Use Of Nonparametric Analysis Research Articles

Improved method to determine standard values of mechanical properties of original bamboo

The standard values of mechanical properties are important performance indexes of original bamboo as a sustainable building material. Such values should be determined by combining the requirement of confidence level and the number of samples. In this paper, systematic tests of longitudinal compression, bending, longitudinal tensile, longitudinal shear, transverse compression, and transverse tensile of bamboo were performed. Based on parametric and non-parametric methods, the influencing factors of the standard values of mechanical properties of bamboo were analyzed. A calculation method and prediction formulas were proposed and the standard values of mechanical properties of bamboo were determined. The results show that the choice of parametric method to calculate the standard value of bamboo strength in the case of a small number of samples may lead to distortion of the results, and the use of non-parametric analysis can effectively reduce the error.

Current Practices in Data Analysis Procedures in Psychology: What Has Changed?

This paper analyzes current practices in psychology in the use of research methods and data analysis procedures (DAP) and aims to determine whether researchers are now using more sophisticated and advanced DAP than were employed previously. We reviewed empirical research published recently in prominent journals from the USA and Europe corresponding to the main psychological categories of Journal Citation Reports and examined research methods, number of studies, number and type of DAP, and statistical package. The 288 papers reviewed used 663 different DAP. Experimental and correlational studies were the most prevalent, depending on the specific field of psychology. Two-thirds of the papers reported a single study, although those in journals with an experimental focus typically described more. The papers mainly used parametric tests for comparison and statistical techniques for analyzing relationships among variables. Regarding the former, the most frequently used procedure was ANOVA, with mixed factorial ANOVA being the most prevalent. A decline in the use of non-parametric analysis was observed in relation to previous research. Relationships among variables were most commonly examined using regression models, with hierarchical regression and mediation analysis being the most prevalent procedures. There was also a decline in the use of stepwise regression and an increase in the use of structural equation modeling, confirmatory factor analysis, and hierarchical linear modeling. Overall, the results show that recent empirical studies published in journals belonging to the main areas of psychology are employing more varied and advanced statistical techniques of greater computational complexity.

Earnings surprises and the response of CDS markets

Purpose This paper aims to investigate the informational content of earnings surprises and accounting information in credit default swap (CDS) markets. Design/methodology/approach This paper analyzes a sample of 444 US firms and 6,907 earnings announcements. By means of parametric and non-parametric event study analysis, the paper assesses the informational value and the timeliness in the assimilation of earnings surprises by CDS rates. Findings This paper shows that earnings surprises contain material information and that CDS rates are affected by the disclosure of obligors’ financial statements. There is also supporting evidence that positive and negative surprises induce asymmetric reactions on CDS rates, especially after accounting for the credit risk of the obligor and the liquidity of the CDS contract. Finally, and perhaps the most interesting conclusion of the study, there is evidence that earnings disclosed during unstable periods lack informational value, in opposition to normal periods. Originality/value As compared with similar studies, this paper presents three novel contributions. The first concerns the use of non-parametric analysis in parallel with parametric tests to achieve robust conclusions. The second novel contribution resides in assessing whether the liquidity of the CDS contracts affects the information value of earnings surprises or the timeliness at which the information is assimilated into CDS rates. Finally, this paper also contributes to improve our understanding on the relationship between the business cycle and the informativeness of accounting information.

Continued Intimate Partner Violence During Pregnancy and After Birth and Its Effect on Child Functioning

ObjectiveTo investigate the effect of intimate partner violence (IPV) during pregnancy with continued IPV up to 6 months after birth and its effect on child functioning. DesignNonexperimental descriptive design. SettingSafe shelters and the District Attorney's office in a large urban community in the United States. ParticipantsAbused women (N = 284) who reported IPV and reached out for services. MethodsAbused women who reported IPV answered a questionnaire on the effects of abuse during pregnancy and continued abuse after birth and child behaviors. Women who continued to experience abuse during pregnancy were compared with women who did not report abuse during pregnancy and after birth. The Achenback Child Behavior Checklist was used to evaluate child behavior. Research questions were analyzed through the use of nonparametric analyses. ResultsBetween the two groups, the relationship between IPV during pregnancy and IPV during the first 6 months after birth was significant (p < .001). The relation between women who reported abuse during pregnancy and conception rape was significant (p < .001). Most abused women (76%) were not screened for IPV during pregnancy (p = .025). Significant findings related to child behaviors and IPV during pregnancy were found for internalizing behaviors (p < .009), externalizing behaviors (p < .001), and total behavioral problems (p < .001). ConclusionIntimate partner violence during pregnancy increases the risk of IPV 6 months after birth. These findings also indicated a negative intergenerational effect of IPV during pregnancy on child behavior. Screening for IPV during pregnancy is vital to interrupt ongoing IPV and possible negative outcomes for mother and child.

La influencia de las estrategias en la Prueba de Acceso a la Universidad en los conocimientos matemáticos de los estudiantes de Ingeniería

Se analiza cuál es el nivel de conocimientos de Cálculo de 402 estudiantes de nuevo ingreso en diversos grados universitarios de Ingeniería durante los cursos 2011-2012, 2012-2013 y 2013-2014, en función de su vía de entrada en la Universidad y de las diferentes estrategias que han utilizado en la Prueba de Acceso a la Universidad. Se utiliza para ello un cuestionario anónimo, diseñado por los autores: a partir de los resultados de este cuestionario se ha determinado la presencia de hasta cuatro grupos significativos de estudiantes de nuevo acceso. Un primer grupo lo forman los estudiantes de Bachillerato que eligieron examinarse de Matemáticas II en la PAU y la superaron; un segundo grupo lo forman los estudiantes de Bachillerato que no superaron esta prueba, hay un tercer grupo de estudiantes que no se han presentado al examen, y un cuarto grupo de alumnos procedentes de los Ciclos Formativos de Grado Superior. En el análisis se utilizan técnicas no paramétricas (análisis post-hoc basados en la prueba de Kruskal- Wallis) que indican que estos grupos tienen un nivel significativamente diferente en los conocimientos básicos de Cálculo medidos por el cuestionario. Esta situación tiene una clara influencia en la labor docente en los primeros cursos universitarios, pues es necesaria una labor importante de adaptación didáctica en las asignaturas de contenido matemáticos para paliar estas deficiencias en los conocimientos matemáticos básicos.

English

The aim of this study was to evaluate different alternative products, foliar sprayed either alone or in combination with fungicide fluazinam, to control white mold in soybean at three locations: Arapoti, Maua-da-Serra, and Pinhao, in Parana state, southern Brazil. The following chemical products were used: sodium dichloroisocyanurate, benzalkonium chloride, pyroligneous extract, sodium hypochlorite, cobalt + molybdenum, sucrose, sodium bicarbonate and acibenzolar-S-methyl. Incidence, severity, yield, and number of sclerotia produced were analyzed. The majority of the variables did not follow the normal distribution of the data according to the Kolmogorov-Smirnov test; therefore, the use of non-parametric analysis was necessary. The analysis of all the treatments individually revealed no significant effects so it was decided to separate the analysis into the following groups of treatments: ‘control’, treatments using alternative products (‘alternatives’), treatment only with fungicide (‘fungicide’) and treatments with alternative products and fungicide (‘alternatives + fungicide’). In Arapoti, no significant differences for any variables were observed. In Maua-da-Serra, the ‘fungicide’ and ‘alternatives + fungicide’ had the lowest incidence and number of sclerotia, with higher yield when compared to ‘control’ and ‘alternatives’. No differences were observed for severity. In Pinhao, the ‘fungicide’ and ‘alternatives + fungicide’ were superior for incidence, number of sclerotia produced, and yield when compared to the ‘control’ and ‘alternatives’. The ‘alternatives + fungicide’ showed significantly lower severity when compared to the control, ‘alternatives’ and ‘fungicide’ in Pinhao experiment. In conclusion, the alternative products applied in combination with fluazinam resulted in lower severity of white mold in soybean in the experiment conducted in Pinhao, and the application of fluazinam alone or in combination with alternative products, was efficient to control white mold in soybean in locations with high disease incidence.

Governança corporativa, eficiência, produtividade e desempenho

Há um grande número de pesquisas cujo objetivo principal é a busca por uma relação empírica entre governança corporativa e desempenho. Os estudos que visam demonstrar essa relação caracterizam-se pela utilização de indicadores contábeis e indicadores de análise de ações, conjugados com o uso de métodos econométricos. No entanto, existem sugestões para que se estabeleçam medidas alternativas de desempenho, como a utilização de análises não paramétricas. Mensurar o desempenho com o uso de outras técnicas de análise, para avaliar a relação entre governança corporativa e desempenho, representa uma contribuição relevante para esse campo de estudo. Por meio da utilização da técnica não paramétrica da análise envoltória de dados, o objetivo principal deste trabalho é verificar se existem diferenças entre a eficiência técnica e a produtividade de empresas dos segmentos de governança corporativa com a eficiência técnica e a produtividade de empresas de outros segmentos da Bovespa. A aplicação do teste t de diferença de médias demonstrou que não há diferenças estatisticamente significativas entre os escores de eficiências técnica dos grupos de empresas com e sem governança. No entanto, nos anos de 2008 e 2009 as empresas com ações negociadas em outros segmentos da Bovespa apresentaram um melhor nível de eficiência técnica. Resultados semelhantes foram verificados com o índice de produtividade de Malmquist. Com a finalidade de estabelecer parâmetros na comparação do desempenho obtido por meio dos escores de eficiência, foram analisadas as métricas tradicionais de mensuração do valor, Q de Tobin e Valor da Empresa. Observou-se, nos três anos analisados, que o valor de mercado das empresas dos segmentos de governança corporativa é inferior ao das empresas de outros segmentos de negociação de ações. Esta pesquisa avança em relação a contribuições anteriores por ter como foco a determinação do desempenho, também, por meio da mensuração da eficiência técnica e do crescimento da produtividade. Os resultados permitem um novo ângulo de análise na avaliação das empresas, de forma específica para a adoção de boas práticas de governança corporativa.

A hybrid decision tree based methodology for event studies and its application to e-commerce initiative announcements

The event study methodology has been applied in various business disciplines. This methodology typically has two goals: (1) to determine whether an event such as the announcement of an e-commerce initiative in the public media leads to cumulative abnormal returns (CAR); and (2) to examine the factors that influence the observed CAR. Most studies have used parametric statistical analysis in estimating CAR and regression for achieving the second goal. In this paper, we propose a hybrid methodology that involves using nonparametric statistical analysis to obtain the first goal, and the use of Decision Tree (DT) induction as a novel approach to reach the second goal. We apply the hybrid methodology to e-commerce announcements. The use of nonparametric analysis enables us to address some of the prior concerns of event study research in the e-commerce domain with regard to the limitations of short run event windows. The use of the novel DT-based approach leads to additional insights beyond what is reported in the literature through the examination of contingency effects. Specifically, our results indicate that the impact of Governance, Customer Type and Firm Type on CAR is contingent on the innovativeness of the e-commerce initiatives. Our study makes both methodological and theoretical contributions regarding the use of DT induction and nonparametric analysis in event studies especially in situations where prior studies present mixed results and where there are concerns about return variability. We present both research and managerial implications of the findings.

Nitric oxide mediation of cardiac receptor reflex responses in the pregnant rat

OBJECTIVES: Our purpose was to determine the contribution of centrally released nitric oxide to baseline sympathetic tone and reflex cardiovascular responses to cardiac stretch in the pregnant rat. STUDY DESIGN: Baseline blood pressure and renal sympathetic nerve activity and reflex changes in these variables in response to intraatrial saline solution injections were measured in anesthetized pregnant ( n = 24) and virgin ( n = 27) rats before and after bilateral microinjection of L-nitroarginine methyl ester (0.01 to 1 μmol) into the dorsal medulla. Data were analyzed with use of nonparametric analysis of variance. RESULTS: L-Nitroarginine methyl ester microinjection altered basal blood pressure and sympathetic nerve activity ( p < 0.05) in virgin but not pregnant rats. L-Nitroarginine methyl ester significantly and equivalently attenuated the reflex sympathoinhibitory and depressor responses to cardiac stretch for 40 minutes in pregnant and virgin animals. CONCLUSION: Central nitric oxide does not modulate basal sympathetic tone in the pregnant rat but is released in the medulla in response to cardiac stretch and plays a role in reflex cardiovascular responses similar to that in virgin rats.(Am J Obstet Gynecol 1997;177:1502-8.)

Proficiency testing of selected antigen and antibody tests for use in dogs and cats

Objective To determine the correlation of seroimmunologic test results between reference and nonreference laboratories. Design Retrospective data analysis. Procedure Serum samples obtained from naturally infected dogs and cats were distributed to reference and nonreference laboratories for seroimmunologic testing. Correlation of test results was evaluated by use of nonparametric analysis. Results Correlation coefficients were high between laboratory groups for samples tested for feline immunodeficiency virus antibodies, FeLV antigen, and toxoplasmosis antibodies in cats. Results for feline immunodeficiency virus antibody tests from reference laboratories were more likely to be positive than results from nonreference laboratories. Test results for feline infectious peritonitis antibodies, antinuclear antibodies, and Borrelia antibodies in cats were not significant. Coefficient correlations were significant for results of heartworm antigen, Brucella antibodies, Toxoplasma antibodies, antinuclear antibodies, and rheumatoid factor in dogs. Results for Borrelia antibodies were not correlated between laboratory groups. Clinical Implications Results were highly correlated between reference and nonreference laboratories for 8 of 14 seroimmunologic tests. Seroimmunologic tests for use in cats were less correlated as a group than those for use in dogs. Poor correlation of results between laboratories was attributed to variations in control agents, antigens, reagents, technical expertise, and cutoff values and end-point titers used for diagnosis. (J Am Vet Med Assoc 1996,209:914-917)

Statistical analyses of microbial counts of dental plaque.

Samples of bacterial plaque were removed from the mesial surfaces of the upper canine, and upper and lower first molars from 20 young adult subjects with gingivitis but without attachment loss. Absolute counts and proportions of 23 categories of microorganisms were enumerated by darkfield microscopy and on selective and elective media. The differences in means of absolute counts of each microbial group on the tooth surfaces were compared by one‐ and two‐way analysis of variance using untransformed, log and square root transformed values. Data were compared with zero values or with zero values replaced with a minimum threshold of detection values of 105 for microscopic counts and 103 for cultural counts. The untransformed and transformed data with and without minimum thresholds replacing zero were tested for conformity to a normal distribution. Differences in counts of each microbial group on the different tooth surfaces were sought by the nonparametric Kruskal‐Wallis one‐way analysis of variance and the Friedman two‐way analysis of variance. Differences in percentages of each microbial group were also sought using the same analyses on untransformed and arc sine transformed percentages.None of the untransformed absolute counts conformed to a normal distribution. Log transformation, particularly with minimum threshold values replacing zero, was more successful in fitting the data to a normal distribution than square root transformation. However, few groups conformed to a normal distribution after either transformation. Percentages with or without arc sine transformation in most instances were not normally distributed. Substitution of minimum thresholds for zero values did not markedly alter significance testing, but did help to decrease confidence intervals of the means, particularly of log transformed counts. Significant differences revealed by the nonparametric analyses of absolute counts were most similar to one‐ and two‐way ANOVA of log transformed absolute counts. The use of nonparametric analyses for microbial counts is recommended because of the variability of the count data and the difficulties in interpreting zero values and in transforming the data to a normal distribution.

Use of nonparametric analysis of cardiorespiratory variables as early predictors of death and survival in postoperative patients

Use of nonparametric analysis of cardiorespiratory variables as early predictors of death and survival in postoperative patients