475 research outputs found
Asymptotics For The Simex Estimator In Structural Measurement Error Models
No full textCook & Stefanski (1994) describe a computer intensive method, the SIMEX method, for approximately consistent estimation in regression problems with additive measurement error. In this paper, we derive the asymptotic distribution of their estimators and show how to compute estimated standard errors. These standard error estimators can either be used alone or as prepivoting devices in a bootstrap analysis. We also give theroetical justification to some of the phenomena observed by Cook & Stefanski in their simulations. Some Key Words: Asymptotics, Bootstrap, Computationally Intensive Methods, Measurement Error Models. Authors' Affiliations R. J. Carroll is Professor of Statistcs at Texas A&M University, College Station, TX 77843-- 3143. F. Lombard is Professor of Statistics, Rand Afrikaans University, P.O. Box 524, Johannesburg 2000, South Africa. H. Kuchenhoff is Wissenschaftlicher Assistent, Seminar fur Okonometrie und Statistik, Universitat Munchen, Akademiestrasse 1, D-80799 Munch..
Density Deconvolution with Replicate Measurements and Auxiliary Data
No full textWe present two deconvolution estimators for the density function of a random variable X that is measured with error. The first estimates the density of X from the set of independent replicate measurements W[subscript r,j], where W[subscript r,j]=X[subscript x]+U[subscript r,j] for r=1,...,n and j=1,...m[subscript r]. We derive an estimator assuming that the U[subscript r,j] are normally distributed measurement errors having unknown and possibly nonconstant variances σ[subscript r]². The estimator generalizes the deconvolution estimator of Stefanski and Carroll (1990), with the measurement error variances estimated from replicate observations. We derive the integrated meansquared error and examine the rate of convergence as n → ∞ and the number of replicates is fixed.The finite-sample performance of the estimator is illustrated through a simulation study and an example.
The second is a semi-parametric deconvolution estimator that assumes the availability of a covariate vector Z statistically related to X, but independent of the error in measuring X, and such that the regression error X-E(X|Z) is normally distributed. The estimator combines parametric modeling of the regression residuals with nonparametric estimation of the mean function. The asymptotic properties of the estimator are discussed. The reliance of the estimator on assumptions of the regression model and normality of model errors is examined via simulation, and an application to real data is presented
Personalized intensification of insulin therapy in type 2 diabetes - does a basal-bolus regimen suit all patients?
No full textDietary changes in nutritional studies shape the structural and functional composition of the pigs' fecal microbiome-from days to weeks
No full textBackground: The possible impact of changes in diet composition on the intestinal microbiome is mostly studied after some days of adaptation to the diet of interest. The question arises if a few days are enough to reflect the microbial response to the diet by changing the community composition and function. The present study investigated the fecal microbiome of pigs during a time span of 4 weeks after a dietary change to obtain insights regarding the time required for adaptation. Four different diets were used differing in either protein source (field peas meal vs. soybean meal) or the concentration of calcium and phosphorus (CaP). Results: Twelve pigs were sampled at seven time points within 4 weeks after the dietary change. Fecal samples were used to sequence the 16S rRNA gene amplicons to analyse microbial proteins via LC-MS/MS and to determine the SCFA production. The analysis of OTU abundances and quantification values of proteins showed a significant separation of three periods of time (p = 0.001). Samples from the first day are used to define the 'zero period'; samples of weeks 1 and 2 are combined as 'metabolic period' and an 'equilibrium period was defined based on samples from weeks 3 and 4. Only in this last period, a separation according to the supplementation of CaP was significantly detectable (p = 0.001). No changes were found based on the corn-soybean meal or corn-field peas administration. The analysis of possible factors causing this significant separation showed only an overall change of bacterial members and functional properties. The metaproteomic approach yielded a total of about 9700 proteins, which were used to deduce possible metabolic functions of the bacterial community. Conclusions: A gradual taxonomic and functional rearrangement of the bacterial community has been depicted after a change of diet composition. The adaptation lasts several weeks despite the usually assumed time span of several days. The obtained knowledge is of a great importance for the design of future nutritional studies. Moreover, considering the high similarities between the porcine and human gastrointestinal tract anatomy and physiology, the findings of the current study might imply in the design of human-related nutritional studies
Effects of measurement error on catch-effort estimation
No full text We have investigated the consequences of using imprecise catch and effort estimates in closed-population catch-effort analyses using traditional regression techniques and maximum likelihood to estimate the catchability coefficient and population size parameters. Our simulation study involved adding known amounts of measurement error to error-free catch and effort data to determine the effects of using such estimates of catch and effort rather than the true, and in many cases unknown, quantities. Our results suggest that naive estimation using estimates of catch and effort as true values may bias estimates of population size and the catchability coefficient. In most cases, the effects of measurement error in catch and effort were to inflate the parameter estimates, the magnitude of inflation being dependent on the size of the measurement error variance. Maximum likelihood estimation proved to be the estimation procedure most robust to the errors in measurement, but still displayed the need for correction of the measurement-error-induced bias. A recently developed simulation-extrapolation method of inference (J.R. Cook and L.A. Stefanski. 1994. J. Am. Stat. Assoc. 89: 1314-1328) is suggested as a possible means for making bias adjustments. </jats:p
Biomass Burning in the Global Environment: First Results from the IGAC/BIBEX Field Campaign STARE/TRACE-A/SAFARI-92
No full textSince the STAREITRACE-NSAFARI-92 Science Team is too numerous to be included in the author list, only those who have contributed text to this paper are listed on the title page. The others are: A-L. Ajavon, C. Anderson, T.W. Andreae, H.J. Annegarn, C.B. Archer, P. Artaxo, E. Atlas, R.E. Babbitt, J. Barsby, J. Beer, R.J. Bendura, D. Bergmann, D.R. Blake, G.E. Bodeker, T. Boyle, J.D. Bradshaw, J.K. Broadbent, E.V. Browell, E.G. Brunke, R.A Burke, H. Cachier, J. Cafmeyer, D.J. Cahoon, R Chadyendiya, M. Chaitwa, T.-Y. Chen, G.J.R Coetzee, W.R Cofer III, J.E. Collins, B. Cros, P. Cunningham, G. de Beer, A de Kock, R. Delmas, RD. Diab, P. Dowty, B.L. Duigan, F. Echalar, M. Edwards, W. Elbert, T. Fickinger, A. Gaudichet, S.J. Godefroy, G.L. Gregory, M. Guest, G.W. Harris, G. Helas, G. Held, J.L. Hery, J.M. Hoell, R Hudson, C. Jambert, A Joubert, M.R. Jury, P. Kiillberg, RP. Karimanzira, J.B. Kauffman, J. Kendall, J. Kim, V.W.J.H. Kirchhoff, M.A Kneen, R. Koppmann, T.N. Krishnamurti, F. Kruger, T. Kuhlbusch, C. Labuschagne, J.P. Lacaux, C. Liousse, E. Lynch, S.A. Macko, W. Maenhaut, C. Manickum, B. Martincigh, P. Masclet, J.A Mason, G.K. Mather, M.A Mazurek, D.P. McNamara, D.J. McRae, F. Meixner, W.L. Miller, E. Mpunduma, E. Mravlag, W. Munyanyiwa, A. Mwale, S. O'Beirne, U. Parchatka, D. Parsons, K. Pickering, J.J. Pienaar, S. Piketh, J.P. Pinto, W. Pollock, A Potgieter, RA. Preston-Whyte, M.W. Raynor, R Rorich, J. Rudolph, G.W. Sachse, I. Salma, S.T. Sandholm, W. Schneider, M.C. Scholes, M. Schormann, G.C. Schulze, M. Scourfield, D.I. Sebacher, M.K. Seely, R. Shea, H.B. Singh, N. Snow, F. Sokolic, B. Stefanski, R. Swap, R.W. Talbot, I. Taviv, A Tegen, M. Thompson, G.R. Tosen, L. Trollope, W.S.W. Trollope, M.M. Truter, S. Tsure, C. Turner, P. Tyson, J. van Heerden, D. Walmsley, D.E. Ward, M.G. Weber, F. Weirich, M. Welling, F.G. Wienhold, E.L. Winstead, T. Zenker, RG. Zepp, and M. Zunckel.Biomass burning is now recognized as a major source of important trace gases, including CO₂, NO₂, CO and CH₄, and of aerosol particles. It takes on many forms: burning of forested areas for land clearing, extensive burning of grasslands and savannas to sustain grazing lands, burning of harvest debris, and use of biomass fuel for heating.https://link.springer.com/chapter/10.1007/978-1-4615-2524-0_
Use of simulation–extrapolation estimation in catch–effort analyses
No full text All catch-effort estimation methods implicitly assume catch and effort are known quantities, whereas in many cases, they have been estimated and are subject to error. We evaluate the application of a simulation-based estimation procedure for measurement error models (J.R. Cook and L.A. Stefanski. 1994. J. Am. Stat. Assoc. 89: 1314-1328) in catch-effort studies. The technique involves a simulation component and an extrapolation step, hence the name SIMEX estimation. We describe SIMEX estimation in general terms and illustrate its use with applications to real and simulated catch and effort data. Correcting for measurement error with SIMEX estimation resulted in population size and catchability coefficient estimates that were substantially less than naive estimates, which ignored measurement errors in some cases. In a simulation of the procedure, we compared estimators from SIMEX with "naive" estimators that ignore measurement errors in catch and effort to determine the ability of SIMEX to produce bias-corrected estimates. The SIMEX estimators were less biased than the naive estimators but in some cases were also more variable. Despite the bias reduction, the SIMEX estimator had a larger mean squared error than the naive estimator for one of two artificial populations studied. However, our results suggest the SIMEX estimator may outperform the naive estimator in terms of bias and precision for larger populations. </jats:p
Slope estimation of covariates that influence renal outcome following renal transplant adjusting for informative right censoring
No full textA new statistical model is proposed to estimate population and individual slopes that are adjusted for covariates and informative right censoring. Individual slopes are assumed to have a mean that depends on the population slope for the covariates. The number of observations for each individual is modeled as a truncated discrete distribution with mean dependent on the individual subjects' slopes. Our simulation study results indicated that the associated bias and mean squared errors for the proposed model were comparable to those associated with the model that only adjusts for informative right censoring. The proposed model was illustrated using renal transplant dataset to estimate population slopes for covariates that could impact the outcome of renal function following renal transplantation. © 2012 Copyright Taylor and Francis Group, LLC.Fletcher R., 1987, PRACTICAL METHODS OP; Jaffa MA, 2010, RENAL FAILURE, V32, P691, DOI 10.3109-0886022X.2010.486495; Jaffa MA, 2011, J R STAT SOC A STAT, V174, P387, DOI 10.1111-j.1467-985X.2010.00671.x; JENNRICH RI, 1986, BIOMETRICS, V42, P805, DOI 10.2307-2530695; Laird N.M., 1988, STAT MED, V44, P175; LAIRD NM, 1982, BIOMETRICS, V38, P963, DOI 10.2307-2529876; LAIRD NM, 1990, CONTROL CLIN TRIALS, V11, P405, DOI 10.1016-0197-2456(90)90018-W; Linsdstrom MJ, 1988, J AM STAT ASSOC, V83, P1014; MORI M, 1994, BIOMETRICS, V50, P39, DOI 10.2307-2533195; Pinheiro J. C., 1995, J COMPUTATIONAL GRAP, V4, P12, DOI [10.1080-10618600.1995.10474663, DOI 10.2307-1390625]; REED E, 1992, TRANSPLANT P, V24, P2670; RICHIE RE, 1983, ANN SURG, V197, P672, DOI 10.1097-00000658-198306000-00005; SAS (Statistical Analysis System) Institute, 2002, SAS STAT 9 2 US GUID; SCHLUCHTER MD, 1992, STAT MED, V11, P1861, DOI 10.1002-sim.4780111408; STEFANSKI LA, 1985, ANN STAT, V13, P1335, DOI 10.1214-aos-1176349741; VONESH EF, 1987, BIOMETRICS, V43, P617, DOI 10.2307-2531999; WU MC, 1988, BIOMETRICS, V44, P175, DOI 10.2307-2531905; WU MC, 1988, CONTROL CLIN TRIALS, V9, P32, DOI 10.1016-0197-2456(88)90007-4; WU MC, 1989, BIOMETRICS, V45, P939, DOI 10.2307-25316940
Short-term inhibition of p53 combined with keratinocyte growth factor improves thymic epithelial cell recovery and enhances T-cell reconstitution after murine bone marrow transplantation
No full textMyeloablative conditioning before bone marrow transplantation (BMT) results in thymic epithelial cell (TEC) injury, T-cell immune deficiency, and susceptibility to opportunistic infections. Conditioning regimen–induced TEC damage directly contributes to slow thymopoietic recovery after BMT. Keratinocyte growth factor (KGF) is a TEC mitogen that stimulates proliferation and, when given before conditioning, reduces TEC injury. Some TEC subsets are refractory to KGF and functional T-cell responses are not fully restored in KGF-treated BM transplant recipients. Therefore, we investigated whether the addition of a pharmacologic inhibitor, PFT-β, to transiently inhibit p53 during radiotherapy could spare TECs from radiation-induced damage in congenic and allogeneic BMTs. Combined before BMT KGF + PFT-β administration additively restored numbers of cortical and medullary TECs and improved thymic function after BMT, resulting in higher numbers of donor-derived, naive peripheral CD4+ and CD8+ T cells. Radiation conditioning caused a loss of T-cell zone fibroblastic reticular cells (FRCs) and CCL21 expression in lymphoid stroma. KGF + PFT-β treatment restored both FRC and CCL21 expression, findings that correlated with improved T-cell reconstitution and an enhanced immune response against Listeria monocytogenes infection. Thus, transient p53 inhibition combined with KGF represents a novel and potentially translatable approach to promote rapid and durable thymic and peripheral T-cell recovery after BMT.Ryan M. Kelly, Emily M. Goren, Patricia A. Taylor, Scott N. Mueller, Heather E. Stefanski, Mark J. Osborn, Hamish S. Scott, Elena A. Komarova, Andrei V. Gudkov, Georg A. Holländer and Bruce R. Blaza
- …
