Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Probability Theory”

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.

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

At least 451 records · Page 25Linked to original sources
PubMed2004

Likert and Guttman scaling of visual function rating scale questionnaires.

PURPOSE: To test the assumptions underlying Likert scoring of visual function questionnaires. METHODS: Questionnaires were administered to 284 low-vision subjects by telephone. Each subject was administered two of four questionnaires: ADVS, NEI VFQ-25 plus supplement, expanded VAQ, and VF-14. RESULTS: Z-scores for cumulative frequency of using each rating category across subjects are not linear with rating category rank and items are not the same difficulty for any of the questionnaires. Guttmann coefficients of reproducibility ranged from 57% for the ADVS to 51% for the NEI VFQ-25. Cronbach alphas ranged from 0.92 for the VF-14 to 0.96 for the NEI VFQ; however, inter-item consistency coefficients ranged from 0.24 for the VAQ to 0.45 for the NEI VFQ. Likert scores were significantly correlated between instruments, ranging from 0.66 for NEI VFQ vs ADVS to 0.90 for the VF-14 vs. ADVS. CONCLUSIONS: The rating scales of all four questionnaires fail to satisfy Likert's assumptions. Also, ratings are probabilistic, rather than deterministic, which means that the Likert model is not valid for these questionnaires. However, Likert scores for all four instruments are intercorrelated, suggesting that they are monotonic with the latent subject trait distributed in the low vision sample.

Adult↗
PubMed1995

Effects of observed correlation structure among tumor types on experimentwise false positive rate in animal carcinogenicity studies.

Probabilities P1, P2, ..., Pn of n events E1, E2, ..., En can impose constraints on the probability of a further event E. deFinetti's fundamental theorem of probability characterizes the interval of coherent probability of E. Lad, Dickey, and Rahman (5) extended deFinetti's theorem in a few directions. In this work we will show some applications of these results to the calculation of experimentwise false positive error rate in multiple hypotheses testing procedure.

Animals↗
PubMed2001

Philosophical conjectures and their refutation.

Sir Karl Popper is well known for explicating science in falsificationist terms, for which his degree of corroboration formalism, C(h,e,b), has become little more than a symbol. For example, de Queiroz and Poe in this issue argue that C(h,e,b) reduces to a single relative (conditional) probability, p(e,hb), the likelihood of evidence e, given both hypothesis h and background knowledge b, and in reaching that conclusion, without stating or expressing it, they render Popper a verificationist. The contradiction they impose is easily explained--de Queiroz and Poe fail to take account of the fact that Popper derived C(h,e,b) from absolute (logical) probability and severity of test, S(e,h,b), where critical evidence, p(e,b), is fundamental. Thus, de Queiroz and Poe's conjecture that p(e,hb) = C(h,e,b) is refuted. Falsificationism, not verificationism, remains a fair description of the parsimony method of inference used in phylogenetic systematics, not withstanding de Queiroz and Poe's mistaken understanding that "statistical" probability justifies that method. Although de Queiroz and Poe assert that maximum likelihood has the power "to explain data", they do not successfully demonstrate how causal explanation is achieved or what it is that is being explained. This is not surprising, bearing in mind that what is assumed about character evolution in the accompanying likelihood model M cannot then be explained by the results of a maximum likelihood analysis.

Likelihood Functions↗
PubMedDate not supplied

The determinants and consequences of information seeking among cancer patients.

This research was designed to examine information seeking behavior among cancer patients. We present a model which identifies the determinants and consequences of information seeking and, in turn, examines the effects of prior variables on four outcome variables: whether patients discussed with their physicians information that they received from other sources, whether the information they obtained helped them make decisions about treatment or care, whether the patient sought a second opinion about his/her diagnosis or treatment, and changes in self-reported stress levels from diagnosis to the time of interview. The model is estimated separately for three groups: patients who sought information from multiple sources including the National Cancer Institute's Cancer Information Service, patients who sought information from multiple sources but did not call the Cancer Information Service, and patients who did not seek information other than from their physician(s). We discuss variables that have similar impacts on outcome variables in all three groups as well as variables that operate differently within the groups. The results indicate that the desire for information and the desire for involvement in medical care decisions are independent factors. Some patients have a strong desire for both information and involvement in making health care decisions. These patients actively seek involvement in their treatment plans. Other patients, however, want to be informed about their disease and treatment but prefer to delegate most decision-making to their physicians. Still other patients choose to delegate information gathering and decision making exclusively to their physicians. We discuss the implications of these results for both patients and providers.

Adolescent↗
PubMed2002

On the joint analysis of longitudinal responses and early discontinuation in randomized trials.

Our focus is on the joint analysis of longitudinal nonnormal responses and early discontinuation in (pre)-clinical trials. Separate models are fitted to the two series (response and discontinuation) to account for covariate and time effects. The serial dependence and the dependence between response and drop-out are also modeled. This is done using particular dependence functions, called copulas. Copulas are used to create a joint distribution with given marginal distributions. Applications are given for the analysis of heart rate/morbidity in toxicology and pain severity/intake of rescue medications in a trial on migraine. Using copulas, the level of dependence between two variables remains invariant to changes in the marginal distribution of either variable. This proves interesting in modeling the association in a longitudinal setting when responses change over time.

Algorithms↗
PubMed2002

Power and sample size determination for noninferiority trials using an exact method.

Noninferiority studies are frequently conducted to justify the development of new drugs and vaccines that have been shown to offer better safety profiles, easier administration, or lower cost while maintaining similar efficacy as compared to the standard treatment. Recently, exact methods have been developed to address the concern that existing asymptotic methods for analyzing and planning noninferiority may fail because of small sample size or because of skewed or sparse data structure. In this paper, we explore the use of exact methods in determining sample size and power for noninferiority studies that focus on the difference of two proportions. The methodology for sample size and power calculations is developed based on an exact unconditional test of noninferiority. We illustrate this exact method using a clinical trial example in childhood nephroblastoma and briefly discuss the optimal sample-size allocation strategy. This exact unconditional method performs very well in various scenarios and compares favorably to its asymptotic counterpart in terms of sensitivity. Therefore, it is a very desirable tool for planning noninferiority trials, especially in situations where asymptotic methods are likely to fail.

Algorithms↗
PubMed2002

Stopping boundaries adjusted for sample size reestimation and negative stop.

We propose an approach to specify group sequential stopping boundaries adjusted for sample size reestimation and negative stop in interim analyses of a clinical trial. Sample size can be adjusted based on the observed delta at each interim to maintain the targeted power. The calculation of stopping boundaries incorporates possible changes in the type-I error due to sample size reestimation and/or negative stops; hence the overall type-I error is well controlled. This approach combines the advantages of the group sequential and sample size reestimation methods and is more efficient than either one alone. It provides flexibility in clinical trials and still maintains the integrity of these trials. When no early stop is planned, the stopping boundaries will be adjusted only for sample size reestimation. All calculations are given in closed mathematical forms and adjustments in stopping boundaries are based on the exact type-I error change. Therefore, the penalty for the type-I error inflation due to such interim conductions is kept to a minimum.

Algorithms↗
PubMed2005

Performance of a mixed effects logistic regression model for binary outcomes with unequal cluster size.

When a clustered randomized controlled trial is considered at a design stage of a clinical trial, it is useful to consider the consequences of unequal cluster size (i.e., sample size per cluster). Furthermore, the assumption of independence of observations within cluster does not hold, of course, because the subjects share the same cluster. Moreover, when the clustered outcomes are binary, a mixed effect logistic regression model is applicable. This article compares the performance of a maximum likelihood estimation of the mixed effects logistic regression model with equal and unequal cluster sizes. This was evaluated in terms of type I error rate, power, bias, and standard error through computer simulations that varied treatment effect, number of clusters, and intracluster correlation coefficients. The results show that the performance of the mixed effects logistic regression model is very similar, regardless of inequality in cluster size. This is illustrated using data from the Prevention Of Suicide in Primary care Elderly: Collaborative Trial (PROSPECT) study.

Algorithms↗
PubMed2004

Analysis of the S810L point mutation of the mineralocorticoid receptor in patients with pregnancy-induced hypertension.

OBJECTIVE: A missense mutation at codon 810 (Ser --> Leu) of the mineralocorticoid receptor was recently observed in a family with early manifestation of hypertension. Our objective was to determine if this mineralocorticoid receptor alterations is prevalent in patients with pregnancy-induced hypertension. METHODS: Thirty-eight women with hypertension during pregnancy were tested for the mineralocorticoid receptor gene mutation. DNA was extracted out of blood leucocytes. PCR and automated DNA sequencing were used to analyze exon 6 for the S810L missense mutation. Anamnestical data concerning cardiovascular risk factors and family history were evaluated with a questionnaire. Pregnancy course and outcome were documented in all cases. RESULTS: In 33 patients with pregnancy-induced hypertension and in five patients with exacerbation of preexisting hypertension in pregnancy no point mutations were found at codon 810 in exon 6. CONCLUSIONS: Our data suggest that the S810L missense mutation of the mineralocorticoid receptor does not play a major role in the etiology of pregnancy-induced hypertension in a German /Turkish population.

Codon↗
PubMed2001

Empirical estimators of gamma fits to tracer-dilution curves and their technical basis and practical scope.

A gamma fit facilitates smoothing and extrapolation of distorted tracer-dilution curves in blood flow studies. Theoretically based empirical estimators were developed as simple alternatives to direct regression approaches from simulated gamma distributions with a wide range of shape asymmetry. Key curve features of peak height p, full width w at half peak height, rising and falling limb inflection tangents and asymmetry of the peak time with respect to the p/2 height occurrences were related to the parameters of the distribution by multiple linear regression after suitable transformations. The product pw was simply related to the total area A under the curve, pw/A being 0.93 +/- 0.01 in 70 cardiac output determinations from ten surgical patients. Shape and scale parameters were closely related to the standard deviation, inflection point properties and w for the curves. Mensuration devices suitable for cardiac output computers were developed that calculated total areas from incomplete portions under gamma curves and by-passed the need for parameter estimation. There was limited point in estimating the distribution parameters just to derive particle transit times, because of the ad hoc nature of the fitting form, which did not allow for the back-dispersion by Brownian motion of tracer molecules diluting in blood flow. Nonetheless, the accuracy of area prediction using a gamma fit was adequate for most clinical purposes and comparable to that via the random walk function, giving good insight to established results and computing procedures.

Algorithms↗
PubMed1996

Dirichlet mixtures: a method for improved detection of weak but significant protein sequence homology.

We present a method for condensing the information in multiple alignments of proteins into a mixture of Dirichlet densities over amino acid distributions. Dirichlet mixture densities are designed to be combined with observed amino acid frequencies to form estimates of expected amino acid probabilities at each position in a profile, hidden Markov model or other statistical model. These estimates give a statistical model greater generalization capacity, so that remotely related family members can be more reliably recognized by the model. This paper corrects the previously published formula for estimating these expected probabilities, and contains complete derivations of the Dirichlet mixture formulas, methods for optimizing the mixtures to match particular databases, and suggestions for efficient implementation.

Algorithms↗
PubMed1999

Quantifying variability in the planum temporale: a probability map.

The acquisition of definitive evidence for systematic hemispheric asymmetries in the size of the planum temporale (PT) has been restricted by difficulties in identifying, standardizing and measuring the region of interest. In this paper an operational definition for identifying the problematic posterior border of the PT on magnetic resonance imaging (MRI) scans is proposed. An interactive voxel-painting program was used to identify and label the PT simultaneously in horizontal, sagittal and coronal planes in MRI scans, transformed into the standardized Talairach-Tournoux stereo-taxic space, from 50 normal right-handed volunteers. Both grey matter volume and cortical surface area of the PT were measured, while controlling for individual variation in overall brain shape and volume. The labeled tissue was averaged together to produce a probability map in standardized space of the region of interest. The PT region is highly variable, with no single voxel being labeled with a probability of >65%. In this study there were no significant hemispheric differences in volume or area of the PT. An asymmetry in area and volume was introduced by using an alternative method - the 'knife-cut' method - for identifying the posterior border. Implications for functional neuroimaging of the PT are discussed.

Adult↗
PubMed1978

Estimating exposure-specific disease rates from case-control studies using Bayes' theorem.

The methods used for selecting subjects yield three types of case-control studies: 1) incident cases are compared to non-cases chosen to be representative of the exposure distribution among the person-years which produced the cases. In this type of study the exposure-odds ratio equals the incidence density ratio; 2) incident cases are compared to residual non-cases at the end of the risk period (exposure-odds ratio = cumulative incidence-odds ratio); 3) prevalent cases are compared to non-cases (exposure-odds ratio = prevalence odds ratio). In study type 1 the equivalence of odds ratio to rate ratio requires no "rare disease assumption;" this permits estimation of exposure-specific illness rates when the overall rate is known. In study types 2 and 3 the exposure-odds ratio equals the corresponding rate ratios only when exposure-specific rates are low. Nonetheless, exposure-specific rates can be calculated without making any rare disease assumption using Bayes' theorem and information on the overall disease rate. A method for obtaining approximate confidence limits around the exposure-specific rates is presented.

Biometry↗
PubMed1981

The validity of approximation methods for interval estimation of the odds ratio.

The validity of a confidence interval is determined by the probability that the random interval covers the true parameter value. A valid interval will have coverage probabilities at least as large as the confidence coefficient for all values of the parameter. The validity of three methods for constructing an approximate confidence interval on the odds ratio parameter for 2 X 2 tables is examined in the conditional hypergeometric sampling situation. Two examples are shown for which Cornfield's method is seen to be valid over a fairly wide range of true odds ratios, while the methods of Miettinen and Woolf are often found to be invalid. A number of other examples are studied with qualitatively similar results.

Epidemiologic Methods↗
PubMed1991

Does epidemiology need a new philosophy? A case study of logical inquiry in the acquired immunodeficiency syndrome epidemic.

The proposals of Popperian epidemiologists are examined using acquired immunodeficiency syndrome (AIDS) research as a case study. Hypothesis generation is shown to be mostly an inductive process in the case of AIDS. For hypothesis testing, researchers again preferred inductive verification over deductive falsification. Action-oriented disciplines, such as medicine and epidemiology, search for common sense certainty and not logical uncertainty. Insistence on falsification is often counterproductive. Induction and deduction, however, are not mutually exclusive. Conventional scientific methods, using both induction and deduction, appear to perform well in elucidating this latest epidemic, and Popper's philosophy has little to offer epidemiologists and other medical researchers.

Acquired Immunodeficiency Syndrome↗