Mapping an uncertainty zone between interpolated types of a categorical variable

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Mapping an uncertainty zone between interpolated types of a categorical variable

Categorical data cannot be interpolated directly because they are outcomes of discrete random variables. Thus, types of categorical variables are transformed into indicator functions that can be handled by interpolation methods. Interpolated indicator values are then backtransformed to the original types of categorical variables. However, aspects such as variability and uncertainty of interpolated values of categorical data have never been considered. In this paper we show that the interpolation variance can be used to map an uncertainty zone around boundaries between types of categorical variables. Moreover, it is shown that the interpolation variance is a component of the total variance of the categorical variables, as measured by the coefficient of unalikeability. (C) 2011 Elsevier Ltd. All rights reserved.

Decline in condition of northern bluefin tuna (Thunnus thynnus) in the Gulf of Maine

The northern bluefin tuna (Thunnus thynnus) is a highly mobile apex predator in the Gulf of Maine. Despite current stock assessments that indicate historically high abundance of its main prey, Atlantic herring (Clupea harengus), commercial fishermen have observed declines in the somatic condition of northern bluefin tuna during the last decade. We examined this claim by reviewing detailed logbooks of northern bluefin tuna condition from a local fishermen’s cooperative and applying multinomial regression, a robust tool for exploring how a categorical variable may be related to other variables of interest. The data set contained >3082 observations of condition (fat and oil content and fish shape) from fish landed between 1991 and 2004. Energy from stored lipids is used for migration and reproduction; therefore a reduction in energy acquisition on bluefin tuna feeding grounds could diminish allocations to growth and gamete production and have detrimental consequences for rebuilding the western Atlantic population. A decline in northern bluefin tuna somatic condition could indicate substantial changes in the bottom-up transfer of energy in the Gulf of Maine, shifts in their reproductive or migratory patterns, impacts of fishing pressure, or synergistic effects from multiple causes.

Prevalence of overweight and obesity in children from urban and rural Niagara

Purpose: The influence of environment in the development of overweight and obesity is an ongoing concern. This investigation examined the influence of urbanization on the rates of childhood overweight and obesity. Method: 2167 (1090M, 1077F) grade four children from 75 schools in Ontario's Niagara Region were sampled. A sophisticated algorithm overlaying electoral boundaries, population densities, and the knowledge of community members was used to classify schools into one of three location categories: urban {N= 1588), urban fringe {N= 379), and rural (A^= 234). Each subject was measured for: height, weight, and aerobic performance (Leger). Physical activity was evaluated with the self-report Participation Questionnaire (free-time and organized sport activities), and teacher's evaluations of student activity. Overweight (overweight and obesity combined) was measured both as a continuous (BMI) and categorical variable (BMI category), to evaluate the prevalence by location. A multivariate analysis was used to test for a suppression effect. Results: BMI and BMI category did not differ significantly by location or gender, and no evidence of a gender interaction existed. According to both a linear and logistic regression, physical activity or fitness levels did not suppress the influence of location on BMI and BMI category. Age, gender, free-time activity, organized sports, fitness level, and number of siblings, were all found to significantly influence overweight. Conclusions: It is plausible that the prevalence of overweight does not differ in urban and rural children from the Niagara Region. Further investigation is recommended, examining subjects by individual location of residence, in multiple regions throughout Ontario.

Mixing compositions and other scales

Theory of compositional data analysis is often focused on the composition only. However in practical applications we often treat a composition together with covariables with some other scale. This contribution systematically gathers and develop statistical tools for this situation. For instance, for the graphical display of the dependence of a composition with a categorical variable, a colored set of ternary diagrams might be a good idea for a first look at the data, but it will fast hide important aspects if the composition has many parts, or it takes extreme values. On the other hand colored scatterplots of ilr components could not be very instructive for the analyst, if the conventional, black-box ilr is used. Thinking on terms of the Euclidean structure of the simplex, we suggest to set up appropriate projections, which on one side show the compositional geometry and on the other side are still comprehensible by a non-expert analyst, readable for all locations and scales of the data. This is e.g. done by defining special balance displays with carefully- selected axes. Following this idea, we need to systematically ask how to display, explore, describe, and test the relation to complementary or explanatory data of categorical, real, ratio or again compositional scales. This contribution shows that it is sufficient to use some basic concepts and very few advanced tools from multivariate statistics (principal covariances, multivariate linear models, trellis or parallel plots, etc.) to build appropriate procedures for all these combinations of scales. This has some fundamental implications in their software implementation, and how might they be taught to analysts not already experts in multivariate analysis

Crossbred cow adoption and milk market participation in a multivariate count data framework

Cross-bred cow adoption is an important and potent policy variable precipitating subsistence household entry into emerging milk markets. This paper focuses on the problem of designing policies that encourage and sustain milkmarket expansion among a sample of subsistence households in the Ethiopian highlands. In this context it is desirable to measure households’ ‘proximity’ to market in terms of the level of deficiency of essential inputs. This problem is compounded by four factors. One is the existence of cross-bred cow numbers (count data) as an important, endogenous decision by the household; second is the lack of a multivariate generalization of the Poisson regression model; third is the censored nature of the milk sales data (sales from non-participating households are, essentially, censored at zero); and fourth is an important simultaneity that exists between the decision to adopt a cross-bred cow, the decision about how much milk to produce, the decision about how much milk to consume and the decision to market that milk which is produced but not consumed internally by the household. Routine application of Gibbs sampling and data augmentation overcome these problems in a relatively straightforward manner. We model the count data from two sites close to Addis Ababa in a latent, categorical-variable setting with known bin boundaries. The single-equation model is then extended to a multivariate system that accommodates the covariance between crossbred-cow adoption, milk-output, and milk-sales equations. The latent-variable procedure proves tractable in extension to the multivariate setting and provides important information for policy formation in emerging-market settings

Construct validity of a figure rating scale for Brazilian adolescents

Background: Figure rating scales were developed as a tool to determine body dissatisfaction in women, men, and children. However, it lacks in the literature the validation of the scale for body silhouettes previously adapted. We aimed to obtain evidence for construct validity of a figure rating scale for Brazilian adolescents.Methods: The study was carried out with adolescent students attending three public schools in an urban region of the municipality of Florianopolis in the State of Santa Catarina (SC). The sample comprised 232 10-19-year-old students, 106 of whom are boys and 126 girls, from the 5th series (i.e. year) of Primary School to the 3rd year of Secondary School. Data-gathering involved the application of an instrument containing 8 body figure drawings representing a range of children's and adolescents' body shapes, ranging from very slim (contour 1) to obese (contour 8). Weights and heights were also collected, and body mass index (BMI) was calculated later. BMI was analyzed as a continuous variable, using z-scores, and as a dichotomous categorical variable, representing a diagnosis of nutritional status (normal and overweight including obesity).Results: Results showed that both males and females with larger BMI z-scores chose larger body contours. Girls with higher BMI z-scores also show higher values of body image dissatisfaction.Conclusion: We provided the first evidence of validity for a figure rating scale for Brazilian adolescents.

Modified radical mastectomy: A pilot clinical trial comparing the use of conventional electric scalpel and harmonic scalpel

Background: The aim of this study was to compare the rates of local postoperative complications among women undergoing modified radical mastectomy with an electric scalpel (ES) or a harmonic scalpel (HS). It is thought that HS use has less postoperative complications, mainly seroma formation. Methods: This study was a prospective non-randomised clinical trial (NCT01391988) among consecutive patients, performed in parallel. Patients underwent modified radical mastectomy using an HS or ES. We analysed the following operative variables: time, blood loss and seroma volume drainage. Postoperative complications, including seroma, flap necrosis, haematoma and infection were evaluated on the 7th and 14th days. Results: Forty-six patients underwent a MRM with ES and 49 with HS; no differences were observed between the groups. The rate of local complications was 29% in the HS group and 52% in the ES group (p=0.024). The rates of seroma (16.3% versus 28.3%; p=0.161), necrosis (4.1% vs. 21.7%; p=0.013; OR=0.15), haematoma (2.0% vs. 8.7%; p=0.195) and infection (2.0% vs. 6.5%; p=0.351) were lower in the HS group. Adding the findings of all comparative studies using HSs in MRM to the seroma rates in the current study, the seroma rate, expressed as a categorical variable, did not decrease with HS. Seroma was present in 60/219 cases using an HS and in 69/239 cases utilising an ES (p=0.72). Based on a multivariate analysis, HS decreased the risk of skin necrosis (p=0.015). Conclusions: HSs do not decrease the seroma rate. However, this method may be useful in skin sparing mastectomy because it decreases skin flap necrosis. © 2013 Surgical Associates Ltd.

Simulação sequencial de atributos diagnósticos do solo

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

The mediating role of physical inactivity on the relationship between inflammation and artery thickness in prepubertal adolescents

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Gli assetti proprietari e di controllo nell'agroalimentare italiano

The recent default of important Italian agri-business companies provides a challenging issue to be investigated through an appropriate scientific approach. The events involving CIRIO, FERRUZZI or PARMALAT rise an important research question: what are the determinants of performance for Italian companies in the Italian agri – food sector? My aim is not to investigate all the factors that are relevant in explaining performance. Performance depends on a wide set of political, social, economic variables that are strongly interconnected and that are often very difficult to express by formal or mathematical tools. Rather, in my thesis I mainly focus on those aspects that are strictly related to the governance and ownership structure of agri – food companies representing a strand of research that has been quite neglected by previous scholars. The conceptual framework from which I move to justify the existence of a relationship between the ownership structure of a company, governance and performance is the model set up by Airoldi and Zattoni (2005). In particular the authors investigate the existence of complex relationships arising within the company and between the company and the environment that can bring different strategies and performances. They do not try to find the “best” ownership structure, rather they outline what variables are connected and how they could vary endogenously within the whole economic system. In spite of the fact that the Airoldi and Zattoni’s model highlights the existence of a relationship between ownership and structure that is crucial for the set up of the thesis the authors fail to apply quantitative analyses in order to verify the magnitude, sign and the causal direction of the impact. In order to fill this gap we start from the literature trying to investigate the determinants of performance. Even in this strand of research studies analysing the relationship between different forms of ownership and performance are still lacking. In this thesis, after a brief description of the Italian agri – food sector and after an introduction including a short explanation of the definitions of performance and ownership structure, I implement a model in which the performance level (interpreted here as Return on Investments and Return on Sales) is related to variables that have been previously identified by the literature as important such as the financial variables (cash and leverage indices), the firm location (North Italy, Centre Italy, South Italy), the power concentration (lower than 25%, between 25% and 50% and between 50% and 100% of ownership control) and the specific agri – food sector (agriculture, food and beverage). Moreover we add a categorical variable representing different forms of ownership structure (public limited company, limited liability company, cooperative) that is the core of our study. All those variables are fully analysed by a preliminary descriptive analysis. As in many previous contributions we apply a panel least squares analysis for 199 Italian firms in the period 1998 – 2007 with data taken from the Bureau Van Dijck Dataset. We apply two different models in which the dependant variables are respectively the Return on Investments (ROI) and the Return on Sales (ROS) indicators. Not surprisingly we find that companies located in the North Italy representing the richest area in Italy perform better than the ones located in the Centre and South of Italy. In contrast with the Modigliani - Miller theorem financial variables could be significant and the specific sector within the agri – food market could play a relevant role. As the power concentration, we find that a strong property control (higher than 50%) or a fragmented concentration (lower than 25%) perform better. This result apparently could suggest that “hybrid” forms of concentrations could create bad functioning in the decision process. As our key variables representing the ownership structure we find that public limited companies and limited liability companies perform better than cooperatives. This is easily explainable by the fact that law establishes that cooperatives are less profit – oriented. Beyond cooperatives public limited companies perform better than limited liability companies and show a more stable path over time. Results are quite consistent when we consider both ROI and ROS as dependant variables. These results should not lead us to claim that public limited company is the “best” among all possible governance structures. First, every governance solution should be considered according to specific situations. Second more robustness analyses are needed to confirm our results. At this stage we deem these findings, the model set up and our approach represent original contributions that could stimulate fruitful future studies aimed at investigating the intriguing issue concerning the effect of ownership structure on the performance levels.

Impact of admission glucose and diabetes on recanalization and outcome after intra-arterial thrombolysis for ischaemic stroke

BACKGROUND: Stroke patients with diabetes and admission hyperglycaemia have worse outcomes than non-diabetics, with or without intravenous thrombolysis. Poor vessel recanalization was reported in diabetics treated with intravenous thrombolysis. AIMS: This study aimed to determine the impact of admission glucose and diabetes on recanalization and outcome after intra-arterial thrombolysis. METHODS: We analysed 389 patients (213 men, 176 women) treated with intra-arterial thrombolysis. The association of diabetes and admission glucose value with recanalization, outcome, mortality, and symptomatic intracranial haemorrhage was determined. Recanalization was classified according to thrombolysis in myocardial infarction grades. Outcome was measured using the modified Rankin Scale at three-months and categorized as favourable (modified Rankin Scale 0-2) or poor (modified Rankin Scale 3-6). RESULTS: The rate of partial or complete recanalization (thrombolysis in myocardial infarction 2-3) did not differ between patients with and without diabetes (67% vs. 66%; P = 1·000). Mean admission glucose values were similar in patients with poor recanalization (thrombolysis in myocardial infarction 0-1) and patients with partial or complete recanalization (thrombolysis in myocardial infarction 2-3; 7·3 vs. 7·3 mmol/l; P = 0·746). Follow-up at three-months was obtained in 388 of 389 patients. Clinical outcome was favourable (modified Rankin Scale 0-2) in 189 patients (49%) and poor (modified Rankin Scale 3-6) in 199 patients (51%). Mortality at three-months was 20%. Diabetics were more likely to have poor outcome (72% vs. 48%; P = 0·001) and to be dead (30% vs. 19%; P = 0·044) at three-months. After multivariable analysis, there remained an independent relationship between diabetes and outcome (P = 0·003; odds ratio 3·033, 95% confidence interval 1·452-6·336), but not with mortality (P = 0·310; odds ratio 1·436; 95% confidence interval 0·714-2·888). Moreover, higher age (P = 0·001; odds ratio 1·039; 95% confidence interval 1·017-1·061), higher baseline National Institutes of Health Stroke Scale score (P < 0·0001; odds ratio 1·130; 95% confidence interval 1·079-1·182), location of vessel occlusion as categorical variable (P < 0·0001), poor collaterals (P = 0·02; odds ratio 1·587; 95% confidence interval 1·076-2·341), poor vessel recanalization (P < 0·0001; odds ratio 4·713; 95% confidence interval 2·627-8·454), and higher leucocyte count (P = 0·032; odds ratio 1·094; 95% confidence interval 1·008-1·188) were independent baseline predictors of poor outcome. Higher admission glucose was associated with poor outcome (P = 0·006) and mortality (P < 0·0001). After multivariate analyses, glucose remained independently associated with poor outcome (P = 0·019; odds ratio 1·150; 95% confidence interval 1·023-1-292) and mortality (P = 0·005; odds ratio 1·183; 95% confidence interval 1052-1·331). The rate of symptomatic intracranial haemorrhage was similar in diabetics and non-diabetics (6·7% vs. 4·6%; P = 0·512). Mean admission glucose was higher in patients with symptomatic intracranial haemorrhage than without (8·58 vs. 7·26 mmol/l; P = 0·010). Multivariable analysis confirmed an independent association between admission glucose and symptomatic intracranial haemorrhage (P = 0·027; odds ratio 1·187; 95% confidence interval 1·020-1·381). CONCLUSIONS: Diabetes and glucose value on admission did not influence recanalization after intra-arterial thrombolysis; nevertheless, they were independent predictors of poor outcome after intra-arterial thrombolysis and a higher admission glucose value was an independent predictor of symptomatic intracranial haemorrhage. This indicates that factors on the capillary, cellular, or metabolic level may account for the worse outcome in patients with elevated glucose value and diabetes.

Physical activity and survival after a first myocardial infarction: The Corpus Christi Heart Project

Previous studies have demonstrated that habitual physical activity is associated with a reduced risk of incident coronary heart disease (CHD). However, the role of physical activity in lowering the risk of all-cause mortality, CHD mortality, reinfarction, or receipt of a revascularization procedure after a first myocardial infarction (MI) remains unresolved, particularly in minority populations. To investigate the associations between physical activity and risk of all-cause mortality, CHD mortality, reinfarction, and receipt of a revascularization procedure, this study was conducted among Mexican-American and non-Hispanic white women and men who survived a first MI. The Corpus Christi Heart Project, a population-based cardiovascular surveillance study, provide data which included vital status, survival time, medical history, CHD risk factor information, including level of physical activity among Mexican-American and non-Hispanic white adults who had experienced a first MI between May, 1988 and April, 1990. MI patients were interviewed at baseline and annually thereafter until their death or through May, 1995. A categorical variable was created to reflect change in level of physical activity following the first MI; categories included (1) sedentary with no change, (2) decreased activity, (3) increased activity, and (4) moderate activity with no change (the referent group). Proportional hazards regression analyses were used to assess the relationship of level of physical activity and risk of death, reinfarction, or receipt of a revascularization procedure adjusting for age, sex, ethnicity, severity of MI, and CHD risk factor status. Over a 7-year follow-up period, the relative risk (95% confidence intervals) of all-cause mortality was 4.67 (2.27, 9.60) for the sedentary-no change group, 2.33 (0.96, 5.67) for the decreased activity group, and 0.52 (0.11, 2.41) for the increased activity group. The relative risk of CHD mortality was 6.92 (2.05, 23.34) for the sedentary-no change group, 2.40 (0.55, 10.51) for the decreased activity group, and 1.58 (0.26, 9.65) for the increased activity group. The relative risk for reinfarction was 2.50 (1.52, 4.10) for the sedentary-no change group, 2.26 (1.24, 4.12) for the decreased activity group, and 0.52 (0.21, 1.32) for the increased activity group. Finally, the relative risk for receipt of a revascularization procedure was 0.65 (0.39, 1.07) for the sedentary-no change group, 0.45 (0.22, 0.92) for the decreased activity group, and 1.01 (0.51, 2.02) for the increased activity group. No interactions were observed for ethnicity or severity of first MI. These results are consistent with the hypothesis that moderate physical activity is independently associated with a lower risk of all-cause mortality, CHD mortality, and reinfarction, but not revascularization, among Mexican-American and non-Hispanic white, female and male, first MI patients. These results also support the current recommendation that physical activity plays an important role in the secondary prevention of CHD. ^

Impact of real time polymerase chain reaction technology on the therapeutic approach to treatment of staphylococcal infections

Can the early identification of the species of staphylococcus responsible for infection by the use of Real Time PCR technology influence the approach to the treatment of these infections? ^ This study was a retrospective cohort study in which two groups of patients were compared. The first group, ‘Physician Aware’ consisted of patients in whom physicians were informed of specific staphylococcal species and antibiotic sensitivity (using RT-PCR) at the time of notification of the gram stain. The second group, ‘Physician Unaware’ consisted of patients in whom treating physicians received the same information 24–72 hours later as a result of blood culture and antibiotic sensitivity determination. ^ The approach to treatment was compared between ‘Physician Aware’ and ‘Physician Unaware’ groups for three different microbiological diagnoses—namely MRSA, MSSA and no-SA (or coagulase negative Staphylococcus). ^ For a diagnosis of MRSA, the mean time interval to the initiation of Vancomycin therapy was 1.08 hours in the ‘Physician Aware’ group as compared to 5.84 hours in the ‘Physician Unaware’ group (p=0.34). ^ For a diagnosis of MSSA, the mean time interval to the initiation of specific anti-MSSA therapy with Nafcillin was 5.18 hours in the ‘Physician Aware’ group as compared to 49.8 hours in the ‘Physician Unaware’ group (p=0.007). Also, for the same diagnosis, the mean duration of empiric therapy in the ‘Physician Aware’ group was 19.68 hours as compared to 80.75 hours in the ‘Physician Unaware’ group (p=0.003) ^ For a diagnosis of no-SA or coagulase negative staphylococcus, the mean duration of empiric therapy was 35.65 hours in the ‘Physician Aware’ group as compared to 44.38 hours in the ‘Physician Unaware’ group (p=0.07). However, when treatment was considered a categorical variable and after exclusion of all cases where anti-MRS therapy was used for unrelated conditions, only 20 of 72 cases in the ‘Physician Aware’ group received treatment as compared to 48 of 106 cases in the ‘Physician Unaware’ group. ^ Conclusions. Earlier diagnosis of MRSA may not alter final treatment outcomes. However, earlier identification may lead to the earlier institution of measures to limit the spread of infection. The early diagnosis of MSSA infection, does lead to treatment with specific antibiotic therapy at an earlier stage of treatment. Also, the duration of empiric therapy is greatly reduced by early diagnosis. The early diagnosis of coagulase negative staphylococcal infection leads to a lower rate of unnecessary treatment for these infections as they are commonly considered contaminants. ^

Elevated cystatin C & heart failure prognosis a systematic review

Renal insufficiency is one of the most common co-morbidities present in heart failure (HF) patients. It has significant impact on mortality and adverse outcomes. Cystatin C has been shown as a promising marker of renal function. A systematic review of all the published studies evaluating the prognostic role of cystatin C in both acute and chronic HF was undertaken. A comprehensive literature search was conducted involving various terms of 'cystatin C' and 'heart failure' in Pubmed medline and Embase libraries using Scopus database. A total of twelve observational studies were selected in this review for detailed assessment. Six studies were performed in acute HF patients and six were performed in chronic HF patients. Cystatin C was used as a continuous variable, as quartiles/tertiles or as a categorical variable in these studies. Different mortality endpoints were reported in these studies. All twelve studies demonstrated a significant association of cystatin C with mortality. This association was found to be independent of other baseline risk factors that are known to impact HF outcomes. In both acute and chronic HF, cystatin C was not only a strong predictor of outcomes but also a better prognostic marker than creatinine and estimated glomerular filtration rate (eGFR). A combination of cystatin C with other biomarkers such as N terminal pro B- type natriuretic peptide (NT-proBNP) or creatinine also improved the risk stratification. The plausible mechanisms are renal dysfunction, inflammation or a direct effect of cystatin C on ventricular remodeling. Either alone or in combination, cystatin C is a better, accurate and a reliable biomarker for HF prognosis. ^