SEARCH · Search PubMed

Results for “hypothesis testing”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,135 records · Page 63Linked to original sources

PubMed1999

Constructing confidence intervals for cost-effectiveness ratios: an evaluation of parametric and non-parametric techniques using Monte Carlo simulation.

The statistic of interest in most health economic evaluations is the incremental cost-effectiveness ratio. Since the variance of a ratio estimator is intractable, the health economics literature has suggested a number of alternative approaches to estimating confidence intervals for the cost-effectiveness ratio. In this paper, Monte Carlo simulation techniques are employed to address the question of which of the proposed methods is most appropriate. By repeatedly sampling from a known distribution and applying the different methods of confidence interval estimation, it is possible to calculate the coverage properties of each method to see if these correspond to the chosen confidence level. As the results of a single Monte Carlo experiment would be valid only for that particular set of circumstances, a series of experiments was conducted in order to examine the performance of the different methods under a variety of conditions relating to the sample size, the coefficient of variation of the numerator and denominator of the ratio, and the covariance between costs and effects in the underlying data. Response surface analysis was used to analyse the results and substantial differences between the different methods of confidence interval estimation were identified. The methods, both parametric and non-parametric, which assume a normal sampling distribution performed poorly, as did the approach based on simply combining the separate intervals on costs and effects. The choice of method for confidence interval estimation can lead to large differences in the estimated confidence limits for cost-effectiveness ratios. The importance of such differences is an empirical question and will depend to a large extent on the role of hypothesis testing in economic appraisal. However, where it is suspected that the sampling distribution is skewed, normal approximation methods produce particularly poor results and should be avoided.

Computer Simulation↗

PubMed2000

Urn models and vaccine efficacy estimation.

We derive the distribution of the number of infections among unvaccinated and vaccinated individuals for model 1 (leaky) and model 2 (all/nothing) vaccines, assuming random mixing of a homogeneous population. For all/nothing vaccines, we show that the distribution of the number of infected vaccinated individuals conditioning on n observed infections follows a hypergeometric distribution, and the vaccine efficacy estimate (VE) can be derived from the usual estimate of the total population size in a capture-recapture sampling program. For leaky vaccines, we show that the number of vaccinated infected follows a distribution that was first derived by Wallenius. We found that the current point estimates of VE for each model perform very well, but the urn model construction presented here provides a strong framework for estimation and hypothesis testing on the parameters, and can be applied when the available data are a sample of the population. Since the method does not require an underlying transmission model, it can be applied to estimate the VE for non-contagious diseases.

Adolescent↗

PubMed2000

Additive isotonic regression models in epidemiology.

Stone's method for assessing disease risk around a point source through isotonic regression is routinely used in spatial epidemiology. It is useful in situations where the relationship of risk with exposure (distance being commonly used as a surrogate variable) is assumed monotonic but otherwise of unknown form. This paper extends this method to non-spatial epidemiology, where typically two or more risk factors are present. The methodology described is based on the additive isotonic model approach of Bacchetti; versions appropriate to count (Poisson) data and case-control (binomial) data are described. In both cases, adjustment for covariates is incorporated, and a Monte Carlo method of hypothesis testing and interval estimation is presented. The methodology is illustrated through a case-control example concerning the analysis of the possible effect of preconceptional external ionizing radiation doses on the sex ratio at birth among children of fathers working at the Sellafield nuclear installation, Cumbria, U.K.

Case-Control Studies↗

PubMedDate not supplied

Longitudinal studies of cognitive, functional and behavioural change in patients with Alzheimer's disease.

This paper reviews data on the natural history of symptoms in patients with Alzheimer's disease (AD) and describes some of the problems encountered in analysing longitudinal data in this population. Data on cognition, functional ability and psychiatric or behavioural symptoms have all been obtained from AD patients. Because of attrition, the length of follow-up is not uniform for all patients and neither is the frequency of evaluation. Furthermore, patients enter longitudinal studies with a wide range of symptom severity and longitudinal decline in cognition and function is distinctly non-linear. Behavioural symptoms do not progress regularly in AD but are episodic phenomena not closely related to cognition or function. Strengths and limitations of various analytic techniques used for hypothesis testing with these longitudinal data are described.

Aged↗

PubMed1998

Occupational risk factors for breast cancer among women in Shanghai.

Although female breast cancer rates are lower in China than in Western countries, rates have been rising rapidly in China. This increase may be due to changes in established breast cancer risk factors, but it is possible that exposure to occupational and environmental carcinogens in Shanghai also have contributed to the rise in incidence. We used data collected by the Shanghai Cancer Registry and the Chinese Third National Census to study the risk of breast cancer by occupation and by occupational exposures. Standardized incidence ratios (SIRs) were used to compare observed cases to expected numbers of cases, based on the incidence rates for Shanghai and the number of women in each occupation according to the 1982 census. Statistically elevated SIRs for breast cancer were seen for a number of professional occupational categories, with the greatest risk seen among scientific research workers (SIR = 3.3). Administrative clerks, political and security personnel, and makers of rubber and plastics products also had significant excesses. Significant deficits of risk were seen for the categories of production and related workers, construction workers, and transportation equipment operators. For specific occupations, the highest SIRs were observed among doctors of Chinese-Western medicine (SIR = 14.7, 95% CI = 5.9-30.3) and doctors of Chinese medicine (SIR = 7.2, 95% CI = 4.4-11.4). We also found excesses among teachers at each level of education, librarians, clerical workers, electrical and electronic engineers, nurses, lab technicians, accountants and bookkeepers, rubber manufacturing products makers, weavers, and knitters. SIRs were significantly elevated for high probability of exposure to organic solvents (SIR = 1.4). For benzene exposure, we found significant excesses for overall exposure (SIR = 1.1) and for medium level of exposure (SIR = 1.3). There was no evidence of an association between risk and electromagnetic fields (EMF) exposure. Based on a small number of exposed, SIRs were elevated for both medium probability and high level of exposure to pesticides. The elevations in occupations reported here support some previous reports. Our finding of an increased risk associated with benzene also has been reported previously; the finding for organic solvents is new. However, the literature on the risk of breast cancer related to occupational exposures is limited and there is no consistent body of literature for any of the exposures studied here. Further, many comparisons were made and the problem of multiple hypothesis testing cannot be ignored in a survey such as ours.

Breast Neoplasms↗

PubMed1996

Phenotypic diversity and kinetics of proliferating microglia and astrocytes following cortical stab wounds.

Brain injury induces reactive gliosis, characterized by increased expression of glial fibrillary acidic protein (GFAP), astrocyte hypertrophy, and hyperplasia of astrocytes and microglia. One hypothesis tested in this study was whether ganglioside GD3+ glial precursor cells would contribute to macroglial proliferation following injury. Adult rats received a cortical stab wound. Proliferating cells were identified by immunostaining for proliferating cell nuclear antigen (PCNA) and by [3H]-thymidine autoradiography, and cell phenotypes by immunocytochemical staining for GD3, GFAP, ED1 (for reactive microglia) and for Bandeiraea Simplicifolia isolectin-B4 binding (all microglia). Animals were labeled with thymidine at 1,2,3, and 4 days postlesion (dpl) and sacrificed at various times thereafter. Proliferating cells of each phenotype were quantified. A dramatic upregulation of GD3 on ramified microglia was seen in the ipsilateral hemisphere by 2 dpl. Proliferating cells consisted of microglia and fewer astrocytes. Microglia proliferated maximally at 2-3 dpl and one third to one half were GD3+. Astrocytes proliferated maximally at 3-4 dpl, and some were also GD3+. Both ramified and ameboid forms of microglia proliferated and by 4 dpl all GD3+ microglia were ED1+ and vice versa. In the contralateral cortex microglia expressed neither GD3 nor ED1. Thus they acquired these antigens when activated. Neither microglia nor astrocytes that were thymidine-labeled at 2, 3, or 4 dpl changed in number in subsequent days. Most thymidine+ astrocytes were large GFAP+ reactive cells that clearly arose from pre-existing astrocytes, not from GD3+ glial precursors. In this model of injury microglia proliferate earlier and to a much greater extent than astrocytes, they can divide when in ramified form, and GD3 is up-regulated in most reactive microglia and in a subset of reactive astrocytes. We also conclude that microglial proliferation precedes proliferation of invading blood-borne macrophages.

Animals↗

PubMed2000

Reconciliation in captive Guyanese squirrel monkeys (Saimiri sciureus).

The tendency for agonistic interaction to increase the probability of friendly interaction between social partners has been demonstrated across a range of Old World primates. While research on such post-conflict behavior proceeds into an hypothesis-testing phase, new comparative information must accumulate to provide full phylogenetic perspective on primate social behavior. Data from New World and prosimian primates are yet extremely limited. We studied captive squirrel monkeys (Saimiri sciureus) via post-conflict (PC) and matched control (MC) observations and analyzed results using both the PC-MC and time-rule methods. Former opponents maintaining affiliative relationships soon engaged in friendly interaction following large proportions of agonistic interactions, whereas non-affiliated individuals, including virtually all male-female pairs, reconciled conflicts rarely. Close-proximity approaching and huddling contact constituted the principal modes of post-conflict amicability. Agonistic interactions of relatively high intensity were most likely to be reconciled and most likely to be reconciled via physical contact. High vulnerability of Saimiri to predation may have favored this species' strong inclination to reconcile soon after agonistic interaction. Research on free-living populations of this and other primate species is needed to illuminate similarities and differences across taxa.

Aggression↗

PubMed2000

Genome-wide loss of heterozygosity analysis of chemically induced rat hepatocellular carcinomas reveals elevated frequency of allelic imbalances on chromosomes 1, 6, 8, 11, 15, 17, and 20.

Neoplastic development is a multistep process that involves the stochastic accumulation of heritable genetic alterations in proto-oncogenes, DNA repair genes, and tumor suppressor genes. Loss of heterozygosity (LOH) analysis has been used successfully to identify the genetic determinants of neoplastic development, including tumor suppressor genes, in several species and organs but not in the rat liver. We report the results of a sensitive genome-wide LOH analysis of rat hepatocellular carcinomas (HCCs). Heterozygous rats (Wistar-Furth x Fisher 344) were subjected to an Initiation-Promotion-Progression (IPP) protocol of hepatocarcinogenesis. Two weeks after initiation (by partial hepatectomy, 10 mg/kg diethylnitrosamine), the rats were placed on a diet containing 0.05% phenobarbital (PB). After 24 wk of PB promotion, the rats received either 100 or 1 50 mg/kg ethylnitrosourea. Hepatocellular tumors were resected after a total of 76wk of PB promotion. LOH analysis was completed on 26 HCCs by using 60 microsatellite markers covering all 20 rat autosomes and chromosome X. While 85% of the HCCs had one or more allelic imbalances, the average HCC had 3.3 allelic imbalances (range 0-9). A conditional hypothesis-testing method called the Hot-Cold model was used to determine the location of statistically significant elevations in the frequency of allelic imbalances. Elevated allelic imbalances were observed on chromosomes 1q, 6, 8, 11, 15, 17, and 20p. Together, these allelic imbalances suggest that the retinoblastoma and insulin-like growth factor genes as well as the resistance to chemical carcinogenesis (rcc) locus may be involved in HCC development in the rat but that LOH of the p53 gene is not. The elevated rate of allelic imbalances on chromosomes 8,11, and 17 may indicate the location of undiscovered tumor suppressor genes important to neoplastic development in rat liver. Microdissection-based LOH analysis of HCC revealed that contamination of non-neoplastic and nonhepatocellular tissue was not masking LOH in the whole-tumor analysis. There were no statistically significant differences in the frequency of allelic imbalances between HCC of any differentiation state (histological grade). To the degree that it does not reflect differences in etiological factors, the absence of allelic imbalances in chromosomal regions containing the p53 and mamose-6-phosphate/insulin-like growth factor II receptor tumor suppressor genes and the generally low frequency of allelic imbalances in these tumors, suggests that LOH and allelic imbalances play a less significant role in the molecular pathogenesis of HCC in rats than humans.

Alleles↗

PubMed1997

Effects of body fat on ventilatory function in children and adolescents: cross-sectional findings from a random population sample of school children.

Childhood obesity is associated with a range of adverse consequences, and the prevalence is increasing in developed nations. Most of the literature on obesity and ventilatory function in children concerns samples selected for gross obesity with relatively little detail available from random population samples. This report examines the effect of total body fat as a percentage of weight (TBF%) on ventilatory function in a nationally representative sample of 2,464 Australian school children aged 9, 12, and 15 years. Forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV1) were used as measures of ventilatory function. TBF% was estimated from skinfold thickness measurements. Ventilatory function was adjusted (for height and then for both height and weight) using linear regression on a logarithmic scale. Adjustment was performed within separate strata of age and gender. Analysis of covariance was used for hypothesis testing. Height-adjusted FVC and FEV1 values increased significantly with increasing weight within each age and gender group and for all subjects combined (P < 0.0001). The effect of TBF% independent of lean tissue was examined using FVC and FEV1 values adjusted for both height and weight, because body weight measures both lean and fat mass. Adjusted FVC and FEV1 values decreased significantly with increasing TBF% within each age and gender group and for all subjects combined (P < 0.0001). Ventilatory function decreased with increasing proportions of body fat. This is consistent with previous findings on lean tissue mass and ventilatory function. Although the magnitude of the effect was relatively small in clinical terms, from a public health perspective our findings indicate yet another adverse consequence of childhood obesity.

Adolescent↗

PubMedDate not supplied

Confidence intervals for cost-effectiveness ratios: an application of Fieller's theorem.

Application of cost-effectiveness analysis (CEA) is growing rapidly in health care. Two general approaches to analysis are differentiated by the type of data available: (i) deterministic models based upon secondary analysis of retrospective data from one or more trials and other sources; and (ii) stochastic analyses in which the design of a randomized controlled trial is adapted to collect prospectively patient-specific data on costs and effectiveness. An important methodological difference between these two approaches is in how uncertainty is handled. Deterministic CEA models typically rely upon sensitivity analysis to determine the robustness of findings to alternative assumptions, whereas stochastic (CEA) analysis, as part of prospective studies, permits the use of conventional statistical methods on the cost and effectiveness data for both inference (hypothesis testing) and estimation. This paper presents a procedure for the statistical analysis of cost-effectiveness data, with specific application to those studies for which effectiveness is measured as a binary outcome. Specifically, Fieller's Theorem was used to calculate confidence intervals for ratios of the two random variables of between-treatment differences in observed costs and effectiveness, i.e. the incremental cost-effectiveness ratio.

Computer Simulation↗

PubMedDate not supplied

Trying to do better than average: a commentary on 'statistical inference for cost-effectiveness ratios'.

In a recent paper, Laska, Meisner and Siegel address issues concerning hypothesis testing in cost-effectiveness analysis. They relate the relative magnitude of two average cost-effectiveness ratios to the incremental cost-effectiveness ratio and go on to propose a statistical procedure for testing the equality of two average ratios. In this paper, we show why the use of average cost-effectiveness ratios is misleading and argue that the appropriate focus for cost-effectiveness analysis is the estimation of confidence intervals around incremental cost-effectiveness ratios.

Confidence Intervals↗

PubMed2001

Analysing gene expression data from DNA microarrays to identify candidate genes.

Microarray data analysis can be divided into two tasks: grouping of genes to discover broad patterns of biological behaviour, and filtering of genes to identify specific genes of interest. Whereas the gene-grouping task is largely addressed by cluster analysis, the gene-filtering task relies primarily on hypothesis testing. This review article surveys analytical methods for the gene-filtering task. Various types of data analysis are discussed for four basic types of experimental protocols: a comparison of two biological samples; a comparison of two biological conditions; each represented by a set of replicate samples; a comparison of multiple biological conditions; and analysis of covariate information.

Computational Biology↗

PubMed2001

Voltage-gated K(+) channel activity in human prostate cancer cell lines of markedly different metastatic potential: distinguishing characteristics of PC-3 and LNCaP cells.

BACKGROUND: Although ion channels are known to contribute to a variety of basic cellular behaviors involved in the metastatic cascade, their role in metastasis per se has only recently been questioned. The hypothesis tested was whether K(+) channels were different between strongly metastatic PC-3 and weakly metastatic LNCaP human prostate cancer cell lines. METHODS: The whole-cell configuration of the patch clamp recording technique was used to record voltage-gated currents from LNCaP and PC-3 cell lines. The responses to different voltage-clamp protocols, sensitivity to external Ca(2+), and addition of drugs and toxins were explored. RESULTS: Voltage-gated K(+) current density was significantly larger in LNCaP than PC-3 cells. In addition, the K(+) currents in a sub-population of PC-3 cells were Ca(2+)-sensitive. These properties reflected the differential metastatic character of the cells, the PC-3 cells appearing potentially more "excitable". CONCLUSIONS: Prostate cancer cells of varying metastatic ability can be distinguished by their ion channel characteristics. The possible contribution(s) of K(+) channel activity to development of malignancy needs exploration.

Calcium Channels↗

PubMed2000

The bootstrap procedure in individual bioequivalence.

A bootstrap-type hypothesis test procedure for assessing individual (or population) bioequivalence between two drug formulations is suggested in a draft guidance from the United States Food and Drug Administration (FDA). The purpose of this article is to study the unknown properties of this test procedure and propose some improved test procedures. We find that: the FDA's bootstrap computation is not correct; the power of the FDA's test can be very low; the use of the REML method suggested in the draft guidance does not have any advantage over the use of simpler methods such as the moment method; and the method of sample size determination in the draft guidance is inappropriate. We study the size and power of different bootstrap test procedures and suggest a method for sample size determination. It is our hope that this article will draw some attention to further research in this area, and eventually a satisfactory statistical method can be implemented for assessing individual (or population) bioequivalence.

Area Under Curve↗

PubMed2000

Statistics in medical journals: some recent trends.

I review some areas of medical statistics that have gained prominence over the last 5-10 years: meta-analysis, evidence-based medicine, and cluster randomized trials. I then consider several issues relating to data analysis and interpretation, many relating to the use and misuse of hypothesis testing, drawing on recent reviews of the use of statistics in medical journals. I also consider developments in the reporting of research in medical journals.

Data Interpretation, Statistical↗

PubMed2001

Statistical inferences for a twin correlation with multinomial outcomes.

Current methods for statistical analysis of twin studies focus on continuous and dichotomous data, while only limited methodology exists for analysing multinomial data. As a consequence, investigators are often tempted to collapse multinomial data into two categories simply to facilitate the analysis. We address this problem by developing and evaluating two approaches to the assessment of twin correlation for an outcome variable having more than two nominal categories. One method developed is an extension of the goodness-of-fit approach, while the other method is based on large sample normal theory. Procedures for confidence interval construction are developed and compared using Monte Carlo simulation. The results show that either method may be safely used for confidence interval construction provided the number of twin pairs is large (> or =100) but that in smaller sample sizes the goodness-of-fit procedure is to be preferred on the grounds of validity. Other inference problems are also discussed, including point estimation, hypothesis testing and sample size estimation. An example is included.

Computer Simulation↗

PubMed1977

Differences in the therapeutic functioning of paraprofessionals with varying lengths of experience.

Measured differences in the ability of paraprofessionals to discriminate and communicate facilitative conditions in psychotherapy as a function of length of experience. Hypothesis tested were that discrimination and communication abilities would be greater in Ss with longer experience and that these abilities would be correlated positively within individuals. Thirty-six mental health workers were categorized into three levels of experience and initial competency. Ss were administered the Carkhuff Discrimination Rating Scale; the level of conditions communicated to patients was assessed through replies to taped patient interviewers. Results failed to support the hypothesized relationships between functioning and experience. However, several interactions were found. Initially more competent Ss tended to improve over time and less competent Ss declined. A positive correlation between abilities within individuals was found. Results were compared with studies that measured the functioning of professional psychology trainees over time, are relevant to issues of therapist selection, and support the use of experiential training programs.

Allied Health Personnel↗

PubMed1984

The Urist Rorschach Mutuality of Autonomy Scale as an indicator of psychopathology.

The Urist Rorschach Mutuality of Autonomy Scale (MAS), which assesses development along a self-object differentiation and mutuality dimension, has shown considerable promise as an index of interpersonal relationship capacities. As such, MAS scores were predicted to correlate significantly with three measures of psychological pathology/health. The reliability of the scale was investigated with non-S Rorschachs and found to be satisfactory. Four-card Rorschachs from 60 previously hospitalized adults comprised the data source for the hypothesis test. Results suggest that the Mutuality Scale accurately reflects observed pathology severity at time of hospitalization and over a lifetime, but not at the time of assessment. Hence, the Urist MAS may indicate potential for pathology.

Adult↗