Multiple classification analysis ; a report on a computer program for multiple regression using categorical predictors /

Bibliographical footnotes.

Mathematical modelling of patient risks in a hospital environment, using multiple regression analysis

The aim of this research work was primarily to examine the relevance of patient parameters, ward structures, procedures and practices, in respect of the potential hazards of wound cross-infection and nasal colonisation with multiple resistant strains of Staphylococcus aureus, which it is thought might provide a useful indication of a patient's general susceptibility to wound infection. Information from a large cross-sectional survey involving 12,000 patients from some 41 hospitals and 375 wards was collected over a five-year period from 1967-72, and its validity checked before any subsequent analysis was carried out. Many environmental factors and procedures which had previously been thought (but never conclusively proved) to have an influence on wound infection or nasal colonisation rates, were assessed, and subsequently dismissed as not being significant, provided that the standard of the current range of practices and procedures is maintained and not allowed to deteriorate. Retrospective analysis revealed that the probability of wound infection was influenced by the patient's age, duration of pre-operative hospitalisation, sex, type of wound, presence and type of drain, number of patients in ward, and other special risk factors, whilst nasal colonisation was found to be influenced by the patient's age, total duration of hospitalisation, sex, antibiotics, proportion of occupied beds in the ward, average distance between bed centres and special risk factors. A multi-variate regression analysis technique was used to develop statistical models, consisting of variable patient and environmental factors which were found to have a significant influence on the risks pertaining to wound infection and nasal colonisation. A relationship between wound infection and nasal colonisation was then established and this led to the development of a more advanced model for predicting wound infections, taking advantage of the additional knowledge of the patient's state of nasal colonisation prior to operation.

Incremental tensor biased discriminant analysis:a new color-based visual tracking method

Most existing color-based tracking algorithms utilize the statistical color information of the object as the tracking clues, without maintaining the spatial structure within a single chromatic image. Recently, the researches on the multilinear algebra provide the possibility to hold the spatial structural relationship in a representation of the image ensembles. In this paper, a third-order color tensor is constructed to represent the object to be tracked. Considering the influence of the environment changing on the tracking, the biased discriminant analysis (BDA) is extended to the tensor biased discriminant analysis (TBDA) for distinguishing the object from the background. At the same time, an incremental scheme for the TBDA is developed for the tensor biased discriminant subspace online learning, which can be used to adapt to the appearance variant of both the object and background. The experimental results show that the proposed method can track objects precisely undergoing large pose, scale and lighting changes, as well as partial occlusion. © 2009 Elsevier B.V.

A Method for Solving a Class of Multiple-Criteria Analysis Problems

AMS subject classification: 90C29.

Application of Regularized Discriminant Analysis

2000 Mathematics Subject Classification: 62H30, 62P99

Interactive Stepwise Discriminant Analysis in Matlab

2000 Mathematics Subject Classification: 62-04, 62H30, 62J20

Comparing Several Methods of Discriminant Analysis on the Case of Wine Data

2000 Mathematics Subject Classification: 62H30, 62J20, 62P12, 68T99

Characteristics of women who frequently under report their energy intake: a doubly labelled water study

Background/Objectives: We applied three dietary assessment methods and aimed at obtaining a set of physical, social and psychological variables that can discriminate those individuals who did not underreport (`never under-reporters`), those who underreported in one dietary assessment method (`occasional under-reporters`) and those who underreported in two or three dietary assessment methods (`frequent under-reporters`). Participants/Methods: Sixty-five women aged 18-57 years were recruited for this study. Total energy expenditure was determined by doubly labelled water, and energy intake was estimated by three 24-h diet recalls, 3-day food records and a food frequency questionnaire. A multiple discriminant analysis was used to identify which of those variables better discriminated the three groups: body mass index (BMI), income, education, social desirability, nutritional knowledge, dietary restraint, physical activity practice, body dissatisfaction and binge-eating symptoms. Results: Twenty-three participants were `never under-reporters`. Twenty-four participants were `occasional under-reporters` and 18 were `frequent under-reporters`. Four variables entered the discriminant model: income, BMI, social desirability and body dissatisfaction. According to potency indices, income contributed the most to the total discriminant power, followed in decreasing order by social desirability score, BMI and body dissatisfaction. Income, social desirability and BMI were the characteristics that mainly separated the `never under-reporters` from the under-reporters (occasional or frequent). Body dissatisfaction better discriminated the `occasional under-reporters` from the `frequent under-reporters`. Conclusions: `Frequent under-reporters` have a greater BMI, social desirability score, body dissatisfaction score and lower income. These four variables seemed to be able to discriminate individuals who are more prone to systematic under reporting. European Journal of Clinical Nutrition (2009) 63, 1192-1199; doi:10.1038/ejcn.2009.54; published online 15 July 2009

"Owned by...". Country of origin's new cue

This study identifies and explores a new country of origin (COO) cue, “owned by….” The importance of three extrinsic cues “owned by …,” “made in …” and price was examined using conjoint analysis. Data were collected from a sample of 268 undergraduate students familiar with color televisions. Segments were formed using cluster analysis and analyzed using multiple discriminant analysis. “Owned by …” was found to be important and distinct from the “made in …” cue. Segments based on the two COO cues were identified using importance weights and individual utilities. When segments were formed using individual utilities the individual difference construct, economic nationalism, provided discriminatory power while consumer ethnocentrism did not, supporting the hypothesis that economic nationalism and consumer ethnocentrism differ. Practitioners can now use “owned by …” knowing that it forms an important and distinct marketing tool. Limitations and future research are discussed.

Subclinical form of the American visceral leishmaniasis

The subclinical form of visceral leishmaniasis (VL) shows nonspecific clinical manifestations, with difficulties being frequently met in its clinical characterization and diagnostic confirmation. Thus, the objective of the present study was to define the clinical-laboratory profile of this clinical form. A cohort study was conducted in the state of Maranhão, Brazil, from January/1998 to December/2000, with monthly follow-up of 784 children aged 0-5 years. Based on the clinical-laboratory parameters reported in the literature, four categories were established, with the children being classified (according to their clinical-evolutive behavior) as asymptomatic (N = 144), as having the subclinical form (N = 33) or the acute form (N = 12) or as subjects "without VL" (N = 595). Multiple discriminant analysis demonstrated that the combination of fever, hepatomegaly, hyperglobulinemia, and increased blood sedimentation rate (BSR) can predict the subclinical form of VL as long as it is not associated with splenomegaly or leukopenia. Subjects with the subclinical form did not show prolonged or intermittent evolution or progression to the acute form of VL. Subclinical cases have a profile differing from the remaining clinical forms of VL, being best characterized by the combination of fever, hepatomegaly, hyperglobulinemia, and increased BSR.

Serum cytokine profile in the subclinical form of visceral leishmaniasis

The factors determining the development or not of visceral leishmaniasis (VL) have not been completely identified, but a Leishmania-specific cellular immune response seems to play a fundamental role in the final control of infection. Few studies are available regarding the production of cytokines in the subclinical form of VL, with only the production of IFN-g and TNF-a known. The aim of the present study was to identify immunological markers for the oligosymptomatic or subclinical form of VL. A prospective cohort study was conducted on 784 children aged 0 to 5 years from an endemic area in the State of Maranhão, Brazil, between January 1998 and December 2001. During 30 consecutive months of follow-up, 33 children developed the oligosymptomatic form of the disease and 12 the acute form. During the clinical manifestations, serum cytokine levels were determined in 27 oligosymptomatic children and in nine patients with the acute form using a quantitative sandwich enzyme immunoassay. In the subclinical form of VL, variable levels of IL-2 were detected in 52.3% of the children, IL-12 in 85.2%, IFN-g in 48.1%, IL-10 in 88.9%, and TNF-a in 100.0%, with the last two cytokines showing significantly lower levels than in the acute form. IL-4 was not detected in oligosymptomatic individuals. Multiple discriminant analysis used to determine the profile or combination of cytokines predominating in the subclinical form revealed both a Leishmania resistance (Th1) and susceptibility (Th2) profile. The detection of both Th1 and Th2 cytokine profiles explains the self-limited evolution accompanied by the discrete alterations observed for the subclinical form of VL.

Individual assets, market structure and the drivers of return

Much prior research on the structure and performance of UK real estate portfolios has relied on aggregated measures for sector and region. For these groupings to have validity, the performance of individual properties within each group should be similar. This paper analyses a sample of 1,200 properties using multiple discriminant analysis and cluster analysis techniques. It is shown that conventional property type and spatial classifications do not capture the variation in return behaviour at the individual building level. The major feature is heterogeneity - but there may be distinctions between growth and income properties and between single and multi-let properties that could help refine portfolio structures.

Influência dos intermediários de distribuição de produtos turísticos no processo de decisão do meio de hospedagem pelo consumidor

This study examines the complex hotel buyer decision process in front of the tourism distribution channels. Its objective is to describe the influence level of the tourism marketing intermediaries, mainly the travel agents and tour operators, over the hotel decision process by the buyer-tourist. The data collection process was done trough a survey with three hundred brazilian tourists hosted in nineteen hotels of Natal, capital of Rio Grande do Norte, Brazil. The data analysis was done using some multivariate statistic techniques as correlation analysis, multiple regression analysis, factor analysis and multiple discriminant analysis. The research characterizes the hotel services consumers profile and his trip, and identifying the distribution channels used by them. Furthermore, the research verifies the intermediaries influence exercised over hotel buyer decision process, looking for identify causality relations between the influence level and the buyer profile. Verifies that information about hotels available on internet reduces the probability that this influence can be practiced; however it was possible identifying those consumers considers this information complementary and non-substitutes than the information from intermediaries. The characteristics of the data do not allow indentifying the factors that constraint the intermediaries influence neither identifying discriminant functions of the specific distribution channel choice by consumers. The study concludes that consumers don t agree in have been influenced by intermediaries or don t know if they have, still considering important to consult them and internet doesn t substitute their function as information source