Search PubMed⌕ Search

Biomedical subjects

G Molenberghs

Publications and source records attributed to G Molenberghs.

At least 37 records · Page 2Linked to original sources
PubMed2001

Testing for bias in weighted estimating equations.

It is very common in regression analysis to encounter incompletely observed covariate information. A recent approach to analyse such data is weighted estimating equations (Robins, J. M., Rotnitzky, A. and Zhao, L. P. (1994), JASA, 89, 846-866, and Zhao, L. P., Lipsitz, S. R. and Lew, D. (1996), Biometrics, 52, 1165-1182). With weighted estimating equations, the contribution to the estimating equation from a complete observation is weighted by the inverse of the probability of being observed. We propose a test statistic to assess if the weighted estimating equations produce biased estimates. Our test statistic is similar to the test statistic proposed by DuMouchel and Duncan (1983) for weighted least squares estimates for sample survey data. The method is illustrated using data from a randomized clinical trial on chemotherapy for multiple myeloma.

Journal Article↗
PubMed2001

Pesticides and mortality from hormone-dependent cancers.

Endocrine-disrupting chemicals are considered to be a possible cause of hormone-dependent cancers. In areas of high exposure to pesticides, people are concerned about the long lasting toxicity of pesticides, some of which are possibly hormonally active. We collected for each Belgian municipality (n = 589) the latest mortality statistics from breast and prostate cancer (period 1985-1994) and the latest data on crops and pesticides (1998). In addition, data on possible confounders such as population density, degree of urbanization, industrial activity and the presence of an incinerator were collected as well. The data were analysed with spatial statistics that takes into account the spatial nature of the data. There is a large variation in crops and pesticide exposure among the municipalities, the highest exposure being seen in the fruit production area. Apart from use of defoliants and potato cultivation, no consistent correlation was detected between crops, pesticides and mortality from breast and prostate cancer. Our data cannot support the hypothesis of a relationship between total and class-related pesticide use and breast and prostate cancer mortality. However, the increased mortality due to breast cancer and to a lesser extent due to prostate cancer in traditional potato-growing areas needs attention and more research.

Belgium↗
PubMed2001

Sensitivity analysis for nonrandom dropout: a local influence approach.

Diggle and Kenward (1994, Applied Statistics 43, 49-93) proposed a selection model for continuous longitudinal data subject to nonrandom dropout. It has provoked a large debate about the role for such models. The original enthusiasm was followed by skepticism about the strong but untestable assumptions on which this type of model invariably rests. Since then, the view has emerged that these models should ideally be made part of a sensitivity analysis. This paper presents a formal and flexible approach to such a sensitivity assessment based on local influence (Cook, 1986, Journal of the Royal Statistical Society, Series B 48, 133-169). The influence of perturbing a missing-at-random dropout model in the direction of nonrandom dropout is explored. The method is applied to data from a randomized experiment on the inhibition of testosterone production in rats.

Animals↗
PubMed2001

Bias in estimating association parameters for longitudinal binary responses with drop-outs.

This paper considers the impact of bias in the estimation of the association parameters for longitudinal binary responses when there are drop-outs. A number of different estimating equation approaches are considered for the case where drop-out cannot be assumed to be a completely random process. In particular, standard generalized estimating equations (GEE), GEE based on conditional residuals, GEE based on multivariate normal estimating equations for the covariance matrix, and second-order estimating equations (GEE2) are examined. These different GEE estimators are compared in terms of finite sample and asymptotic bias under a variety of drop-out processes. Finally, the relationship between bias in the estimation of the association parameters and bias in the estimation of the mean parameters is explored.

Algorithms↗
PubMed2001

An exact trend test for correlated binary data.

The problem of testing a dose-response relationship in the presence of exchangeably correlated binary data has been addressed using a variety of models. Most commonly used approaches are derived from likelihood or generalized estimating equations and rely on large-sample theory to justify their inferences. However, while earlier work has determined that these methods may perform poorly for small or sparse samples, there are few alternatives available to those faced with such data. We propose an exact trend test for exchangeably correlated binary data when groups of correlated observations are ordered. This exact approach is based on an exponential model derived by Molenberghs and Ryan (1999) and Ryan and Molenberghs (1999) and provides natural analogues to Fisher's exact test and the binomial trend test when the data are correlated. We use a graphical method with which one can efficiently compute the exact tail distribution and apply the test to two examples.

Abnormalities, Drug-Induced↗
PubMed2000

Relation between tumour response to first-line chemotherapy and survival in advanced colorectal cancer: a meta-analysis. Meta-Analysis Group in Cancer.

BACKGROUND: Treatment of advanced colorectal cancer has progressed substantially. However, improvements in response rates have not always translated into significant survival benefits. Doubts have therefore been raised about the usefulness of tumour response as a clinical endpoint. METHODS: This meta-analysis was done on individual data from 3791 patients enrolled in 25 randomised trials of first-line treatment with standard bolus intravenous fluoropyrimidines versus experimental treatments (fluorouracil plus leucovorin, fluorouracil plus methotrexate, fluorouracil continuous infusion, or hepatic-arterial infusion of floxuridine). Analyses were by intention to treat. FINDINGS: Compared with bolus fluoropyrimidines, experimental fluoropyrimidines led to significantly higher tumour response rates (454 responses among 2031 patients vs 209 among 1760; odds ratio 0.48 [95% CI 0.40-0.57], p<0.0001) and better survival (1808 deaths among 2031 vs 1580 among 1760; hazard ratio 0.90 [0.84-0.97], p=0.003). The survival benefits could be explained by the higher tumour response rates. However, a treatment that lowered the odds of failure to respond by 50% would be expected to decrease the odds of death by only 6%. In addition, less than half of the variability of the survival benefits in the 25 trials could be explained by the variability of the response benefits in these trials. INTERPRETATION: These analyses confirm that an increase in tumour response rate translates into an increase in overall survival for patients with advanced colorectal cancer. However, in the context of individual trials, knowledge that a treatment has benefits on tumour response does not allow accurate prediction of the ultimate benefit on survival.

Antimetabolites, Antineoplastic↗
PubMed2000

Summary measures and statistics in the analysis of quality of life data: an example from an EORTC-NCIC-SAKK locally advanced breast cancer study.

Quality of Life (QL) is now included as an endpoint in many phase III cancer clinical trials. Numerous statistical techniques have been presented in the literature to analyse QL data but there is still no agreement as to what is the optimal approach of analysis. In this paper we, therefore, present and compare various techniques which have all appeared in the literature and which may be globally described as summary measures and summary statistics. These techniques are illustrated using data from an EORTC clinical trial in locally advanced breast cancer (EORTC trial 10921). It is also explained in this paper how and when these techniques may be used in other cancer settings. For EORTC trial 10921, it is shown that by choosing different techniques different conclusions may be drawn concerning the QL outcome. This highlights the importance of choosing an appropriate primary statistical method and for describing it a priori in the protocol and analysis plan. In this paper, we show the importance of performing sensitivity or supportive analysis to support conclusions drawn from the primary analysis.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed2000

The dysphonia severity index: an objective measure of vocal quality based on a multiparameter approach.

The vocal quality of a patient is modeled by means of a Dysphonia Severity Index (DSI), which is designed to establish an objective and quantitative correlate of the perceived vocal quality. The DSI is based on the weighted combination of the following selected set of voice measurements: highest frequency (F(0)-High in Hz), lowest intensity (I-Low in dB), maximum phonation time (MPT in s), and jitter (%). The DSI is derived from a multivariate analysis of 387 subjects with the goal of describing, purely based on objective measures, the perceived voice quality. It is constructed as DSI = 0.13 x MPT + 0.0053 x F(0)-High - 0.26 x I-Low - 1.18 x Jitter (%) + 12.4. The DSI for perceptually normal voices equals +5 and for severely dysphonic voices -5. The more negative the patient's index, the worse is his or her vocal quality. As such, the DSI is especially useful to evaluate therapeutic evolution of dysphonic patients. Additionally, there is a high correlation between the DSI and the Voice Handicap Index score.

Adolescent↗
PubMed2000

The validation of surrogate endpoints in meta-analyses of randomized experiments.

The validation of surrogate endpoints has been studied by Prentice (1989). He presented a definition as well as a set of criteria, which are equivalent only if the surrogate and true endpoints are binary. Freedman et al. (1992) supplemented these criteria with the so-called 'proportion explained'. Buyse and Molenberghs (1998) proposed replacing the proportion explained by two quantities: (1) the relative effect linking the effect of treatment on both endpoints and (2) an individual-level measure of agreement between both endpoints. The latter quantity carries over when data are available on several randomized trials, while the former can be extended to be a trial-level measure of agreement between the effects of treatment of both endpoints. This approach suggests a new method for the validation of surrogate endpoints, and naturally leads to the prediction of the effect of treatment upon the true endpoint, given its observed effect upon the surrogate endpoint. These ideas are illustrated using data from two sets of multicenter trials: one comparing chemotherapy regimens for patients with advanced ovarian cancer, the other comparing interferon-alpha with placebo for patients with age-related macular degeneration.

Journal Article↗
PubMed2000

GEE with Gaussian estimation of the correlations when data are incomplete.

This paper considers a modification of generalized estimating equations (GEE) for handling missing binary response data. The proposed method uses Gaussian estimation of the correlation parameters, i.e., the estimating function that yields an estimate of the correlation parameters is obtained from the multivariate normal likelihood. The proposed method yields consistent estimates of the regression parameters when data are missing completely at random (MCAR). However, when data are missing at random (MAR), consistency may not hold. In a simulation study with repeated binary outcomes that are missing at random, the magnitude of the potential bias that can arise is examined. The results of the simulation study indicate that, when the working correlation matrix is correctly specified, the bias is almost negligible for the modified GEE. In the simulation study, the proposed modification of GEE is also compared to the standard GEE, multiple imputation, and weighted estimating equations approaches. Finally, the proposed method is illustrated using data from a longitudinal clinical trial comparing two therapeutic treatments, zidovudine (AZT) and didanosine (ddI), in patients with HIV.

Anti-HIV Agents↗
PubMed1999

Modelling long-term persistence of hepatitis B antibodies after vaccination.

Antibody response to hepatitis B vaccination was measured in 97 institutionalized, mentally handicapped patients after a 0-, 1-, 6-month vaccination schedule. Two groups were formed at month 7 according to the antibody response, which determined whether they needed an additional vaccine dose at month 12, to achieve an antibody titre of 100 IU/liter. All residents were followed up yearly for the first 5 years, after which, they received another booster dose. Another blood sample was taken 11 years after the start of the program. A linear mixed-regression model was used to analyze the data. Random and fixed effects were included to determine the generally known risk factors and the still unknown individual characteristics that influence the titre of hepatitis B surface antibodies (anti-HBs). The mean anti-HBs titre was a function of time, type of mental retardation (Down's syndrome or other types of mental retardation), the use of antiepileptic drugs, and the additional booster at month 12. The immediate and vigorous response of the immune system to booster vaccination shows that the immunologic memory is good after primary vaccination. For the maintenance of protection, the recommendation for mentally retarded patients in institutions is vaccination of all seronegative residents as well as new entrants, after which, no additional boosters will be necessary.

Anticonvulsants↗
PubMed1999

Effects of soft drink and table beer consumption on insulin response in normal teenagers and carbohydrate drink in youngsters.

There is ample evidence that breast cancer susceptibility is induced during the developmental stages of the human breast where, in a manner related to sex-steroid hormones, insulin plays an important role. In turn, nutrition might be implicated. Regular soft drinks and table beer, both carbohydrate-containing drinks, are candidates affecting insulin concentrations. Eleven teenagers, between the ages of 13 and 17 years, consumed a soft drink and a table beer in a crossover study. The blood levels of insulin and glucose were related to anthropomorphometric and endocrine factors. In contrast to table beer, consumption of regular soft drinks induced a fast and dramatic increase in both glucose and insulin concentration within a maximum 1 hour after consumption. The insulin response was linearly correlated to the body mass index (BMI). Children with a small increase in BMI are highly sensitive to regular soft drinks with regard to glucose and insulin response. The finding suggests a vicious circle of high caloric drinks, increase in BMI and insulin response. It is one of the nutritional pathways which might affect susceptibility for breast cancer in youngsters. Table beer, a drink with fermented sugars, does not share these effects on carbohydrate metabolism.

Adolescent↗
PubMed1999

Selection models and pattern-mixture models for incomplete data with covariates.

Most models for incomplete data are formulated within the selection model framework. This paper studies similarities and differences of modeling incomplete data within both selection and pattern-mixture settings. The focus is on missing at random mechanisms and on categorical data. Point and interval estimation is discussed. A comparison of both approaches is done on side effects in a psychiatric study.

Biometry↗
PubMed1999

Statistical methods for developmental toxicity. Analysis of clustered multivariate binary data.

This paper discusses some of the statistical issues that arise from developmental toxicity studies, wherein pregnant mice are exposed to chemicals in order to assess possible adverse effects on developing fetuses. We begin with a review of some current approaches to risk assessment, based on NOAELs, and provide justification for the use of methods based on dose-response models. Due to the hierarchical nature of the data, such models are more complicated in the present context than, say, in cancer studies. For example, multivariate binary outcomes arise when each fetus in a litter is assessed for the presence of malformations and/or low birth weight. We describe a multivariate exponential family model that works well for these data and that is flexible in terms of allowing response rates to depend on cluster side. Maximum likelihood estimation of model parameters and the construction of score tests for dose effect are briefly discussed. Results are illustrated with data from several NTP studies.

Animals↗
PubMed1999

Parametric models for incomplete continuous and categorical longitudinal data.

This paper reviews models for incomplete continuous and categorical longitudinal data. In terms of Rubin's classification of missing value processes we are specifically concerned with the problem of nonrandom missingness. A distinction is drawn between the classes of selection and pattern-mixture models and, using several examples, these approaches are compared and contrasted. The central roles of identifiability and sensitivity are emphasized throughout.

Data Interpretation, Statistical↗
PubMed1999

Analysis of incomplete public health data.

The problem of dealing with missing values is common throughout statistics and is very prominent with epidemiologic data in the broad sense. Not only do data collection procedures break down, but subjects may be lost to follow up, or simply withdraw their consent without further providing a reason for doing so. In this paper, we review a framework for handling incomplete studies, and then concentrate on a specific case. It comes from a complex health interview survey, conducted in Belgium in 1997, where different types of missingness arise at various levels of the hierarchical sampling procedure.

Belgium↗
PubMed1998

Estimating the causal effect of compliance on binary outcome in randomized controlled trials.

We examine likelihood based methods aimed at analysing the causal effect of actual exposure to drug treatment on a (repeated) binary outcome in two randomized trials with partial compliance. Starting with the univariate compliance summary 'total treatment dose history', we apply a method for ordinal compliance and monotone dose response, proposed by Goetghebeur and Molenberghs. In a short duration trial of blood pressure reduction, this summary leads to meaningful effect estimators. However, in the analysis of a vitamin A trial, this method reaches a boundary solution; the estimated possible benefit from vitamin A for children who did not receive any pills on the treatment arm is zero. In our formulation the number of pills that were taken captures part of the outcome, and the corresponding effect parameters suffer from this confounding. To gain additional insight, we account explicitly for the temporal structure of compliance. We extend the likelihood based methodology for univariate ordered compliance to more dimensional compliance with only a partial order structure on exposure. The randomization assumptions in the causal formulation of Rubin are translated to this setting. We motivate a set of parametric assumptions on the joint distribution of potential outcomes and observed compliance levels and reanalyse the vitamin A trial. Our findings suggest that one capsule of vitamin A had a large impact on mortality during the first 4 months. The greatest reduction in risk was estimated amongst children who received two doses. This supports findings from a vitamin A trial in Ghana and in Nepal. Finally, we discuss extensions of this method, covering uncensored and censored grouped survival data.

Adult↗