices in PA programmes, there are still relevant areas that require improvement.

While univariate instances of binomial data are readily handled with generalized linear models, cases of multivariate or repeated measure binomial data are complicated by the possibility of correlated responses. Likelihood-based estimation can be applied by using mixture distribution models, though this approach can present computational challenges. The logistic transformation can be used to bypass these concerns and allow for alternative estimating procedures. One popular alternative is the generalized estimating equation (GEE) method, though systematic errors can lead to infeasible correlation estimates or nonconvergence problems. Our approach is the coupling of quasileast squares (QLSs) method with a rarely used matrix factorization, which achieves a simplified estimation platform—as compared to the mixture model approach—and does not suffer from the convergence problems in GEE method. A noncontrived example is provided that shows the mechanical breakdown of GEE using several sta...

The aim of this paper is twofold. On the one hand, we analyze a feature ranking technique based on the weights estimated by an evolutionary algorithm for multiobjective optimization. On the other hand, we address the problem of comparing and aggregating different rankings obtained either by applying different methods to the same dataset, or by applying, in the context of distributed data mining tasks, the same method to different datasets.

People who inject drugs are an important population to study in order to reduce transmission of blood-borne illnesses including HIV and Hepatitis. In this paper we estimate the HIV and Hepatitis C prevalence among people who inject drugs, as well as the proportion of people who inject drugs who are female in Mauritius. Respondent driven sampling (RDS), a widely adopted link-tracing sampling design used to collect samples from hard-to-reach human populations, was used to collect this sample. The random walk approximation underlying many common RDS estimators assumes that each social relation (edge) in the underlying social network has an equal probability of being traced in the collection of the sample. This assumption does not hold in practice. We show that certain RDS estimators are sensitive to the violation of this assumption. In order to address this limitation in current methodology, and the impact it may have on prevalence estimates, we present a new method for improving RDS prevalence estimators using estimated edge inclusion probabilities, and apply this to data from Mauritius.

This article presents an extension of the methodology developed by Gilmour et al. , for ordered categorical data, taking into account the hetero- geneity of residual variances of latent variables. Heterogeneity of residual variances is described via a structural linear model on log-variances. This method involves ' two main steps: i) a 'marginalization' with respect to the random effects leading to quasi-score estimators; ii) an approximation of the variance-covariance matrix of the observations which leads to an analogue of the Henderson mixed model equations for continuous Gaussian data. This methodology is illustrated by a numerical example of footshape in sheep. &copy; Inra/Elsevier, Paris generalized linear mixed models / quasi-score / heterogeneity of variances / threshold response model Résumé -Une approche de quasi-score pour l'analyse de variables qualitatives ordonnées par un modèle mixte à seuils hétéroscédastique. Cet article présente une extension de la méthodologie développée par Gilmour et al. !19! dans le cas de variables qualitatives ordonnées, prenant en compte l'hétérogénéité des variances résiduelles des variables latentes. L'hétérogénéité des variances résiduelles est décrite par un modèle linéaire structurel sur les logarithmes des variances. Cette méthode comprend deux étapes principales : i) une « marginalisation » par rapport aux effets aléatoires qui conduit, grâce aux équations de quasi-score, à l'estimation des paramètres ; ii) une approximation de la matrice de variance-covariance des observations qui aboutit à un système analogue aux équations du modèle mixte d'Henderson dans le cas de variables continues gaussiennnes. Cette méthodologie est illustrée par un exemple sur la forme des pieds chez le mouton. @ Inra/Elsevier, Paris modèles linéaires généralisés mixtes / quasi-score / variances hétérogènes / modèle à seuils

We compare correspondence analysis (CA) and the alternative approach using Hellinger distance (HD), for representing categorical data in a contingency table. As both methods may be appropriate, we introduce a parameter and define a generalized version of correspondence analysis (GCA) which contains CA and HD as particular cases. Comparison with alternative approaches are performed. We propose a coefficient which globally measures the similarity between CA and GCA, which can be decomposed into several components, one component for each principal dimension, indicating the contribution of the dimensions on the difference between both representations. Two criteria for choosing the best value of the parameter are proposed.

Many instruments have been developed to measure the multidimensional construct of quality of life. One of them has been developed by the World Health Organization (WHOQOL-100) and adapted into different languages and cultures around the world. The authors of this study wanted to assess the measurement properties of the Turkish version of WHOQOL-100, to find out the latent factors underlying quality of life, and to determine the direction and magnitude of the interdependent effects among these factors by using structural equation modeling (SEM). The measurement properties of the Turkish version of WHOQOL-100 scale were assessed on 520 voluntary participants who were immigrants in Stockholm/Sweden. SEM gave us one second-order factor QOL and the five correlated first-order factors labelled: physical, social relations, psychological, environment and independence. In the model for total participants, all the factor loadings were high (ranging from 0.60 to 0.92 except for "sexuality" which was 0.47), indicating a strong association between each of the latent factors and their respective items. In the models which were separately constructed regarding birthplace, the authors found a strong association between each of the latent factors and their respective items. The most substantial possible effect on QOL was psychological domain (0.93), which was larger than physical health (0.84), social relations (0.82), level of independence (0.91) and environment (0.73). The effect of psychological domain on the overall quality of life is greater than those of other domains.

The problem of incessant decline in academic performance of Nigeria students in recent years cannot be over emphasized. Despite importance attached to academic performance, researchers have shown that students' performance is declining. Researches had also shown that there are a lot of factors responsible for this trend. Using data obtained from records of graduated students from the Faculty of Science, University of Ilorin for 2011/2012 academic session, mode of entry, age at entry, department, and sex of students are examined as factors that could contribute to students' performance. Ordinal Logistic Regression (Proportional Odds Model) is used to model the data and the results reveal that only sex of students is not a determinant factor of final grade that students may attained at graduation. This research also finds that there is equal chance for both male and female students to graduate from a university with First Class, hence, governments' policy on education should be focused on both gender instead of special attention usually given to female students. It has also been established that younger students perform better than the older ones; hence, age of students at entry into any of educational level should not be of major concerned but the ability of such student to cope with the demand of such level. It is also established that the highest odds of graduating with First Class is obtained by students who were admitted through Direct Entry (DE). Most of these students are educationally matured as they have spent at least two academic sessions in their previous school mostly Polytechnics, hence, in order to ensure that we have better graduates in our tertiary institutions, a policy that encouraged programmes such as Higher School Certificate (HSC) should be reintroduced into the system to ensure that only set of academically matured students get in different universities.

The study sought to propose a statistical model for the public Secondary School students' retention rates for Kisumu County. We used survival regression analysis in which students were grouped according to the their performance in KCSE, mean school fee payment, school category, sex, mean age and teacher-student ratio using a desirable survival function. The model was of interest because the study sought to address a life testing experience mostly restricted to survival models and most of the existing models on student retention addressed Universities and tertiary colleges' trend and were particularly developed outside the country. This was in spite of the fact that Kenya suffers from high dropout rates at the Secondary level. The annual Secondary School students data traced from a cohort in form one in the year 2010 to form four in the year 2013 were obtained from the Kisumu County Ministry of Education headquarters and analyzed using survival regression. The variables which were insignificant were dropped to get the desirable function. Survival rates of students in the Secondary Schools were traced at the end of each and every level. It was found out that dropping out of students was influenced by; the category of the school, average fee payment, performance in KCSE and sex, with more girls dropping out than boys and the dropping out mostly rampant at form two. The model will be of relevance to the concerned Secondary education stakeholders in improving the quality of education for it will inform the planning of necessary educational interventions to ensure enhanced retention rate and transition.

Introduction: Poor neuro-cognitive performance in patients with schizophrenia has been described as a core symptom of the illness and is shown to be associated with poor psycho-social functioning. Management of schizophrenia has shifted its focus to treat this deficit apart from only emphasising on positive and negative symptoms, as it will subsequently improve patient functioning and outcome. Objective: The study aims to determine the proportion of neuro-cognitive impairment in patients with schizophrenia in a psychiatric clinic in Hospital Universiti Kebangsaan Malaysia and factors that are likely to be associated with the impairment. Method: A cross-sectional study design was conducted in this hospital-based study and subjects were randomly chosen from the psychiatric clinic. Rey Auditory Verbal Learning Test (RAVLT), Digit Forward and Backward (DF and DB), Trail Making Test (TMT) and Verbal Fluency Test (VF) were used to assess subjects' neuro-cognitive performance that measured their verbal memory and executive functioning of the brain. Results: The proportion of neuro-cognitive impairment is estimated at about 80% in patients with schizophrenia in this hospital-based study. A higher percentages of respondents had abnormal scores for RAVLT1, RAVLT5 and RAVLTB tests (75.6%, 68.3% and 82.9% respectively). The majority of respondents had normal scores for DF, VF tests (80.5% and 73.2% respectively), and about 51.2% of respondents had normal scores for DB test. For TMT, overall performance of respondents in Set A and B was poor. The mean duration of time taken to complete both sets was longer than that of a normal population based on age group: (age group: 18-39 years; TMT A 68.98 vs 40 seconds; TMT B 174.09 vs 90 seconds and age group: 40-49 years; TMT A 58.57 vs 45 seconds; TMT B 162.43 vs 100 seconds). There was a significant association between duration of illness and scores of RAVLT1 and between age of onset of illness and RAVLTB scores (p<0.05). There was no significant association between scores of all tests with the type of treatment received by respondents. Conclusion: The proportion of neuro-cognitive impairment in patients with schizophrenia is very high (80%) and has major implications on the current management of schizophrenia in which this core symptom should also be a focus of treatment. The significant association between clinical factors and neuro-cognitive impairment highlights the importance of modifying those factors in order to minimise the deficit in patients with schizophrenia.

The dynamic ensemble selection of classifiers is an effective approach for processing labelimbalanced data classifications. However, such a technique is prone to overfitting, owing to the lack of regularization methods and the dependence of the aforementioned technique on local geometry. In this study, focusing on binary imbalanced data classification, a novel dynamic ensemble method, namely adaptive ensemble of classifiers with regularization (AER), is proposed, to overcome the stated limitations. The method solves the overfitting problem through implicit regularization. Specifically, it leverages the properties of stochastic gradient descent to obtain the solution with the minimum norm, thereby achieving regularization; furthermore, it interpolates the ensemble weights by exploiting the global geometry of data to further prevent overfitting. According to our theoretical proofs, the seemingly complicated AER paradigm, in addition to its regularization capabilities, can actually reduce the asymptotic time and memory complexities of several other algorithms. We evaluate the proposed AER method on seven benchmark imbalanced datasets from the UCI machine learning repository and one artificially generated GMM-based dataset with five variations. The results show that the proposed algorithm outperforms the major existing algorithms based on multiple metrics in most cases, and two hypothesis tests (McNemar's and Wilcoxon tests) verify the statistical significance further. In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.

The present study is an attempt to examine factors affecting undergraduates’ rate of completion. Data from 7,443 students collected during 2017 were adopted in this research, and a predictive approach and multiple regression analysis were used. Results indicated that the most influential academic factors on the rate of completion were cumulative grade point average (GPA) and discipline; medical college students had a higher rate of completion compared to students of basic science and humanities. The second factor influencing the rate of completion was admission criteria, and the achievement test emerged as the most important factor of admission criteria. Among the social factors that affected academic achievements were gender and age variables, and there was a significant gender difference, favouring females. This study emphasizes the role of academic factors and admission criteria in affecting the rate of completion, contradicting most previous studies, which have indicated that ec...

In this article, we offer a new way of exploring relationships between three different dimensions of a business operation, namely the stage of business development, the methods of creativity and the major cultural values. Although separately, each of these has gained enormous attention from the management research community, evidenced by a large volume of research studies, there have been not many studies that attempt to describe the logic that connect these three important aspects of a business; let alone empirical evidences that support any significant relationships among these variables. The paper also provides a data set and an empirical investigation on that data set, using a categorical data analysis, to conclude that examinations of these possible relationships are meaningful and possible for seemingly unquantifiable information. The results also show that the most significant category among all creativity methods employed in Vietnamese enterprises is the "creative disciplines" rule in the "entrepreneurial phase," while in general creative disciplines have played a critical role in explaining the structure of our data sample, for both stages of development in our consideration.

The presented work aims at exploring voicing alternation and assimilation on very large corpora using a Bayesian framework. A voice feature (VF) variable has been introduced whose value is determined using statistical acoustic phoneme models, corresponding to 3-state Gaussian mixture Hidden Markov Models. For all relevant consonants, i.e. oral plosives and fricatives their surface form voice feature is determined by maximising the acoustic likelihood of the competing phoneme models. A voicing alternation (VA) measure counts the number of changes between underlying and surface form voice features. Using a corpus of 90h of French journalistic speech, an overall voicing alternation rate of 2.7% has been measured, thus calibrating the method's accuracy. The VA rate remains below 2% word-internally and on word starts and raises up to 9% on lexical word endings. In assimilation contexts rates grow significantly (> 20%), highlighting regressive voicing assimilation. Results also exhibit a weak tendency for progressive devoicing.