Incongruence between test statistics and P values in medical papers

Given an observed test statistic and its degrees of freedom, one may compute the observed P value with most statistical packages. It is unknown to what extent test statistics and P values are congruent in published medical papers. Methods:We checked the congruence of statistical results reported in all the papers of volumes 409–412 of Nature (2001) and a random sample of 63 results from volumes 322–323 of BMJ (2001). We also tested whether the frequencies of the last digit of a sample of 610 test statistics deviated from a uniform distribution (i.e., equally probable digits).Results: 11.6% (21 of 181) and 11.1% (7 of 63) of the statistical results published in Nature and BMJ respectively during 2001 were incongruent, probably mostly due to rounding, transcription, or type-setting errors. At least one such error appeared in 38% and 25% of the papers of Nature and BMJ, respectively. In 12% of the cases, the significance level might change one or more orders of magnitude. The frequencies of the last digit of statistics deviated from the uniform distribution and suggested digit preference in rounding and reporting.Conclusions: this incongruence of test statistics and P values is another example that statistical practice is generally poor, even in the most renowned scientific journals, and that quality of papers should be more controlled and valued

Comparing and validating hypothesis test procedures: Graphical and numerical tools

When the behaviour of a specific hypothesis test statistic is studied by aMonte Carlo experiment, the usual way to describe its quality is by givingthe empirical level of the test. As an alternative to this procedure, we usethe empirical distribution of the obtained \emph{p-}values and exploit itsinformation both graphically and numerically.

Bootstrapping pairs in Distance-Based Regression

La regressió basada en distàncies és un mètode de predicció que consisteix en dos passos: a partir de les distàncies entre observacions obtenim les variables latents, les quals passen a ser els regressors en un model lineal de mínims quadrats ordinaris. Les distàncies les calculem a partir dels predictors originals fent us d'una funció de dissimilaritats adequada. Donat que, en general, els regressors estan relacionats de manera no lineal amb la resposta, la seva selecció amb el test F usual no és possible. En aquest treball proposem una solució a aquest problema de selecció de predictors definint tests estadístics generalitzats i adaptant un mètode de bootstrap no paramètric per a l'estimació dels p-valors. Incluim un exemple numèric amb dades de l'assegurança d'automòbils.

Bootstrapping pairs in Distance-Based Regression

La regressió basada en distàncies és un mètode de predicció que consisteix en dos passos: a partir de les distàncies entre observacions obtenim les variables latents, les quals passen a ser els regressors en un model lineal de mínims quadrats ordinaris. Les distàncies les calculem a partir dels predictors originals fent us d'una funció de dissimilaritats adequada. Donat que, en general, els regressors estan relacionats de manera no lineal amb la resposta, la seva selecció amb el test F usual no és possible. En aquest treball proposem una solució a aquest problema de selecció de predictors definint tests estadístics generalitzats i adaptant un mètode de bootstrap no paramètric per a l'estimació dels p-valors. Incluim un exemple numèric amb dades de l'assegurança d'automòbils.

Random assignment of intervention points in two phase single-case designs: data-division-specific distributions

The present study explores the statistical properties of a randomization test based on the random assignment of the intervention point in a two-phase (AB) single-case design. The focus is on randomization distributions constructed with the values of the test statistic for all possible random assignments and used to obtain p-values. The shape of those distributions is investigated for each specific data division defined by the moment in which the intervention is introduced. Another aim of the study consisted in testing the detection of inexistent effects (i.e., production of false alarms) in autocorrelated data series, in which the assumption of exchangeability between observations may be untenable. In this way, it was possible to compare nominal and empirical Type I error rates in order to obtain evidence on the statistical validity of the randomization test for each individual data division. The results suggest that when either of the two phases has considerably less measurement times, Type I errors may be too probable and, hence, the decision making process to be carried out by applied researchers may be jeopardized.

Assigning and combining probabilities in single-case studies

There is currently a considerable diversity of quantitative measures available for summarizing the results in single-case studies. Given that the interpretation of some of them is difficult due to the lack of established benchmarks, the current paper proposes an approach for obtaining further numerical evidence on the importance of the results, complementing the substantive criteria, visual analysis, and primary summary measures. This additional evidence consists of obtaining the statistical significance of the outcome when referred to the corresponding sampling distribution. This sampling distribution is formed by the values of the outcomes (expressed as data nonoverlap, R-squared, etc.) in case the intervention is ineffective. The approach proposed here is intended to offer the outcome"s probability of being as extreme when there is no treatment effect without the need for some assumptions that cannot be checked with guarantees. Following this approach, researchers would compare their outcomes to reference values rather than constructing the sampling distributions themselves. The integration of single-case studies is problematic, when different metrics are used across primary studies and not all raw data are available. Via the approach for assigning p values it is possible to combine the results of similar studies regardless of the primary effect size indicator. The alternatives for combining probabilities are discussed in the context of single-case studies pointing out two potentially useful methods one based on a weighted average and the other on the binomial test.

Polygenic determinants of white matter volume derived from GWAS lack reproducibility in a replicate sample

A recent publication reported an exciting polygenic effect of schizophrenia (SCZ) risk variants, identified by a large genome-wide association study (GWAS), on total brain and white matter volumes in schizophrenic patients and, even more prominently, in healthy subjects. The aim of the present work was to replicate and then potentially extend these findings. According to the original publication, polygenic risk scores using single nucleotide polymorphism (SNP) information of SCZ GWAS (polygenic SCZ risk scores; PSS) were calculated in 122 healthy subjects, enrolled in a structural magnetic resonance imaging (MRI) study. These scores were computed based on P-values and odds ratios available through the Psychiatric GWAS Consortium. In addition, polygenic white matter scores (PWM) were calculated, using the respective SNP subset in the original publication. None of the polygenic scores, either PSS or PWM, were found to be associated with total brain, white matter or gray matter volume in our replicate sample. Minor differences between the original and the present study that might have contributed to lack of reproducibility (but unlikely explain it fully), are number of subjects, ethnicity, age distribution, array technology, SNP imputation quality and MRI scanner type. In contrast to the original publication, our results do not reveal the slightest signal of association of the described sets of GWAS-identified SCZ risk variants with brain volumes in adults. Caution is indicated in interpreting studies building on polygenic risk scores without replication sample.

Assigning and combining probabilities in single-case designs: A second study

The present study builds on a previous proposal for assigning probabilities to the outcomes computed using different primary indicators in single-case studies. These probabilities are obtained comparing the outcome to previously tabulated reference values and reflect the likelihood of the results in case there was no intervention effect. The current study explores how well different metrics are translated into p values in the context of simulation data. Furthermore, two published multiple baseline data sets are used to illustrate how well the probabilities could reflect the intervention effectiveness as assessed by the original authors. Finally, the importance of which primary indicator is used in each data set to be integrated is explored; two ways of combining probabilities are used: a weighted average and a binomial test. The results indicate that the translation into p values works well for the two nonoverlap procedures, with the results for the regression-based procedure diverging due to some undesirable features of its performance. These p values, both when taken individually and when combined, were well-aligned with the effectiveness for the real-life data. The results suggest that assigning probabilities can be useful for translating the primary measure into the same metric, using these probabilities as additional evidence on the importance of behavioral change, complementing visual analysis and professional's judgments.

Olympic education experiences: the sponsorship in the promotion of Olympic values

This text was presented at the 16th International Seminar on Olympic Studies for Postgraduate Students that was organised by the International Olympic Academy in Ancient Olympia, from 1st to 30th July 2008. First here are reported, fundamental concepts on Olympics such as the Olympic values and the educational mandate of Pierre de Coubertin, the Olympic brand and symbols, the sponsorship and the Olympic partner programme. Then there is a chapter regarding the Top sponsors educational initiatives on Olympic values, and specially, describing the Olympic sponsors involvement in education and Top sponsors educational activities. And finally, the author analyses the sponsorship role in the promotion of Olympic Values Education, providing conclusions, comments on future and perspectives and some recommendations.

The new role of the mass media in the construction of sport and Olympic values

This paper was presented in the International Symposium on Toward the Creation of New-Sport Cultures, undertaken in Osaka, Japan, in January 28, 1996. The main purpose is to make an interpretation of the cultural values of sport and Olympism in contemporary society, considering the enormous influence that the media have on them.

Un programa psicosocial: programa psicoestimulatiu integral (P.P.I.) amb persones afectades de malaltia d' Alzheimer

L'any 2011 la malaltia d'Alzheimer es situava com la quarta causa de mort més freqüent amb un augment de fins a 11.907, més del doble de morts que l'any 2000 (INE). Aquestes dades demostren l'augment del número de persones que pateixen una demència a mesura que envelleixen i una de les explicacions és l'augment de l'esperança de vida. Per aquest motiu l'estudi de la qualitat de vida ha adquirit una gran importància des de la dècada dels 90. La qualitat de vida és un concepte especialment subjectiu pel fet que cada persona la viu segons la pròpia percepció de salut i benestar i el grau d'adaptació a l'entorn que l'envolta. Per aquest motiu es planteja un programa de psicoestimulació integral (PPI) centrat en les individualitats de cada persona: valors, interessos, història ocupacional..., des de la filosofia de la Teràpia Ocupacional. El projecte està elaborat mitjançant la metodologia qualitativa utilitzant l'enquesta en profunditat semi-estructurada per a realitzar les entrevistes i obtenir la informació principal a l'inici i al final del programa juntament amb tota la informació que s'obtingui de l'observació participant del dia a dia de cada un dels professionals per tal d'estudiar fins a quin punt aquesta atenció centrada en la persona contribueix a millorar la qualitat de vida de les persones afectades de Malaltia d'Alzheimer que reben tractaments no farmacològics com el proposat en aquest projecte. Com a tot estudi es poden trobar alguns factors condicionants com pot ser l'evolució pròpia de la malaltia amb les conseqüències negatives que això comporta i/o el número de participants que formen la mostra.

Personality, social values, and marital satisfaction as predictors of parents’ rearing styles

Los estilos de crianza parentales pueden afectar la conducta y socialización de los adolescentes, por lo que es de interés conocer cómo algunas variables psicológicas de los padres se relacionan con los estilos de crianza. Este estudio tiene el objetivo de analizar los estilos de crianza de los padres, valores sociales (prestigio social, orden, benevolencia, y conservadurismo-liberalismo), los cinco grandes factores de personalidad, y la satisfacción de pareja (acuerdo general, afecto, satisfacción, y cohesión) en los padres de adolescentes. Este es un estudio prospectivo basado en método de análisis correlacional. Se encontró que los estilos educativos definidos por el cariño y aceptación se relacionan con los rasgos de personalidad como responsabilidad y estabilidad emocional, alta satisfacción de pareja y preferencia por valores prosociales. Al contrario, los estilos de crianza de sobreprotección y favoritismo se relacionan con baja amabilidad y baja apertura el poco ajuste de pareja con falta de cohesión y valores sociales definidos por falta de benevolencia y preferencia por valores de prestigio social.

Two different epidemiological scenarios of border disease in the populations of Pyrenean chamois (Rupicapra p. pyrenaica) after the first disease outbreaks

Since 2001 several outbreaks of a new disease associated with Border disease virus (BDV) infection have caused important declines in Pyrenean chamois (Rupicapra pyrenaica) populations in the Pyrenees. The goal of this study was to analyze the post-outbreak BDV epidemiology in the first two areas affected by disease with the aim to establish if the infection has become endemic. We also investigated if BDV infected wild and domestic ruminants sharing habitat with chamois. Unexpectedly, we found different epidemiological scenarios in each population. Since the disease outbreaks, some chamois populations recuperated quickly, while others did not recover as expected. In chamois from the first areas, prevalence was high (73.47%) and constant throughout the whole study period and did not differ between chamois born before and after the BDV outbreak; in all, BDV was detected by RT-PCR in six chamois. In the other areas, prevalence was lower (52.79%) and decreased during the study period; as well, prevalence was significantly lower in chamois born after the disease outbreak. No BDV were detected in this population. A comparative virus neutralisation test performed with four BDV strains and one Bovine viral diarrhoea virus (BVDV) strain showed that all the chamois had BDV-specific antibodies. Pestivirus antibodies were detected in all the rest of analyzed species, with low prevalence values in wild ruminants and moderate values in domestic ruminants. No viruses were detected in these species. These results confirm the hypothesis that outbreaks of BDV infection only affect the Pyrenean chamois, although other wild ruminants can occasionally be infected. In conclusion, two different scenarios have appeared since the first border disease outbreaks in Pyrenean chamois: on the one hand frequent BDV circulation with possible negative impact on population dynamics in some areas and on the other, lack of virus circulation and quick recovery of the chamois population.

V0 production in p+A collisions at √s = 41.6 GeV

Inclusive doubly differential cross sections d 2 σ pA /dx F   dp T 2 as a function of Feynman-x (x F ) and transverse momentum (p T ) for the production of K S 0 , Λ and Λ¯ in proton-nucleus interactions at 920 GeV are presented. The measurements were performed by HERA-B in the negative x F range (−0.12p to p T =1.6 GeV/c. Results for three target materials: carbon, titanium and tungsten are given. The ratios of production cross sections are presented and discussed. The Cronin effect is clearly observed for all three V 0 species. The atomic number dependence is parameterized as σ pA =σ pN ⋅A α where σ pN is the proton-nucleon cross section. The measured values of α are all near one. The results are compared with EPOS 1.67 and PYTHIA 6.3. EPOS reproduces the data to within ≈20% except at very low transverse momentum.

Metabolic origin of δ15N values in nitrogenous compounds from Brassica napus L. leaves

Nitrogen isotope composition (δ15N) in plant organic matter is currently used as a natural tracer of nitrogen acquisition efficiency. However, the δ15N value of whole leaf material does not properly reflect the way in which N is assimilated because isotope fractionations along metabolic reactions may cause substantial differences among leaf compounds. In other words, any change in metabolic composition or allocation pattern may cause undesirable variability in leaf δ15N. Here, we investigated the δ15N in different leaf fractions and individual metabolites from rapeseed (Brassica napus) leaves. We show that there were substantial differences in δ15N between nitrogenous compounds (up to 30 ) and the content in (15N enriched) nitrate had a clear influence on leaf δ15N. Using a simple steady-state model of day metabolism, we suggest that the δ15N value in major amino acids was mostly explained by isotope fractionation associated with isotope effects on enzyme-catalysed reactions in primary nitrogen metabolism. δ15N values were further influenced by light versus dark conditions and the probable occurrence of alternative biosynthetic pathways. We conclude that both biochemical pathways (that fractionate between isotopes) and nitrogen sources (used for amino acid production) should be considered when interpreting the δ15N value of leaf nitrogenous compounds