SEARCH · PubMed Health

Results for “parameter estimation”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 631 records · Page 35Linked to original sources

PubMed2004

Mathematical and statistical analysis of the Trypanosoma brucei slender to stumpy transition.

We propose a new model for the Stumpy Induction Factor-induced slender to stumpy transformation of Trypanosoma brucei gambiense cells in immunosuppressed mice. The model is a set of delay differential equations that describe the time-course of the infection. We fit the model, using a maximum-likelihood method, to previously published data on parasitaemia in four mice. The model is shown to be a good fit and parameter estimates and confidence intervals are derived. Our estimated parameter values are consistent with estimates from previous experimental studies. The model predicts the following. Slender cells can be classified as uncommitted, committed and dividing, and committed and non-dividing. A committed slender cell undergoes about 5 divisions before exiting the cell-cycle. Committed slender cells must produce SIF, and stumpy cells must not produce SIF. There are two mechanisms for differentiation, a background differentiation rate, and a SIF-concentration-dependent differentiation rate, which is proportional to SIF concentration. SIF has a half-life of about 1.4 h in mice. We also show, with suitable changes in the parameter values, that the model reflects behaviours seen in other host species and trypanosome strains.

Animals↗

PubMed1990

Estimates of genetic parameters in turkeys. 3. Sexual dimorphism and its implications in selection procedures.

Live, carcass, and skeletal data taken at 16 wk of age on 504 female and 584 male turkeys from 34 sires and 168 dams were utilized to evaluate sex differences in genetic parameter estimates. Data were transformed to common mean and variance to evaluate possible scaling effects. Genetic parameters were estimated from transformed and untransformed data. Further analyses were conducted with a model that included sire by sex and dams within sire by sex interactions, and the variance estimates were used to calculate genetic correlations between the sexes and genetic regression parameters. Heritability estimates from transformed and untransformed data were similar, indicating that sex differences were present in the genetic parameters, but scaling effects were not an important factor. Genetic correlation estimates from paternal (PHS) and maternal (MHS) half-sib estimates were close to unity for BW (1.14, PHS; 1.09, MHS), shank width (.99, PHS; .93, MHS), breast muscle weight (1.23, PHS; 1.04, MHS), and shank length (1.09, PHS; .97, MHS). However, abdominal fat (.79, PHS; .59 MHS), total drumstick muscle weight (.75, PHS; 1.14, MHS), rough cleaned shank weight (.78, PHS; not estimatable, MHS), and shank bone density (1.00, PHS; .53, MHS) estimates were somewhat lower. The estimates suggest that the measurement of these latter "traits" at the same age in the two sexes may, in fact, be measuring different genetic effects and that selection procedures in turkeys need to take these correlations into account in order to make optimum progress. The genetic regression parameters indicated that more intense selection in the sex that has the smaller genetic variation could be practiced to make greater gains in the opposite sex.

Analysis of Variance↗

PubMed2007

A mathematical model of zinc absorption in humans as a function of dietary zinc and phytate.

The quantities of zinc and phytate in the diet are the primary factors determining zinc absorption. A mathematical model of zinc absorption as a function of dietary zinc and phytate can be used to predict dietary zinc requirements and, potentially, enhance our understanding of zinc absorption. Our goal was to develop a model of practical and informative value based on fundamental knowledge of the zinc absorption process and then fit the model to selected published data to assess its validity and estimate parameter values. A model of moderate mathematical complexity relating total zinc absorption to total dietary zinc and total dietary phytate was derived and fit to 21 mean data from whole day absorption studies using nonlinear regression analysis. Model validity, goodness of fit, satisfaction of regression assumptions, and quality of the parameter estimates were evaluated using standard statistical criteria. The fit had an R(2) of 0.82. The residuals were found to exhibit a normal distribution, constant variance, and independence. The parameters of the model, A(MAX), K(R), and K(P), were estimated to have values of 0.13, 0.10, and 1.2 mmol/d, respectively. Several of these estimates had wide CI attributable in part to the small number and the scatter of the data. The model was judged to be valid and of immediate value for studying and predicting absorption. A version of the model incorporating a passive absorption mechanism was not supported by the available data.

Humans↗

PubMed1993

Regression dilution in the proportional hazards model.

The problem of regression dilution arising from covariate measurement error is investigated for survival data using the proportional hazards model. The naive approach to parameter estimation is considered whereby observed covariate values are used, inappropriately, in the usual analysis instead of the underlying covariate values. A relationship between the estimated parameter in large samples and the true parameter is obtained showing that the bias does not depend on the form of the baseline hazard function when the errors are normally distributed. With high censorship, adjustment of the naive estimate by the factor 1 + lambda, where lambda is the ratio of within-person variability about an underlying mean level to the variability of these levels in the population sampled, removes the bias. As censorship increases, the adjustment required increases and when there is no censorship is markedly higher than 1 + lambda and depends also on the true risk relationship.

Analysis of Variance↗

PubMed2003

Using the expolinear growth equation for modelling crop growth in year-round cut chrysanthemum.

The aim of this study was to predict crop growth of year-round cut chrysanthemum (Chrysanthemum morifolium Ramat.) based on an empirical model of potential crop growth rate as a function of daily incident photosynthetically active radiation (PAR, MJ m-2 d-1), using generalized estimated parameters of the expolinear growth equation. For development of the model, chrysanthemum crops were grown in four experiments at different plant densities (32, 48, 64 and 80 plants m-2), during different seasons (planting in January, May-June and September) and under different light regimes [natural light, shading to 66 and 43 % of natural light, and supplementary assimilation light (ASS, 40-48 micro mol m-2 s-1)]. The expolinear growth equation as a function of time (EXPOT) or as a function of incident PAR integral (EXPOPAR) effectively described periodically measured total dry mass of shoot (R2 > 0.98). However, growth parameter estimates for the fitted EXPOPAR were more suitable as they were not correlated to each other. Coefficients of EXPOPAR characterized the relative growth rate per incident PAR integral [rm,i (MJ m-2)-1] and light use efficiency (LUE, g MJ-1) at closed canopy. In all four experiments, no interaction effects between treatments on crop growth parameters were found. rm,i and LUE were not different between ASS and natural light treatments, but were increased significantly when light levels were reduced by shading in the summer experiments. There was no consistent effect of plant density on growth parameters. rm,i and LUE showed hyperbolic relationships to average daily incident PAR averaged over 10-d periods after planting (rm,i) or before final harvest (LUE). Based on those relationships, maximum relative growth rate (rm, g g-1 d-1) and maximum crop growth rate (cm, g m-2 d-1) were described successfully by rectangular hyperbolic relationships to daily incident PAR. In model validation, total dry mass of shoot (Wshoot, g m-2) simulated over time was in good agreement with measured ones in three independent experiments, using daily incident PAR and leaf area index as inputs. Based on these results, it is concluded that the expolinear growth equation is a useful tool for quantifying cut chrysanthemum growth parameters and comparing growth parameter values between different treatments, especially when light is the growth-limiting factor. Under controlled environmental conditions the regression model worked satisfactorily, hence the model may be applied as a simple tool for understanding crop growth behaviour under seasonal variation in daily light integral, and for planning cropping systems of year-round cut chrysanthemum. However, further research on leaf area development in cut chrysanthemum is required to advance chrysanthemum crop growth prediction.

Chrysanthemum↗

PubMed1999

Analysis program based on finite element method, MULTI(FEM), for evaluation of dose-dependent local disposition of drug in liver.

A curve-fitting program based on the Finite Element Method, MULTI(FEM), was developed to model nonlinear local disposition of a drug in the liver under non-steady-state conditions. The program was written in FORTRAN on an IBM-compatible personal computer. The validity of MULTI(FEM) was confirmed by analyzing the outflow kinetics of oxacillin (a model drug) following a pulse input to isolated, perfused rat livers, according to both linear and nonlinear dispersion models. Four dose levels (300, 1000, 3000, and 5000 microg) of oxacillin were administered to observe the dose-dependency in the hepatic local disposition. First, the individual outflow time-profiles at the same dose were averaged, and the average time-profile was analyzed by MULTI(FEM) based on linear dispersion models to yield a single curve fit. The fitted parameters at each dose level were compared with parameters estimated using MULTI(FILT), a program based on fast inverse Laplace transform, to analyze linear pharmacokinetics. The estimated parameters by MULTI(FEM) were in good agreement with those by MULTI(FILT). The apparent elimination rate constant (ke) decreased with an increase in dose, whereas other parameters showed no discernible dependency on an increase of dose. Second, the average outflow time-profiles at the four dose levels were simultaneously analyzed by MULTI(FEM) based on dispersion models featuring Michaelis-Menten elimination. The outflow time-profiles of oxacillin were well approximated by a two-compartment dispersion model with central Michaelis-Menten elimination. The maximum elimination rate constant (Vmax) and the Michaelis constant (Km) were estimated to be 1520 microg/mL/min and 41.3 microg/mL, respectively. Thus, the capability of MULTI(FEM) was demonstrated in evaluating capacity-limited local disposition in the liver.

Animals↗

PubMed1999

Monte Carlo EM for missing covariates in parametric regression models.

We propose a method for estimating parameters for general parametric regression models with an arbitrary number of missing covariates. We allow any pattern of missing data and assume that the missing data mechanism is ignorable throughout. When the missing covariates are categorical, a useful technique for obtaining parameter estimates is the EM algorithm by the method of weights proposed in Ibrahim (1990, Journal of the American Statistical Association 85, 765-769). We extend this method to continuous or mixed categorical and continuous covariates, and for arbitrary parametric regression models, by adapting a Monte Carlo version of the EM algorithm as discussed by Wei and Tanner (1990, Journal of the American Statistical Association 85, 699-704). In addition, we discuss the Gibbs sampler for sampling from the conditional distribution of the missing covariates given the observed data and show that the appropriate complete conditionals are log-concave. The log-concavity property of the conditional distributions will facilitate a straightforward implementation of the Gibbs sampler via the adaptive rejection algorithm of Gilks and Wild (1992, Applied Statistics 41, 337-348). We assume the model for the response given the covariates is an arbitrary parametric regression model, such as a generalized linear model, a parametric survival model, or a nonlinear model. We model the marginal distribution of the covariates as a product of one-dimensional conditional distributions. This allows us a great deal of flexibility in modeling the distribution of the covariates and reduces the number of nuisance parameters that are introduced in the E-step. We present examples involving both simulated and real data.

Algorithms↗

PubMed1993

MacELLIPSE, a graphical aid to the problem of the joint confidence region: a practical example for ligand binding experiments.

The analysis of receptor binding experiments involving saturation or displacement curves may represent a problem when data are obtained from a number of experimental groups characterized by different tissues or different treatments. The conceptual difficulty of comparing such binding parameters and the complexity in graphically representing many curves is often overcome using tables and statistical tests for uncorrelated parameters. These, however, might be misleading. In fact, computing parameters using a nonlinear least squares (NLLS) technique may yield a significant covariance or correlation in the parameter estimates. In the present paper we suggest a practical method for comparing curves from different experimental groups using the LIGAND program and present the program MacELLIPSE that permits the graphical representation of the binding results together with the correlation existing between the estimated parameters.

Computer Graphics↗

PubMed2005

Parametric response surface models for analysis of multi-site fMRI data.

Analyses of fMRI brain data are often based on statistical tests applied to each voxel or use summary statistics within a region of interest (such as mean or peak activation). These approaches do not explicitly take into account spatial patterns in the activation signal. In this paper, we develop a response surface model with parameters that directly describe the spatial shapes of activation patterns. We present a stochastic search algorithm for parameter estimation. We apply our method to data from a multi-site fMRI study, and show how the estimated parameters can be used to analyze different sources of variability in image generation, both qualitatively and quantitatively, based on spatial activation patterns.

Algorithms↗

PubMed2006

Population models for threshold-based control of Tetranychus urticae in small-scale Kenyan tomato fields and for evaluating weather and host plant species effects.

The spatial distribution of motile life stages of the two-spotted spider mite Tetranychus urticae Koch in Kenyan small-scale tomato fields was described by Taylor's power law and an enumerative sampling plan was designed for research purposes. The exponential increase of T. urticae populations during three growing seasons permits the development and use of a simple exponential model for the design of a threshold-based chemical control system. For this purpose, a critical threshold of 440 motile mites per sample unit at the end of the growing season (12 weeks after transplanting) was translated into a proportion of 0.83 infested units in sample 3, i.e. five weeks after transplanting. A sequential binomial sampling plan with respect to the proportion of 0.83, five weeks after transplanting, was designed. The exponential model was extended to account for the influence of weather and host plant species. Model development and parameter estimation were based on three data sets (Kenyan tomato fields, Italian and Californian strawberry fields). The model satisfactorily predicted a positive influence on growth rates by (i) changing the host plant from tomato to strawberry, and (ii) temperature, while a negative effect resulted from (iii) rainfall; both (ii) and (iii) are controlled by temperature-rainfall interactions. In contrast, the estimated parameter values did not satisfactorily describe the expected responses at specific temperature and rainfall values. Nevertheless, the model allowed the rating of host plant species in the field. A fourth data set from Swiss apple orchards was used to test the model, and population build-up on the apple host plant appeared to be higher than on tomatoes but lower than on strawberry.

Animals↗

PubMed2004

Quantitative measurement of histamine H(1) receptors in human brains by PET and [11C]doxepin.

The aim of this study is to establish a method for quantitative measurement of histamine H(1) receptor (H1R) in human brain by PET and [(11)C]doxepin ([(11)C]DOX). The estimated parameters with a two-compartment model were stable for the initial values for parameter estimation but those with a three-compartment model were not. This finding suggests that the H1R measured by the [(11)C]DOX and PET can be evaluated with a two-compartment model.

Adult↗

PubMed2004

Efficient and cost-effective experimental determination of kinetic constants and data: the success of a Bayesian systematic approach to drug transport, receptor binding, continuous culture and cell transport kinetics.

Details about the parameters of kinetic systems are crucial for progress in both medical and industrial research, including drug development, clinical diagnosis and biotechnology applications. Such details must be collected by a series of kinetic experiments and investigations. The correct design of the experiment is essential to collecting data suitable for analysis, modelling and deriving the correct information. We have developed a systematic and iterative Bayesian method and sets of rules for the design of enzyme kinetic experiments. Our method selects the optimum design to collect data suitable for accurate modelling and analysis and minimises the error in the parameters estimated. The rules select features of the design such as the substrate range and the number of measurements. We show here that this method can be directly applied to the study of other important kinetic systems, including drug transport, receptor binding, microbial culture and cell transport kinetics. It is possible to reduce the errors in the estimated parameters and, most importantly, increase the efficiency and cost-effectiveness by reducing the necessary amount of experiments and data points measured.

Bayes Theorem↗

PubMed1997

Towards the reduction of dynamic image data in position emission tomography studies.

In this study, we propose a method and investigate the reduction of dynamic image data with positron emission tomography (PET). The method is based upon the use of sampling schedules with a reduced number of scanning intervals and the use of an integral model in the cost function of nonlinear regression. The application of this method is illustrated by the problem of estimating the metabolic rate of glucose with the [18F]2-fluoro-2-deoxyglucose (FDG) model. Computer simulations were performed using various sampling schedules with scanning intervals of different lengths. The results were compared in terms of the accuracy and precision of the estimated parameters. It has been found that the use of sampling schedules with a reduced number of scanning intervals in conjunction with the integral model is very effective. The number of images in dynamic PET FDG studies can be reduced by a factor of 4.5 without losing the accuracy and precision of the parameter estimates.

Computer Simulation↗

PubMed1998

Mapping quantitative trait loci for binary traits using a heterogeneous residual variance model: an application to Marek's disease susceptibility in chickens.

A typical problem in mapping quantitative trait loci (QTLs) comes from missing QTL genotype. A routine method for parameter estimation involving missing data is the mixture model maximum likelihood method. We developed an alternative QTL mapping method that describes a mixture of several distributions by a single model with a heterogeneous residual variance. The two methods produce similar results, but the heterogeneous residual variance method is computationally much faster than the mixture model approach. In addition, the new method can automatically generate sampling variances of the estimated parameters. We derive the new method in the context of QTL mapping for binary traits in a F2 population. Using the heterogeneous residual variance model, we identified a QTL on chromosome IV that controls Marek's disease susceptibility in chickens. The QTL alone explains 7.2% of the total disease variation.

Algorithms↗

PubMed2006

A multivariate model for ordinal trait analysis.

Many economically important characteristics of agricultural crops are measured as ordinal traits. Statistical analysis of the genetic basis of ordinal traits appears to be quite different from regular quantitative traits. The generalized linear model methodology implemented via the Newton-Raphson algorithm offers improved efficiency in the analysis of such data, but does not take full advantage of the extensive theory developed in the linear model arena. Instead, we develop a multivariate model for ordinal trait analysis and implement an EM algorithm for parameter estimation. We also propose a method for calculating the variance-covariance matrix of the estimated parameters. The EM equations turn out to be extremely similar to formulae seen in standard linear model analysis. Computer simulations are performed to validate the EM algorithm. A real data set is analyzed to demonstrate the application of the method. The advantages of the EM algorithm over other methods are addressed. Application of the method to QTL mapping for ordinal traits is demonstrated using a simulated baclcross (BC) population.

Algorithms↗

PubMed2000

Alcohol and coronary heart disease: a meta-analysis.

OBJECTIVE: To estimate parameters of the function relating alcohol consumption with the risk of coronary heart disease and to identify the sources of heterogeneity in the parameter estimates. METHODS: A search of the epidemiological literature from 1966 to 1998 was performed using several bibliographic databases. Meta-regression models were fitted to evaluate non-linear effects of alcohol intake on the relative risk. The effects of some characteristics of the studies, including an index of their quality, were considered as putative sources of heterogeneity of the estimates. Publication bias was also investigated. FINDINGS: Among the 196 initially reviewed articles, 51 were selected. Since qualitative characteristics of the studies were significant sources of heterogeneity, the pooled dose-response functions were based on the 28 cohort studies with higher quality. Risk decreased from 0 to 20 g/day (RR = 0.80; 95% CI: 0.78, 0.83); there was evidence of a protective effect up to 72 g/day (RR = 0.96; 95% CI: 0.92, 1.00) and increased risk above > or = 89 g/day (RR = 1.05; 95% CI: 1.00, 1.11). Lower protective effects and harmful effects were found in women, in men living in countries outside the Mediterranean area and in studies where fatal events were used as the outcome. Evidence of publication bias for moderate intakes and of heterogeneity of the estimates across studies for higher intakes were found. CONCLUSIONS: The degree of protection from moderate doses of alcohol should be reconsidered. Further research investigating the effect of drinking patterns on the risk of coronary heart disease should be performed. Caution in making general recommendations is needed.

Alcohol Drinking↗

PubMedDate not supplied

Simple membrane models for peritoneal dialysis. Evaluation of diffusive and convective solute transport.

Currently used mathematical models to estimate parameters describing diffusive (diffusive mass transport coefficient, KBD) and convective (sieving coefficient, S) solute transport during peritoneal dialysis, as proposed by Pyle, Popovich, and Moncrief (PPM model) and Babb, Randerson, and Farrell (BRF model), require nonlinear regression and advanced numerical methods for parameter estimation. In this study, a simplified approach to the evaluation of KBD and S, using the same transport equation used in the PPM and BRF models but based on two-dimensional linear regression, is proposed. This new approach can be extended to generate a family of membrane models that differ in assumption concerning the average solute concentration (c) inside the peritoneal membrane. In particular, c was assumed to be equal to the arithmetic mean value of the dialysate and blood concentrations (PPM model), the blood concentration (BRF model), or the dialysate concentration (D model). The investigated family of models was used to study the transport of urea, creatinine, glucose, sodium, potassium, and total protein in 20 single, 6 hr dwell studies carried out in 20 nondiabetic patients in stable clinical condition using hypertonic (3.86%) glucose solution. For the PPM model, the linear and nonlinear regressions were able to provide almost identical values of KBD and S. The theoretical dialysate to plasma concentration ratio (D/P) was adequately fitted to experimental D/P for both the PPM and BRF models, but the fit was worse for the D model. However, unphysiologic (i.e., out of the 0-1 range) values of S were found for urea, potassium, and glucose independent of the version of the model used.

Adult↗

PubMed1991

Recursive parameter identification of constrained systems: an application to electrically stimulated muscle.

In the application of real-time identification methods for diagnosis or adaptive control of biomedical systems, there is often known model information that is ignored. Constraints on the allowable values of parameters, which may be based on physical considerations, are often neglected because the information does "fit" easily into commonly used parameter-identification algorithms. In this paper a method of incorporating constraints on model parameters is developed. This method is applicable to most recursive parameter-identification algorithms. It enforces linear equality constraints on identified parameters. The use of this method for the real-time identification of autoregressive moving-average-type time series models, subject to parameter constraints, is described in detail. These constraints may be time varying. At each time step, the parameter estimate obtained by a recursive least squares estimator is orthogonally projected onto the constraint surface. This simple idea, when appropriately executed, enhances the output prediction accuracy of estimated parameters. Using constraint information in this way is important when we do not wish to destroy a "natural" parameterization of the model (by an initial projection to incorporate equality constraints), or when we cannot use a single initial model simplification (because the constraints are time varying or involve inputs and outputs). Because it improves output prediction at future times, this method is advantageous for use in predictive adaptive controllers. The use of this algorithm is demonstrated in the identification of electrically stimulated quadriceps muscles in paraplegic human subjects, using percutaneous intramuscular electrodes. The nonlinear steady-state force versus pulsewidth recruitment characteristic of the electrode-muscle system is identified simultaneously with the input-output muscle response dynamics, using a Hammerstein-type model. Knowledge of the recruitment curve's shape is translated into constraints on the identified parameters. This information improves the experimental predictive quality of the identified model.

Adult↗