Home About us Contact
|
Home About us Contact | ||
|
|
||
Standard Statistical Methods (standard + statistical_methods)
Selected AbstractsSmoothing Observational Data: A Philosophy and Implementation for the Health SciencesINTERNATIONAL STATISTICAL REVIEW, Issue 1 2006Sander Greenland Summary Standard statistical methods (such as regression analysis) presume the data are generated by an identifiable random process, and attempt to model that process in a parsimonious fashion. In contrast, observational data in the health sciences are generated by complex, nonidentified, and largely nonrandom mechanisms, and are analyzed to form inferences on latent structures. Despite this gap between the methods and reality, most observational data analysis comprises application of standard methods, followed by narrative discussion of the problems of entailed by doing so. Alternative approaches employ latent-structure models that include components for nonidentified mechanisms. Standard methods can still be useful, however, provided their modeling philosophy is modified to encourage preservation of structure, rather than achieving parsimonious description. With this modification they can be viewed as smoothing or filtering methods for separating noise from signal before the task of latent-structure modeling begins. I here give a detailed justification of this view, and a hierarchical-modeling implementation that can be carried out with popular software. Concepts are illustrated in the smoothing of a contingency table from an analysis of magnetic fields and childhood leukemia. Résumé Les méthodes statistiques standard (telles que l'analyse par régression) supposent que les données sont générées par un processus aléatoire identifiable, et tentent de modéliser ce processus d'une façon parcimonieuse. Par contraste, les données d'observation dans les sciences de la santé sont générées par des mécanismes complexes, non identifiés et largement non aléatoires, et elles sont analysées pour tirer des conclusions sur les structures latentes. En dépit de cet écart entre les méthodes et la réalité, l'analyse de la plupart des données d'observation comprend l'application des méthodes standard, suivies par la discussion narrative des problèmes engendrés par ces procédés. Les approches alternatives emploient des modèles à structure latente qui incluent des composantes pour les mécanismes non identifiés. Cependant, les méthodes standard peuvent encor être utiles, à condition que la conception de leur modélisation soit modifiée pour encourager la préservation de la structure, plutôt que d'arriver à une description parcimonieuse. Avec cette modification elles peuvent être considérées comme des méthodes de lissage ou de filtrage pour séparer le bruit du signal avant que commence le travail de modélisation à structure latente. Je donne ici une justification detaillée de cette opinion et je présente une mise en oeuvre de modélisation hiérachique qui peut être réalisée avec un logiciel courant. Les concepts sont illustrés dans le lissage d'un tableau de contingence à partir d'une analyse de champs magnétiques et de leucémie enfantine. [source] Modulation of salivation and heartburn in response to the site of acid infusion in the human oesophagusALIMENTARY PHARMACOLOGY & THERAPEUTICS, Issue 6 2010S. K. Dutta Summary Background, The pathogenesis of gastro-oesophageal reflux disease includes increased acid reflux, reduced salivation and impaired peristalsis. This may depend upon the height of acid wave and magnitude of oesophageal mucosal exposure. Interestingly, the effect of site of acid infusion upon salivary secretion and heartburn has not been examined in any detail. Aim, To examine whether acid infusion in the upper oesophagus may cause increased salivation and heartburn as compared with acid infusion in the lower oesophagus. Methods, Twelve healthy male subjects (mean age 30) received infusions of HCl, citric acid and acetic acid at 10 and 20 cm above the lower oesophageal sphincter (LES) for fixed time periods. Parotid saliva collected periodically and heartburn severity scored using standardized scale. Standard statistical methods (paired t -tests, analysis of variance) were used to determine the significance of results. Results, Acid infusion in the upper oesophagus increased parotid flow rate as compared with that in the lower oesophagus (P < 0.05). Likewise, there was a significantly increased heartburn score at 20 cm as well as 10 cm above LES (P < 0.05) as compared with that in the stomach. Conclusion, These data suggest a significant increase in salivation and heartburn in response to acid infusion in the upper vs. lower part of the oesophagus. [source] Cerebral metastasis and other central nervous system complications of pleuropulmonary blastoma,,PEDIATRIC BLOOD & CANCER, Issue 3 2007John R. Priest MD Abstract Background Pleuropulmonary blastoma (PPB) is a rare tumor of pleura and lung in young children. Central nervous system (CNS) complications, particularly cerebral parenchymal metastases, occur in aggressive forms of PPB: Types II and III PPB. This article evaluates cerebral and meningeal metastases, cerebrovascular events (CVA) caused by tumor emboli, spinal cord complications, and intracranial second malignancies in PPB. Procedure International PPB Registry and literature cases were evaluated for CNS events. Cerebral metastasis patients were evaluated for gender, side of origin of PPB, PPB Type, interval from diagnosis to metastasis, status of chest disease, treatment, and outcome. Standard statistical methods were used to calculate the cumulative probability of cerebral metastasis and survival following metastasis. Results Thirty-nine cases of cerebral metastasis were identified in 5/53 Registry Type II cases, 15/44 Registry Type III cases, and 19/143 literature Type II/III cases. Metastases occurred 1,60, median 11.5 months after diagnosis. Chest disease was controlled in 50% of children at time of metastasis. The cumulative probability of cerebral metastasis by 5 years from diagnosis was 11% for Type II patients (95%CI (confidence interval): 2,20%) and 54% for Type III patients (95%CI: 31,76%). Seven children survive cerebral metastasis. Other CNS complications were post-operative CVA (five cases), spinal cord invasion or compression (six), leptomeningeal disease (three), and second intracranial malignancies (two). Conclusions Cerebral metastasis is more frequent in PPB than in other childhood sarcomas. Clinicians should screen for this complication. Diverse other CNS complications are less common and require careful diagnosis. Pediatr Blood Cancer 2007;49:266,273. © 2006 Wiley-Liss, Inc. [source] Heterogeneity, speciation/extinction history and climate: explaining regional plant diversity patterns in the Cape Floristic RegionDIVERSITY AND DISTRIBUTIONS, Issue 3 2002R. M. Cowling Abstract. This paper investigates the role of heterogeneity and speciation/extinction history in explaining variation in regional scale (c. 0.1,3000 km2) plant diversity in the Cape Floristic Region of south-western Africa, a species- and endemic-rich biogeographical region. We used species-area analysis and analysis of covariance to investigate geographical (east vs. west) and topographic (lowland vs. montane) patterns of diversity. We used community diversity as a surrogate for biological heterogeneity, and the diversity of naturally rare species in quarter degree squares as an indicator of differences in speciation/extinction histories across the study region. We then used standard statistical methods to analyse geographical and topographic patterns of these two measures. There was a clear geographical diversity pattern (richer in the west), while a topographic pattern (richer in mountains) was evident only in the west. The geographical boundary coincided with a transition from the reliable winter-rainfall zone (west) to the less reliable non-seasonal rainfall zone (east). Community diversity, or biological heterogeneity, showed no significant variation in relation to geography and topography. Diversity patterns of rare species mirrored the diversity pattern for all species. We hypothesize that regional diversity patterns are the product of different speciation and extinction histories, leading to different steady-state diversities. Greater Pleistocene climatic stability in the west would have resulted in higher rates of speciation and lower rates of extinction than in the east, where for the most, Pleistocene climates would not have favoured Cape lineages. A more parsimonious hypothesis is that the more predictable seasonal rainfall of the west would have favoured non-sprouting plants and that this, in turn, resulted in higher speciation and lower extinction rates. Both hypotheses are consistent with the higher incidence of rare species in the west, and higher levels of beta and gamma diversity there, associated with the turnover of species along environmental and geographical gradients, respectively. These rare species do not contribute to community patterns; hence, biological heterogeneity is uniform across the region. The weak topography pattern of diversity in the west arises from higher speciation rates and lower extinction rates in the topographically complex mountains, rather than from the influence of environmental heterogeneity on diversity. [source] Adjusting for mortality effects in chronic toxicity testing: Mixture model approachENVIRONMENTAL TOXICOLOGY & CHEMISTRY, Issue 1 2000Shin Cheng David Wang Abstract Chronic toxicity tests, such as the Ceriodaphnia dubia 7-d test are typically analyzed using standard statistical methods such as analysis of variance or regression. Recent research has emphasized the use of Poisson regression or more generalized regression for the analysis of the fecundity data from these studies. A possible problem in using standard statistical techniques is that mortality may occur from toxicant effects as well as reduced fecundity. A mixture model that accounts for fecundity and mortality is proposed for the analysis of data arising from these studies. Inferences about key parameters in the model are discussed. A joint estimate of the inhibition concentration is proposed based on the model. Confidence interval estimation via the bootstrap method is discussed. An example is given for a study involving copper and mercury. [source] Ecotourism and biodiversity conservation in Jozani,Chwaka Bay National Park, ZanzibarAFRICAN JOURNAL OF ECOLOGY, Issue 2009Layla A. Salum Abstract This study is based on a study undertaken to assess how ecotourism has influenced biodiversity conservation in Jozani,Chwaka Bay National Park (JCBNP). It involved two communities surrounding the park, namely Pete and Kitogani. Field data were collected using structured questionnaires, key informant interviews and field observations. Questionnaires were administered to 76 households, whereas key informant interviews were conducted with foresters and JCBNP officials. Data analysis was undertaken using standard statistical methods. Findings from the study show that biodiversity management in the JCBNP has improved considerably after the introduction of ecotourism. The number of endemic colobus monkeys (Piliocolobus kirkii) and other rare species has increased. However, this achievement has been attained by restricting surrounding communities from using forest resources without providing alternative sources of livelihood. Findings also show that the benefits from ecotourism do not reach individual households, but the community as whole, in form of various social services. This has caused some resentment among the local people leading to their reluctance to reduce their direct use of ecosystem services available in the JCBNP, claiming that they cannot sustain their livelihood without such services. This has become a major source of conflict between the JCBNP and surrounding communities. Increased awareness and knowledge on biodiversity conservation would be needed for the communities surrounding the park to realize the potential and long-term benefits of ecotourism, and hence the need for their increased involvement in biodiversity management. [source] A Comparison of Neural Network, Statistical Methods, and Variable Choice for Life Insurers' Financial Distress PredictionJOURNAL OF RISK AND INSURANCE, Issue 3 2006Patrick L. Brockett This study examines the effect of the statistical/mathematical model selected and the variable set considered on the ability to identify financially troubled life insurers. Models considered are two artificial neural network methods (back-propagation and learning vector quantization (LVQ)) and two more standard statistical methods (multiple discriminant analysis and logistic regression analysis). The variable sets considered are the insurance regulatory information system (IRIS) variables, the financial analysis solvency tracking (FAST) variables, and Texas early warning information system (EWIS) variables, and a data set consisting of twenty-two variables selected by us in conjunction with the research staff at TDI and a review of the insolvency prediction literature. The results show that the back-propagation (BP) and LVQ outperform the traditional statistical approaches for all four variable sets with a consistent superiority across the two different evaluation criteria (total misclassification cost and resubstitution risk criteria), and that the twenty-two variables and the Texas EWIS variable sets are more efficient than the IRIS and the FAST variable sets for identification of financially troubled life insurers in most comparisons. [source] Ambulatory foot temperature measurement: A new technique in polyneuropathy evaluationMUSCLE AND NERVE, Issue 6 2003Peter B. Kang MD Abstract Complaints of abnormal foot temperature are common among patients with polyneuropathy. However, there is no published method of ambulatory foot temperature measurement to identify possible thermoregulatory disturbances in these patients. We configured a digital electronic thermometer and thermocouple to measure and record distal foot and ambient temperatures simultaneously every minute for 24 to 48 h. Sixteen patients with polyneuropathy and 5 normal subjects were studied; 12 patients with polyneuropathy and 4 normal subjects had at least 24 h of successful recording. The data obtained from these patients were consistent and easily summarized by standard statistical methods. In the others, technical difficulties produced nonphysiological readings. In the patients with polyneuropathy, changes in foot temperature mirrored ambient temperature fluctuations more closely than in normal subjects. This technique shows promise in studying temperature regulation in the feet and may provide new insights into neuropathy-associated pain and the pathogenesis of polyneuropathy. Muscle Nerve 27: 737,742, 2003 [source] Do six-antigen-matched cadaver donor kidneys provide better graft survival to children compared with one-haploidentical living-related donor transplants?PEDIATRIC TRANSPLANTATION, Issue 2 2000A report of the North American Pediatric Renal Transplant Cooperative Study Abstract: Since 1991, more than 50% of pediatric transplant recipients have received a living donor (LD) kidney, and , 85% of these allografts were one-haploidentical parental kidneys. Short-term (1 yr) and long-term (5 yr) graft survival of LD kidneys are 10% and 15% better, respectively, than that of cadaver donor (CD) kidneys. Because of these results, children are frequently not placed on a cadaver waiting list until the possibility of a LD is excluded , a process that may take up to 1 yr. The hypothesis for this study was that the graft outcome of a six-antigen-matched CD kidney is superior to that of a one-haploidentical LD kidney, and that children are at a disadvantage by not being placed on a CD list whilst waiting for a LD. The database of the North American Pediatric Renal Transplant Cooperative Study (NAPRTCS) for 11 yrs (1987,98), was reviewed to identify children who were recipients of a six-antigen-matched CD kidney (primary and repeat transplants), and those who were recipients of a one-haploidentical LD kidney (primary and repeat transplants). Using standard statistical methods, the morbidity, rejection episodes, post-transplant hospitalizations, renal function, long- and short-term graft survival, and half-life of primary recipients were compared in the two groups. Unlike adult patients, only 2.7% (87/3313) of CD recipients in the pediatric age range received a six-antigen-matched kidney, and the annual accrual rate over 11 yrs was never higher than 4%. Comparison of 57 primary six-antigen-CD kidneys (PCD) with 2472 primary LD (PLD) kidneys revealed that morbidity, rejection rates, and ratios were identical in the two groups. Renal function and subsequent hospitalizations were also identical in the two groups. Five-year graft survival of the PCD group was 90% compared with 80% for the PLD group, and the half-life of the PCD group was 25 ± 12.9 yrs compared with 19.6 ± 1.3 yrs. Our data suggest that the six-antigen-matched CD kidney may have less graft loss as a result of chronic rejection and would therefore confer a better long-term outcome. Based on these findings we recommend that all children, whilst waiting for a LD work-up, be listed with the United Network for Organ Sharing (UNOS) registry for a CD kidney. [source] Antipsychotic polypharmacy at the University Psychiatric Hospital in Serbia,PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, Issue 11 2007Nevena Divac Abstract The aim of the study was to analyse the prevalence of polypharmacy with antipsychotic drugs and analyse types of coprescribing episodes at the University Psychiatric Hospital in Serbia. A sample of 120 patients (198 hospitalisations) was analysed. The prevalence of polypharmacy was calculated as the proportion of patients receiving two or more antipsychotic drugs concomitantly for at least 28 days. Total daily antipsychotic drug load was calculated as the number of defined daily doses (DDDs) of drugs per patient per day. It was compared between patients receiving monotherapy and patients receiving polypharmacy. Statistics was performed using standard statistical methods. Monotherapy was prescribed during 32.3% hospitalisations (n,=,64), while polypharmacy was noted in 67.7% (n,=,134). Polypharmacy with two drugs was observed during 126 (63.6%) hospitalisations and three antipsychotics were prescribed concomitantly during 8 (4.1%) hospitalisations. Patients' characteristics were not significantly different between patients who received only monotherapy and patients receiving polypharmacy. Patients on monotherapy had significantly more prior hospitalisations than patients from the other group (t,=,3.94, df,=,119, p,<,0.001). The prevalence of polypharmacy patient episodes (67.7%) is approximately 100% higher than the prevalence observed in developed European countries. The explanation of such prescribing habit of Serbian psychiatrists requires further investigation. The only distinguishing factor between patients receiving monotherapy and patients receiving polypharmacy is the number of prior hospitalisations. Copyright © 2007 John Wiley & Sons, Ltd. [source] Metric and nonmetric dental variation and the population structure of the AinuAMERICAN JOURNAL OF HUMAN BIOLOGY, Issue 2 2010Tsunehiko Hanihara Gene flow and genetic drift are important factors affecting geographic variations in human phenotypic traits. In the present study, the effects of gene flow from an outside source on the pattern of within- and among-group variation of the Ainu from Sakhalin Island and three local groups of Hokkaido are examined by applying an R-matrix approach to metric and nonmetric dental data. The comparative samples consist of their ancestral and neighboring populations, such as the Neolithic Jomon, the subsequent Epi-Jomon/Satsumon, the Okhotsk culture people who migrated from Northeast Asia to the northeastern part of Hokkaido during a period 1600,900 years B.P., and modern non-Ainu Japanese. The results obtained by using the census population sizes of the regional groups of the Ainu as an estimate of relative effective population size suggest the possibility of an admixture between the Okhotsk culture people and the indigenous inhabitants in Hokkaido, at least in the coastal region along the Sea of Okhotsk. Such gene flow from Northeast Asian continent may have exerted an effect on the genetic structure of the contemporary Ainu. The present findings indicate that the population structure, as represented by genetic drift and gene flow, tend to be obscured in the results obtained by standard statistical methods such as Mahalanobis' generalized distance and Smith's MMDs. The present extension of the R-matrix approach to metric and nonmetric dental data provide results that can be interpreted in terms of a genetically, archaeologically, and prehistorically suggested pattern of gene flow and isolation. Am. J. Hum. Biol., 2010. © 2009 Wiley-Liss, Inc. [source] | |||||||||||||