Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “missing data”

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 919 records · Page 51Linked to original sources
PubMed2006

Measuring quality of life in PSP: the PSP-QoL.

OBJECTIVE: To develop a new patient-reported outcome measure for progressive supranuclear palsy (PSP) and to test its psychometric properties. METHODS: First, the authors generated a pool of potential scale items from in-depth patient interviews. Second, the authors administered these items, in the form of a questionnaire, to a sample of people with PSP and traditional psychometric methods were used to develop a rating scale satisfying standard criteria for reliability and validity. Third, the authors examined the psychometric properties of the rating scale in a second sample. RESULTS: In stage 1, a pool of 87 items was generated from 27 patient interviews. In stage 2, a scale with two subscales (physical, 22 items; mental, 23 items), satisfying standard criteria for reliability and validity, was developed from the response data of 225 patients with PSP. In stage 3, the scale was examined in 188 people with PSP. Missing data were low, scores in both subscales were evenly distributed, floor and ceiling effects were small. Reliability was high (Cronbach's alpha 0.93, 0.95; test-retest 0.95, 0.92). Validity was supported by the interscale intercorrelation (0.60), factor analysis, and the magnitude and pattern of correlations with four other rating scales, disease severity, and disease duration. The psychometric properties of the new scale were similar in the United Kingdom and North America, and in clinic- and community-based samples studied. CONCLUSIONS: The Progressive Supranuclear Palsy Quality of Life scale (PSP-QoL) may be a helpful patient-reported scale for clinical trials and studies in PSP.

Aged↗
PubMed2003

Sampling correction in pedigree analysis.

Usually, a pedigree is sampled and included in the sample that is analyzed after following a predefined non-random sampling design comprising several specific procedures. To obtain a pedigree analysis result free from the bias caused by the sampling procedures, a correction is applied to the pedigree likelihood. The sampling procedures usually considered are: the pedigree ascertainment, determining whether a population unit is to be sampled; the intrafamilial pedigree extension, determining what part of the pedigree is to be sampled; and selective censoring of the sampled pedigree, determining whether it should be included in the sample to be analyzed. The probability of pedigree ascertainment is determined by the total set of potential probands in the true pedigree from which the sampled pedigree is obtained and we indicate how the necessary information on this set can be collected. If insufficient information on this set is observed, it is impossible to correct the pedigree likelihood adequately. Here we show that, if only the structure of this set is known, then an ascertainment-model-based pedigree likelihood can be obtained by conditioning on this structure. An ascertainment-model-free (AMF) pedigree likelihood can be correctly constructed by conditioning on all the data in this set, i.e. on both its structure and its phenotypic content. However, if this set has missing data, the AMF likelihood becomes undefined, which limits the utility of this AMF approach originally proposed by Ewens and Shute (1986). We also consider the sampling correction necessary when the pedigrees included in the sample analyzed have been subjected to censoring. The forms of likelihood correction developed here provide asymptotically unbiased estimators of the genetic model only if the formulated model is correct, which means that it must correctly allow for the most important features of the true inheritance of the trait studied. Otherwise, if no special case of the formulated general model is close to the true inheritance model, then the forms of likelihood correction proposed here result in biases, the magnitude and direction of which depend on both the true model and the general analysis model that should subsume it.

Journal Article↗
PubMed1995

Consequences of prolonged inhalation of ozone on F344/N rats: collaborative studies. Part X: Robust composite scores based on median polish analysis.

This report describes some of the statistical methods used to analyze data from the National Toxicology Program/Health Effects Institute Collaborative Ozone Project. The purpose of the collaborative study was to assess the health effects of chronic ozone inhalation. Data were obtained from a subset of 164 F344/N rats dedicated to use by the Health Effects Institute from a standard ozone inhalation study conducted by Battelle Pacific Northwest Laboratories for the National Toxicology Program. The study involved eight groups of investigators, each assessing different types of ozone-related health effects. These included studies of respiratory function and of structural, cellular, and biochemical changes in the lungs and airways. Designing and analyzing a study with several groups of investigators raises many statistical challenges. The highest design priority for this study was that each investigation be individually interpretable as an independent study. This meant that each investigator had to receive an adequate number of animals, balanced with respect to level of ozone exposure and other factors such as the gender of the rats and the time they were killed. Another feature of the collaborative study was the opportunity it provided to assess and quantify the effect of ozone exposure on a broad spectrum of endpoints, and to explore the relations between the different types of effect. Maximizing the potential to assess these correlations required that the individual animals studied by the different groups of investigators overlap as much as possible. This aspect of the statistical design required careful consideration of the compatibility between various investigations. Fortunately, the degree of compatibility was substantial. In many cases, for example, it was possible to assess respiratory function in the animals before they were killed, and then to divide the tissue among several different investigators. This report concentrates on the methods that were specially developed to analyze the data for multiple endpoints collected in the study. Nonstandard techniques were required to accommodate the complex pattern of missing data that was inherent in the study design because no animals were measured by all investigators.

Administration, Inhalation↗
PubMed1999

Empirical power for distribution-free tests of incomplete longitudinal data with applications to AIDS clinical trials.

The design of AIDS clinical trials is of growing importance. These studies tend to be longitudinal and typically involve missing data. HIV-1 RNA is a common endpoint for these studies and is inherently non-normal, although viral load can be measured only within certain bounds, resulting in censored data. We compared several analysis methods, both univariate and multivariate, on the basis of empirical power and provide an illustrative example of data from a controlled clinical trial. Simulated viral load data demonstrate that methods adjusting for baseline data have power increasing with increasing positive intrasubject correlation expected with this type of data. Several summary measures considered have power compatible with multivariate tests.

Acquired Immunodeficiency Syndrome↗
PubMed2004

Generalized additive models for cancer mapping with incomplete covariates.

Maps depicting cancer incidence rates have become useful tools in public health research, giving valuable information about the spatial variation in rates of disease. Typically, these maps are generated using count data aggregated over areas such as counties or census blocks. However, with the proliferation of geographic information systems and related databases, it is becoming easier to obtain exact spatial locations for the cancer cases and suitable control subjects. The use of such point data allows us to adjust for individual-level covariates, such as age and smoking status, when estimating the spatial variation in disease risk. Unfortunately, such covariate information is often subject to missingness. We propose a method for mapping cancer risk when covariates are not completely observed. We model these data using a logistic generalized additive model. Estimates of the linear and non-linear effects are obtained using a mixed effects model representation. We develop an EM algorithm to account for missing data and the random effects. Since the expectation step involves an intractable integral, we estimate the E-step with a Laplace approximation. This framework provides a general method for handling missing covariate values when fitting generalized additive models. We illustrate our method through an analysis of cancer incidence data from Cape Cod, Massachusetts. These analyses demonstrate that standard complete-case methods can yield biased estimates of the spatial variation of cancer risk.

Algorithms↗
PubMed2006

Progesterone for Premenstrual Syndrome.

BACKGROUND: Premenstrual Syndrome (PMS) is the term for severe symptoms experienced by about 5% of menstruating women up to two weeks before their menstrual periods, but not at other times. Treatment with progesterone may restore a deficiency, or balance the level of progesterone with other menstrual hormones. Progesterone therapy may reduce the effects of falling progesterone levels on the brain or on electrolytes in the blood. OBJECTIVES: The objectives were to determine if progesterone has been found to be an effective treatment for all or some premenstrual symptoms, and if adverse events associated with this treatment have been reported. SEARCH STRATEGY: We last searched the Cochrane Menstrual Disorders and Subfertility Group's Trials Register, the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library, Issue 1, 2005), MEDLINE (1966 to 2005) and EMBASE (1980 to 2005) in March 2005, and PsycINFO (1806 to 2006) in April 2006. We contacted pharmaceutical companies for information about unpublished trials. SELECTION CRITERIA: We included randomised double-blind, placebo-controlled trials of progesterone on women with PMS diagnosed by at least two prospective cycles, without current psychiatric disorder. DATA COLLECTION AND ANALYSIS: Two reviewers (BM and OF) extracted data independently, and decided on the trials to be included. OF wrote to the trial investigators to ask for missing data. MAIN RESULTS: We considered 17 studies. We included two trials totaling 280 participants aged from 18 to 45 years. Of these 115 yielded analysable results. Both studies measured outcomes using subjective scales of symptom severity but made calculations as if they were interval data. The two studies differed in design, participants, dose of progesterone, how and when the dose was administered and in outcome measures. It was impossible to combine data in a meta-analysis. Adverse events which may or may not have been the side effects of the treatment, were generally described as mild. Both trials intended to exclude women whose symptoms continued after their periods; unfortunately the larger multicentre study had some ineligible participants. Overall, participants benefited more from progesterone than placebo. This was statistically significant in per protocol analysis but not in the intention-to-treat analysis, except for the first cycle. The smaller, crossover study found no statistically significant difference between oral progesterone, vaginally absorbed progesterone and placebo. AUTHORS' CONCLUSIONS: We could not say that progesterone helped women with PMS, nor that it was ineffective. Neither trial distinguished a subgroup of women who benefited.

Female↗
PubMed2003

Regional (spinal, epidural, caudal) versus general anaesthesia in preterm infants undergoing inguinal herniorrhaphy in early infancy.

BACKGROUND: With improvements in neonatal intensive care, more premature infants are surviving the neonatal period. With this increase, more are presenting for surgery in early infancy. Of predominance in this period is the repair of inguinal herniae, appearing in 38% of infants whose birth weight is between 751g and 1000g. Most postoperative studies show that approximately 20% to 30% of otherwise healthy former preterm infants having inguinal herniorrhaphy under general anaesthesia have one or more apnoeas in the postoperative period. Regional anaesthesia might reduce postoperative apnoea in this population. OBJECTIVES: To determine if regional anaesthesia, in preterm infants undergoing inguinal herniorrhaphy, reduces post-operative apnoea, bradycardia, and the use of assisted ventilation, in comparison to those infants undergoing inguinal herniorrhaphy with general anaesthesia. SEARCH STRATEGY: Randomised controlled trials were identified by searching MEDLINE (1966-Nov 2002), EMBASE (1982-Nov 2002), Cochrane Central Register of Controlled Trials (CENTRAL, The Cochrane Library, Issue 1, 2002), reference lists of published trials and abstracts published in Pediatric Research. SELECTION CRITERIA: Randomised and quasi-randomised controlled trials of spinal versus general anaesthesia in preterm infants undergoing inguinal herniorrhaphy in early infancy. DATA COLLECTION AND ANALYSIS: Data were extracted and the analyses performed independently by two reviewers. Authors of each eligible study were contacted for missing data. Studies were analysed for methodologic quality using the criteria of the Cochrane Neonatal Review Group. All data were analysed using RevMan 4.1. When possible meta-analysis was performed to calculate typical relative risk, typical risk difference, along with their 95% confidence intervals (CI). MAIN RESULTS: Four small trials comparing spinal with general anaesthesia in the repair of inguinal hernia were identified. One trial was excluded due to inadequate information. There was no statistically significant difference in the proportions of infants having postoperative apnoea/bradycardia, typical RR 0.69 (0.40, 1.21) or postoperative oxygen desaturations, RR 0.91 (0.61, 1.37). If infants having preoperative sedatives were excluded, then the meta-analysis supported a reduction in postoperative apnoea in the spinal anaesthetic group, typical RR 0.39 (0.19, 0.81). There was a reduction of borderline statistical significance in the use of postoperative assisted ventilation with spinal anaesthesia. There was an increase of borderline statistical significance in anaesthetic placement failure when spinal anaesthesia was attempted. REVIEWER'S CONCLUSIONS: There is no reliable evidence from the trials reviewed concerning the effect of spinal as compared to general anaesthesia on the incidence of post-operative apnoea, bradycardia, or oxygen desaturation in ex-preterm infants undergoing herniorrhaphy. The estimates of effect in this review are based on a total population of only 108 patients or fewer.A large well designed randomised controlled trial is needed to determine if spinal anaesthesia reduces post-operative apnoea in ex-preterm infants not pretreated with sedatives. Adequate blinding, follow up and intention to treat analysis are required.

Anesthesia, Conduction↗
PubMed2007

An approach to joint analysis of longitudinal measurements and competing risks failure time data.

Joint analysis of longitudinal measurements and survival data has received much attention in recent years. However, previous work has primarily focused on a single failure type for the event time. In this paper we consider joint modelling of repeated measurements and competing risks failure time data to allow for more than one distinct failure type in the survival endpoint which occurs frequently in clinical trials. Our model uses latent random variables and common covariates to link together the sub-models for the longitudinal measurements and competing risks failure time data, respectively. An EM-based algorithm is derived to obtain the parameter estimates, and a profile likelihood method is proposed to estimate their standard errors. Our method enables one to make joint inference on multiple outcomes which is often necessary in analyses of clinical trials. Furthermore, joint analysis has several advantages compared with separate analysis of either the longitudinal data or competing risks survival data. By modelling the event time, the analysis of longitudinal measurements is adjusted to allow for non-ignorable missing data due to informative dropout, which cannot be appropriately handled by the standard linear mixed effects models alone. In addition, the joint model utilizes information from both outcomes, and could be substantially more efficient than the separate analysis of the competing risk survival data as shown in our simulation study. The performance of our method is evaluated and compared with separate analyses using both simulated data and a clinical trial for the scleroderma lung disease.

Clinical Trials as Topic↗
PubMed2006

The effect of unrelated donor marrow transplantation on health-related quality of life: a report of the unrelated donor marrow transplantation trial (T-cell depletion trial).

The primary objective of this study was to compare health-related quality of life (HRQL) in adult patients undergoing either ex vivo T cell-depleted bone marrow transplantation or conventional marrow transplantation. Data on patients' HRQL were gathered as part of a multicenter randomized trial comparing the effect of ex vivo T-cell depletion versus methotrexate and cyclosporine immunosuppression on disease-free survival. HRQL assessments were conducted at baseline, day +100, 6 months, 1 year, and 3 years. There were no treatment arm differences 1 year after transplantation on the Functional Assessment of Cancer Therapy, Bone Marrow Transplantation, the Medical Outcomes Study Short-Form 36, and the Centers for Epidemiological Studies of Depression. The lack of treatment differences was robust across types of data analyses that took baseline functioning into account and that recognized the sensitivity of outcome measures to assumptions concerning missing data. The trajectory of recovery revealed an initial decrease in function and then a recovery to pretreatment levels that were similar for both treatment arms. Furthermore, the patients in both treatment groups returned to a functional level that approximated general US population norms. Even though the incidence of acute graft-versus-host disease was slightly higher in the conventional treatment arm, T-cell depletion did not differentially affect HRQL at 1 year after transplantation.

Adult↗
PubMed2003

Risk of postnatal depression after emergency delivery.

AIM: To identify whether women having emergency delivery are at increased risk of developing postnatal depression (PND). METHODS: This is a retrospective comparative cohort study design. Two hundred and fifty Malaysian women were part of a previous study examining the prevalence of PND in a multiracial country and the effects of postnatal rituals. All women were at least 6 weeks post-partum when asked to complete the Edinburgh Postnatal Depression Scale (EPDS). Sociodemographic and birth data were obtained. RESULTS: Data collected were divided into two groups: 55 emergency delivery and 191 non-emergency delivery. There were four missing data. There was no significant difference in the mean age, parity, gestational period, baby birthweight, 5 min baby Apgar score and EPDS scores of the two groups. However, the analysis of PND indicated that women with emergency delivery had a relative risk of 1.81 compared with women with non-emergency delivery. The comparison of the two groups using chi2 indicated a significant (chi2 = 3.94, d.f. = 1, P = 0.04) increase in the presence of PND in the emergency delivery. CONCLUSION: When compared with women having non-emergency delivery, women having emergency delivery had about twice the risk of developing PND. Special attention to this group appears warranted.

Adult↗
PubMed2002

Use of personal digital assistants to enhance educational evaluation in a primary care clerkship.

Experiences of students using optically scanned cards were compared with those of students using personal digital assistants (PDAs) to log patient encounters in a primary care clerkship. From April to September 2001, students were offered the option of using a PDA in lieu of scanned cards to track clinical encounters. Data obtained from PDA users were compared with those previously obtained from scanned card users. Verbal and written feedback was obtained from all students. Of the 71 students invited to participate, 21 (30%) owned a PDA, and of these, 20 agreed to participate. Eighteen students completed the pilot. One student was unable to participate owing to software installation problems; another student lost data because of improper back-up. Students using the PDAs recorded more encounters per rotation and had fewer missing data when compared with students who used scanned card. Additionally, feedback from students suggested that PDAs offered other important educational benefits.

Adolescent↗
PubMed2005

Reversal distance for partially ordered genomes.

MOTIVATION: The total order of the genes or markers on a chromosome inherent in its representation as a signed per-mutation must often be weakened to a partial order in the case of real data. This is due to lack of resolution (where several genes are mapped to the same chromosomal position) to missing data from some of the datasets used to compile a gene order, and to conflicts between these datasets. The available genome rearrangement algorithms, however, require total orders as input. A more general approach is needed to handle rearrangements of gene partial orders. RESULTS: We formalize the uncertainty in gene order data by representing a chromosome from each genome as a partial order, summarized by a directed acyclic graph (DAG). The rearrangement problem is then to infer a minimal sequence of reversals for transforming any topological sort of one DAG to any one of the other DAG. Each topological sort represents a possible linearization compatible with all the datasets on the chromosome. The set of all possible topological sorts is embedded in each DAG by appropriately augmenting the edge set, so that it becomes a general directed graph (DG). The DGs representing chromosomes of two genomes are combined to produce a bicoloured graph from which we extract a maximal decomposition into alternating coloured cycles, and from which, in turn, an optimal sequence of reversals can usually be identified. We test this approach on simulated incomplete comparative maps and on cereal chromosomal maps drawn from the Gramene browser.

Algorithms↗
PubMed1993

PRISM: topologically constrained phased refinement for macromolecular crystallography.

We describe the further development of phase refinement by iterative skeletonization (PRISM), a recently introduced phase-refinement strategy [Wilson & Agard (1993). Acta Cryst. A49, 97-104] which makes use of the information that proteins consist of connected linear chains of atoms. An initial electron-density map is generated with inaccurate phases derived from a partial structure or from isomorphous replacement. A linear connected skeleton is then constructed from the map using a modified version of Greer's algorithm [Greer (1985). Methods Enzymol. 115, 206-226] and a new map is created from the skeleton. This 'skeletonized' map is Fourier transformed to obtained new phases, which are combined with any starting-phase information and the experimental structure-factor amplitudes to produce a new map. The procedure is iterated until convergence is reached. In this paper significant improvements to the method are described as is a challenging molecular-replacement test case in which initial phases are calculated from a model containing only one third of the atoms of the intact protein. Application of the skeletonization procedure yields an easily interpretable map. In contrast, application of solvent flattening does not significantly improve the starting map. The iterative skeletonization procedure performs well in the presence of random noise and missing data, but requires Fourier data to at least 3.0 A. The constraints of linearity and connectedness prove strong enough to restore not only missing phase information, but also missing amplitudes. This enables the use of a powerful statistical test, analogous to the 'free R factor' of conventional refinement [Brünger (1992). Nature (London), 355, 472-474], for optimizing the performance of the skeletonization procedure. In the accompanying paper, we describe the application of the method to the solution of the structure of the protease inhibitor ecotin bound to trypsin and to a single isomorphous replacement problem.

Journal Article↗
PubMed2002

Extended generalized estimating equations for binary familial data with incomplete families.

In this article, we assess the performance of two standard, but naive, methods for handling incomplete familial data in GEE2 analyses when the outcome is binary. We also propose a new method for analyzing such data using GEE2 when explanatory variables are discrete. Unlike the naive methods, the new method does not require the missing data process to be ignorable. We illustrate our method with an example that examines the familial aggregation of obesity.

Biometry↗
PubMedDate not supplied

Intraindividual variability and short-term change. Commentary.

BACKGROUND: Interest in the study of intraindividual variability is growing rapidly. OBJECTIVE: The present collection of papers deals with both longer-term, growth and change and shorter-term intraindividual variability. METHODS: The papers emphasize primarily the former within the context of analyzing large, longitudinal data sets. Also discussed are some key methodological matters. RESULTS: Criteria to help with choosing methods and modeling with missing data are included. CONCLUSIONS: A promising direction is toward developing a more systematic and intensive conception of the meaning and significance of the wide variety of manifestations of intraindividual variability and integrating them into theories of aging.

Aging↗
PubMed2004

New developments in medical clinical trials.

This paper reviews several new developments and long-standing good practices for conducting clinical trials. Discussion starts with the need for clear statements of study objectives, proceeds to clarify target and sample population, and elaborates on primary vs. secondary variables with the need for alpha adjustment in the presence of multiple outcomes. Here we also review the issue of surrogate endpoints. Study design issues--including blinding, randomization, and multicenter studies--come next. Then we discuss the current trend of the replacement of placebo-controlled trials by active controlled non-inferiority trials, the increasing use of Independent Data Monitoring Committees, the prominence of analysis on Intention-to-Treat samples, and the importance of imputation of missing data. We close with a brief discussion of the unit of analysis, the role of newer statistical analysis methods, safety issues, subset analysis, and, most importantly, clinical significance.

Clinical Trials Data Monitoring Committees↗
PubMed2003

Modern statistical methods for handling missing repeated measurements in obesity trial data: beyond LOCF.

This paper brings together some modern statistical methods to address the problem of missing data in obesity trials with repeated measurements. Such missing data occur when subjects miss one or more follow-up visits, or drop out early from an obesity trial. A common approach to dealing with missing data because of dropout is 'last observation carried forward' (LOCF). This method, although intuitively appealing, requires restrictive assumptions to produce valid statistical conclusions. We review the need for obesity trials, the assumptions that must be made regarding missing data in such trials, and some modern statistical methods for analysing data containing missing repeated measurements. These modern methods have fewer limitations and less restrictive assumptions than required for LOCF. Moreover, their recent introduction into current releases of statistical software and textbooks makes them more readily available to the applied data analyses.

Clinical Trials as Topic↗
PubMed2003

Modeling longitudinal data with nonignorable dropouts using a latent dropout class model.

In longitudinal studies with dropout, pattern-mixture models form an attractive modeling framework to account for nonignorable missing data. However, pattern-mixture models assume that the components of the mixture distribution are entirely determined by the dropout times. That is, two subjects with the same dropout time have the same distribution for their response with probability one. As that is unlikely to be the case, this assumption made lead to classification error. In addition, if there are certain dropout patterns with very few subjects, which often occurs when the number of observation times is relatively large, pattern-specific parameters may be weakly identified or require identifying restrictions. We propose an alternative approach, which is a latent-class model. The dropout time is assumed to be related to the unobserved (latent) class membership, where the number of classes is less than the number of observed patterns; a regression model for the response is specified conditional on the latent variable. This is a type of shared-parameter model, where the shared "parameter" is discrete. Parameter estimates are obtained using the method of maximum likelihood. Averaging the estimates of the conditional parameters over the distribution of the latent variable yields estimates of the marginal regression parameters. The methodology is illustrated using longitudinal data on depression from a study of HIV in women.

Analysis of Variance↗