Targeted minimum loss based estimator that outperforms a given estimator

Targeted minimum loss based estimation (TMLE) provides a template for the construction of semiparametric locally efficient double robust substitution estimators of the target parameter of the data generating distribution in a semiparametric censored data or causal inference model (van der Laan and Rubin (2006), van der Laan (2008), van der Laan and Rose (2011)). In this article we demonstrate how to construct a TMLE that also satisfies the property that it is at least as efficient as a user supplied asymptotically linear estimator. In particular it is shown that this type of TMLE can incorporate empirical efficiency maximization as in Rubin and van der Laan (2008), Tan (2008, 2010), Rotnitzky et al. (2012), and retain double robustness. For the sake of illustration we focus on estimation of the additive average causal effect of a point treatment on an outcome, adjusting for baseline covariates.     

Bone marrow cell therapy after acute myocardial infarction: the HEBE trial in perspective, first results

During the last decennium, the role of bone marrow mononuclear cells (BMMC) has been underscored in the healing process after acute myocardial infarction (AMI). Although these cells improve left ventricular recovery after AMI in experimental studies, results from large-scale randomised trials investigating BMMC therapy in patients with AMI have shown contradictory results. To address this issue the HEBE study was designed, a multicentre, randomised trial, evaluating the effects of intracoronary infusion of BMMCs and the effects of intracoronary infusion of peripheral blood mononuclear cells after primary percutaneous coronary intervention. The primary endpoint of the HEBE trial is the change in regional myocardial function in dysfunctional segments at four months relative to baseline, based on segmental analysis as measured by magnetic resonance imaging. The results from the HEBE trial will provide detailed information about the effects of intracoronary BMMC therapy on post-infarct left ventricular recovery. In addition, further analysis of the data and material obtained may provide important mechanistic insights into the contribution of BMMCs to natural recovery from AMI as well as the response to cell therapy. This may significantly contribute to the development of improved cell-based therapies, aiming at optimising post-infarct recovery and preventing heart failure. (Neth Heart J 2008;16:436-9.)     

Pituitary adenylate cyclase-activating peptide inhibits neutrophil chemotaxis

Pituitary adenylate cyclase-activating peptide 38 (PACAP 38) is a neuropeptide that displays several biological effects of interest in the context of airway diseases such as asthma and chronic obstructive pulmonary disease. These effects include inhibition of airway and vascular smooth muscle tone as well as modulation of inflammatory cell activity. However, little is known about the effect of PACAP on granulocytes. The present study was designed to investigate if PACAP and the closely related peptide vasoactive intestinal peptide (VIP) could affect neutrophil migration. A standard 48 well chemotaxis chamber was used to assess the effects of PACAP on N-Formyl-L-methionyl-L-leucyl-L-phenylalanine (fMLP)-induced neutrophil chemotaxis and spontaneous random migration. PACAP 38 and VIP inhibited fMLP-induced human neutrophil chemotaxis. Furthermore, both peptides also exhibited a dose-related trend toward inhibiting the spontaneous, unstimulated migration of neutrophils. Since enhanced cell migration in cell chamber systems is reported to correlate with increased invasive properties in vivo, the presented inhibitory effects of PACAP 38 on neutrophil chemotaxis, supports the idea of an anti-inflammatory role for PACAP. This together with the well documented bronchodilatory capacity of PACAP might indicate a role for PACAP-agonists in future treatment of asthma and other inflammatory airway diseases.     

Classical Analysis of Variance Methods and Nonparametric Counterparts

The present investigation is concerned with the use of classical and nonparametric techniques in the analysis of experiments. Occasionally biometricians are confronted with results arising from an experiment with data which do not necessarily satisfy the assumption of Normality, the basis of the classical analysis of variance methods. Sometimes the biometrician handles such a situation by transformation of the observations and applying the classical techniques. Although this attack may lead to a satisfactory analysis, the results may be questionable in a number of cases. In analyzing continuous data without the Normality assumption nonparametric methods provide realistic alternatives. In this paper a number of problems will be discussed with and without the Normality assumption resulting in the well-known classical analysis and its nonparametric counterparts. Most of the nonparametric procedures to be discussed are based on ranks.     

Book reviews

Book reviewed in this article: B. D. MORETON: Beneficial Insects and Mites. Min. Agric., Fisher, and Food, Bull. W. ETKIN and L. I. GILBERT (Eds.): Metamorphosis (A Problem in Developmental Biology). H. W. MULLIGAN (Ed.): The A[rican Trypanosomiases. George Allen and Unwin Ltd.     

Circular pools in the seagrass beds of the Banc d’Arguin,Mauritania, and their possible origin

The tidal flats of the Banc d’Arguin, Mauritania, are covered by vast beds of Zostera noltii. At low tide these seagrass beds appear to be interspersed with partly vegetated, circular pools of 5–25 m diameter. Between February and May 2001 we described these pools and studied their possible origin. Several hypotheses regarding the origin have been developed. The first group of hypotheses assumes that the pools result from erosion activity. Since human disturbance of seagrass beds at the Banc d’Arguin is virtually non-existent, causes should be found in natural bed disturbances and/or tide or wave action. Therefore, small gaps, simulating holes dug by the crab Callinectes marginatus, were made to see if they would further erode by tidal currents or waves. The experiments showed no erosion. Neither we found support for other hypotheses assuming erosion to be the cause of circular pools. The alternative group of hypotheses stated that sedimentation on the flats would be responsible. We conclude that accretion of creek remnants is the most likely process behind the development of the pools; this conclusion is based on both mapping of the pattern of pools, the sediment profile in and around the pools and the distribution of seagrass biomass. Also the disturbance experiments showed bed accretion rather than bed erosion and support this hypothesis.