Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “linear mixed model”

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 1,423 records · Page 79Linked to original sources
PubMed2004

Correlates of sleep-wake patterns among children and young adolescents in Taiwan.

STUDY OBJECTIVE: To determine correlates of morning and evening sleep-wake patterns in a community sample of children. DESIGN: A school-based cross-sectional survey. PARTICIPANTS: Sample included 1572 students, grades 4 to 8 (response rate, 98.4%), using a multistage sampling method. INTERVENTIONS: N/A. MEASUREMENTS AND RESULTS: Student participants completed a Sleep Habits Questionnaire, which included sleep schedules, a mood scale, substance use, the morningness/eveningness (M/E) scale, pubertal development scale, sleep disturbance scale, and parental monitoring scale. The morning (n = 367) and evening (n = 364) groups were operationally defined as participants who scored in the top or bottom 25% of the M/E scale, respectively. Linear mixed and tree-based classification models were used to explore correlates of sleep-wake patterns. Our results showed the evening type was associated with older school grade level, increased coffee drinking, moodiness, decreased parental monitoring, daytime sleepiness, and several sleep disturbances, including early insomnia, fear of sleeping in darkness, bedwetting, and going to bed later than 3 am. The 2 most potent discriminators between evening and morning subtypes were higher grade level, an index of age, and moodiness. The association of moodiness with the evening type was greater in boys than girls. CONCLUSIONS: These findings suggest that further research should address explanations for the association between evening type and mood and anxiety symptoms, including order of the effects, developmental factors, environmental determinants of sleep time such as school start time and parental bedtime monitoring, and circadian maturation.

Adolescent↗
PubMed2005

Mixed-effects variance components models for biometric family analyses.

Recent substantive research on biometric analyses of twin and family data has used both a biometric path analysis model (PAM) and a biometric variance components model (VCM). Methodological research on these same topics have suggested benefits of using linear structural equation model algorithms (SEMA) as well as mixed effect multilevel algorithms (MEMA). To better understand the potential similarities and differences among these approaches we first highlight the algebraic equivalence between the standard biometric PAM and the corresponding biometric VCM models for family data. Second, we demonstrate how several SEMA programs based on either the PAM or VCM approach produce equivalent estimates for all phenotypic and biometric parameters. Third, we show how the biometric VCM approach (but not the PAM approach) can be easily programmed using current MEMA programs (e.g., SAS PROC MIXED). We then expand the scope of these different approaches to include measured covariates, observed variable interactions and multiple relatives within each family. MEMA software is compared to SEMA software for programming complex models, including the flexibility of data input, treatment of missing data, inclusion of covariates, and ease of accommodating varying numbers of observations (per family or individual).

Algorithms↗
PubMed2003

Population pharmacokinetics of high dose ibuprofen in cystic fibrosis.

AIMS: To evaluate ibuprofen population pharmacokinetics in a large series of data collected in children with cystic fibrosis (CF) treated with high doses of ibuprofen (59 patients; 2-18 years), and to identify the main causes responsible for the considerable interindividual variability in ibuprofen serum levels. METHODS: Blood samples were collected during routine clinical care; serum ibuprofen concentrations were determined by HPLC. Fitting of the concentration/time data to a one compartment kinetic population model was performed by a non-linear mixed effect regression method. RESULTS: Body weight, dose, and ibuprofen dosage form (lysinate salt or the free acid form), for elimination clearance (CL/F); and body weight, dose, and fasting status for the apparent distribution volume (Vd/F) proved to be the covariates with influence in the model. The four factors identified helped to explain part of the interindividual variability observed, but the remaining unexplained variability made therapeutic drug monitoring absolutely essential.

Administration, Oral↗
PubMed2000

A semiparametric approach to analysing dose-response data.

In the analysis of a quantal dose-response experiment with grouped data, the most commonly used parametric procedure is logistic regression, commonly referred to as 'logit analysis'. The adequacy of the fit by the logistic regression curve is tested using the chi-square lack-of-fit test. If the lack-of-fit test is not significant, then the logistic model is assumed to be adequate and estimation of effective doses and confidence intervals on the effective doses can be made. When the tolerance distribution of the dose-response data is not known and cannot be assumed by the user, one can use non-parametric methods, such as kernel regression or local linear regression, to estimate the dose-response curve, effective doses and confidence intervals. This research proposes another alternative based on semi-parametric regression to analysing quantal dose-response data called model-robust quantal regression (MRQR). MRQR linearly combines the parametric and non-parametric predictions with the use of a mixing parameter. MRQR uses logistic regression as the parametric portion of the model and local linear regression as the non-parametric portion of the model. Our research has shown that the MRQR procedure can improve the fit of the dose-response curve by producing narrower confidence intervals for predictions while providing improved precision of estimates of the effective doses with respect to either logistic or local linear regression results.

Dose-Response Relationship, Drug↗
PubMed1994

A componential model of human interaction with graphs: 1. Linear regression modeling.

Task analyses served as the basis for developing the Mixed Arithmetic-Perceptual (MA-P) model, which proposes (1) that people interacting with common graphs to answer common questions apply a set of component processes--searching for indicators, encoding the value of indicators, performing arithmetic operations on the values, making spatial comparisons among the indicators, and responding; and (2) that the type of graph and user's task determine the combination and order of the components applied (i.e., the processing steps). Two experiments investigated the prediction that response time will be linearly related to the number of processing steps according to the MA-P model. Subjects used line graphs, scatter plots, and stacked bar graphs to answer comparison questions and questions requiring arithmetic calculations. A one-parameter version of the model (with equal weights for all components) and a two-parameter version (with different weights for arithmetic and nonarithmetic processes) accounted for 76%-85% of individual subjects' variance in response time and 61%-68% of the variance taken across all subjects. The discussion addresses possible modifications in the MA-P model, alternative models, and design implications from the MA-P model.

Computer Graphics↗
PubMed1989

Biological equivalent dose prediction in pion irradiation using pion star density and the mixed beam lesion additivity model.

The biological equivalent dose profile of the pion beam was predicted with one parameter (gamma) using physical dose and pion star density. The value of the relative biological effectiveness (RBE) at each depth was given as a linear function of pion star density (PSD): RBE = 1.0 + gamma PSD, assuming (i) the mixed beam lesion additivity model and (ii) the linear relationship between the ratio of high LET dose to total dose and pion star density. The predicted depth-survival curve fitted well with the pooled biological data of the gel technique using Chinese hamster cells (CHO). The predicted RBE were consistent with previously published results through the flat dose peak, except at the decreasing portion of the dose profile. The practical usefulness of this model in clinical treatment is stressed.

Animals↗
PubMed1997

Modeling schizophrenic behavior using general mixture components.

This article proposes a novel and general mixture component model, the features of which include a hierarchical structure with random effects, mixture components characterized by ANOVA-like linear regressions, and mixing mechanisms governed by logistic regressions. The model was developed as a consequence of attending to long-standing psychological theory about schizophrenic behavior. Scientifically revealing results are obtained by fitting the model to a data set concerning nonschizophrenic and schizophrenic eye-tracking behavior under different conditions. Included are descriptions of the algorithms for model fitting, specifically the ECM/SECM algorithms for large sample modal inference, and the Gibbs sampler for simulating the posterior distribution. For guidance on model comparison and selection, we use posterior predictive check distributions to obtain posterior predictive p-values for likelihood ratio statistics, which do not have asymptotic chi 2 reference distributions. These posterior predictive p-values suggest that all the mixture components in our model are necessary. The final model is selected using a combination of scientific parsimony, the posterior predictive p-values, and the posterior distributions of relevant parameters.

Algorithms↗
PubMed1976

Quantitative structure-activity relationships. 2. A mixed approach, based on Hansch and Free-Wilson Analysis.

Based on the theoretical and numerical equivalence of Hansch's linear multiple regression model and the modified Free-Wilson model a mixed approach is developed. The mixed approach is a combination of both models which makes use of the advantages of each model and widens the applicability of Hansch and Free-Wilson analysis. The Free-Wilson approach now is applicable also in the case of parabolic dependence of biological activity on a particular physical property, e.g., log P or pi. A rational explanation is given for the use of dummy variables in Hansch equations and the derivation of Hansch correlations for de novo group contributions obtained from Free-Wilson analysis. Some examples illustrate the mixed approach and demonstrate its usefulness to establish biologically meaningful structure-activity relationships.

Animals↗
PubMed1998

Extending the simple linear regression model to account for correlated responses: an introduction to generalized estimating equations and multi-level mixed modelling.

Much of the research in epidemiology and clinical science is based upon longitudinal designs which involve repeated measurements of a variable of interest in each of a series of individuals. Such designs can be very powerful, both statistically and scientifically, because they enable one to study changes within individual subjects over time or under varied conditions. However, this power arises because the repeated measurements tend to be correlated with one another, and this must be taken into proper account at the time of analysis or misleading conclusions may result. Recent advances in statistical theory and in software development mean that studies based upon such designs can now be analysed more easily, in a valid yet flexible manner, using a variety of approaches which include the use of generalized estimating equations, and mixed models which incorporate random effects. This paper provides a particularly simple illustration of the use of these two approaches, taking as a practical example the analysis of a study which examined the response of portable peak expiratory flow meters to changes in true peak expiratory flow in 12 children with asthma. The paper takes the reader through the relevant practicalities of model fitting, interpretation and criticism and demonstrates that, in a simple case such as this, analyses based upon these model-based approaches produce reassuringly similar inferences to standard analyses based upon more conventional methods.

Adolescent↗
PubMed2003

Normal linear models with genetically structured residual variance heterogeneity: a case study.

Normal mixed models with different levels of heterogeneity in the residual variance are fitted to pig litter size data. Exploratory analysis and model assessment is based on examination of various posterior predictive distributions. Comparisons based on Bayes factors and related criteria favour models with a genetically structured residual variance heterogeneity. There is, moreover, strong evidence of a negative correlation between the additive genetic values affecting litter size and those affecting residual variance. The models are also compared according to the purposes for which they might be used, such as prediction of 'future' data, inference about response to selection and ranking candidates for selection. A brief discussion is given of some implications for selection of the genetically structured residual variance model.

Analysis of Variance↗
PubMed2005

Development and validation of a population pharmacokinetic model for ritonavir used as a booster or as an antiviral agent in HIV-1-infected patients.

AIMS: The aim of this study was to develop and validate a population pharmacokinetic model of ritonavir, used as an antiviral agent or as a booster, in a large patient population and to identify factors influencing its pharmacokinetics. METHODS: Ambulatory HIV-1-infected patients from the outpatient clinic of the Slotervaart Hospital, Amsterdam, the Netherlands, who were being treated with a ritonavir-containing regimen were included. During regular visits, blood samples were collected for the determination of ritonavir plasma concentrations and several clinical chemistry parameters. Furthermore, complete pharmacokinetic curves were available in some patients. Single and multiple compartment models with zero-order and first-order absorption, with and without absorption lag-time, with linear and nonlinear elimination were tested, using nonlinear mixed effect modelling (NONMEM). Pharmacokinetic parameters and interindividual, interoccasion and residual variability were estimated. In addition, the influence of several factors (e.g. patient characteristics, comedication) on the pharmacokinetics of ritonavir was explored. RESULTS: From 186 patients 505 ritonavir plasma concentrations at a single time-point and 55 full pharmacokinetic profiles were available, resulting in a database of 1228 plasma ritonavir concentrations. In total 62% of the patients used ritonavir as a booster of their protease inhibitor containing antiretroviral regimen. First order absorption in combination with one-compartment disposition best described the pharmacokinetics of ritonavir. Clearance, volume of distribution and absorption rate constant were 10.5 l h(-1) (95% prediction interval (95% PI) 9.38-11.7), 96.6 l (95% PI 67.2-121) and 0.871 h(-1) (95% PI 0.429-1.47), respectively, with 38.3%, 80.0% and 169% interindividual variability, respectively. The interoccasion variability in the apparent bioavailability was 59.1%. The concomitant use of lopinavir resulted in a 2.7-fold increase in the clearance of ritonavir (P value < 0.001). No patients characteristics influenced the pharmacokinetics of ritonavir. CONCLUSIONS: The pharmacokinetic parameters of ritonavir were adequately described by our population pharmacokinetic model. Concomitant use of the protease inhibitor lopinavir strongly influenced the pharmacokinetics of ritonavir. The model has been validated and can be used for further investigation of the interaction between ritonavir and other protease inhibitors.

Adult↗
PubMed2001

Stabilized Kuramoto-Sivashinsky system.

A model consisting of a mixed Kuramoto-Sivashinsky-Korteweg-de Vries equation, linearly coupled to an extra linear dissipative equation, is proposed. The model applies to a description of surface waves on multilayered liquid films. The extra equation makes it possible to stabilize the zero solution in the model, thus opening the way to the existence of stable solitary pulses. By means of perturbation theory, treating the dissipation and the instability-generating gain in the model (but not the linear coupling between the two waves) as small perturbations, and making use of the balance equation for the net momentum, we demonstrate that the perturbations may select two steady-state solitons from their continuous family existing in the absence of the dissipation and gain. In this case, the selected pulse with the larger value of the amplitude is expected to be stable, provided that the zero solution is stable. The prediction is completely confirmed by direct simulations. If the integration domain is not very large, some pulses are stable even when the zero background is unstable. An explanation for the latter finding is proposed. Furthermore, stable bound states of two and three pulses are found numerically.

Journal Article↗
PubMed1996

Dust exposure, respiratory symptoms, and longitudinal decline of lung function in young coal miners.

OBJECTIVES: To study the role of dust exposure on incidence of respiratory symptoms and decline of lung function in young coal miners. METHODS: The loss of lung function (forced vital capacity (FVC), forced expiratory volume in one second (FEV1), forced expiratory flow (MEF), carbon monoxide transfer factor (TLCO)) with time and the incidence of respiratory symptoms in 909 Sardinian coal miners (followed up between 1983 and 1993 with seven separate surveys) has been compared with the past and current individual exposures to respirable mixed coal dust. Multiple linear and logistic regression models were used simultaneously controlling for age, smoking, past occupational exposures, and other relevant covariates. RESULTS: According to the relatively low dust exposures experienced during the follow up few abnormal chest x ray films were detected. In the cross sectional analysis of initial data, significant associations between individual cumulative exposure to dust, decrements in FEV1 and MEFs, and increasing prevalence of respiratory symptoms were detected after allowing for the covariates included in the model. The yearly decline of FVC, FEV1, and single breath carbon monoxide transfer factor (TLCO/VA) was still significantly related to the individual exposure to dust experienced during the follow up, even after allowing for age, smoking, initial cumulative exposure to dust, and initial level of each functional variable. In logistic models, dust exposure was a significant predictor of the onset of respiratory symptoms besides age and smoking. CONCLUSIONS: The results show that even moderate exposures to mixed coal dust, as in our study, significantly affect lung function and incidence of symptoms of underground miners. Although the frequency of chest x ray examination might be fixed at every three or four years, yearly measurements of lung function (spirometry, MEFs, and TLCO) are recommended for evaluation of the respiratory risk from the coal mine environment to assess the need for further preventive interventions.

Age Factors↗
PubMed1996

Vibrational Analysis of a Molecular Heme-Copper Assembly with a Nearly Linear Fe(III)-CN-Cu(II) Bridge: Insight into Cyanide Binding to Fully Oxidized Cytochrome c Oxidase.

The complete vibrational analysis of [(1-MeIm)Fe(OEP)-CN-Cu(Me(6)tren)](2+) (1), which has been constructed as a model for the cyanide-ligated binuclear center in the respiratory protein cytochrome c oxidase, has been carried out. The resonance Raman spectra (lambda(exc) = 647 nm) and the mid-infrared spectra display three cyanide isotope-dependent vibrational modes. Two vibrations showed monotonic decreases with increasing mass of the cyanide ligand (2182-2137-2146-2101 cm(-)(1) and 535-526-526-520 cm(-)(1), respectively, for the (12)C(14)N-(13)C(14)N-(12)C(15)N-(13)C(15)N isotopomers), and could thus be assigned to the C&tbd1;N and Fe-CN-Cu stretching vibrations, respectively. The third vibration, detected with resonance Raman, showed a zigzag-type behavior (495-487-493-485 cm(-)(1) with the set of isotopomers above) with the frequency being more sensitive to (13)C labeling of the cyanide ligand than with (15)N labeling. This pattern of isotopic dependence is characteristic of a bending vibration. Additionally, with the same laser excitation frequency, the C&tbd1;N stretching mode was observed, which is the first time that this vibration has been detected in the resonance Raman spectrum of a synthetic heme-cyanide complex. The normal coordinate analysis showed marked differences between bridged and unbridged heme-cyanide complexes. Internal coordinates that are orthogonal in unbridged systems are significantly mixed in the bridged model, despite the overall linearity of the Fe-CN-Cu moiety. These measurements strengthen the proposal that cyanide bridges the two metal atoms in the cyanide-ligated, oxidized binuclear center of cytochrome c oxidase. A quantitative consideration of the vibrational characteristics of cyanide bound to the resting enzyme, in light of our model compound results, strongly suggests that the binuclear center is flexible and can undergo structural rearrangement to accommodate exogenous ligands. This is likely to be of mechanistic importance in both dioxygen reduction and proton translocation.

Journal Article↗
PubMed1995

Prediction of mesiodistal diameter of unerupted lower canines and premolars using 45 degrees cephalometric radiography.

The reliability of using the oblique cephalometric radiograph for early prediction of the mesiodistal widths of unerupted lower canines and premolars was investigated. Mandibular models and oblique cephalometric radiographs were obtained for 40 Brazilian children (20 boys and 20 girls), in the mixed dentition phase. Further models were obtained for the same sample when all permanent teeth had erupted. A Student t test showed statistically significant differences of tooth size between the sexes but not between right and left sides. Measurements of the unerupted canines and premolars taken from the 45 degrees cephalometric radiograph were statistically greater than the actual values, although a high correlation was observed between them. Linear regression equations and correction tables were established to compensate for this magnification. The actual values for these teeth were compared with the corrected predicted values from the 45 degrees radiograph and with the predicted values obtained from the methods of Ballard and Wylie, Carey, Moyers, and Tanaka and Johnston. A high correlation was observed only between the actual values and the corrected predicted values from the radiograph. The results indicate that, correcting the magnification, the 45 degrees cephalometric radiographic may be used in predicting unerupted lower canine and premolar widths in Brazilian children.

Bicuspid↗
PubMed2003

The reliability of virtual organ computer-aided analysis (VOCAL) for the semiquantification of ovarian, endometrial and subendometrial perfusion.

OBJECTIVES: Three-dimensional power Doppler angiography (3D-PDA) has been largely used for the subjective assessment of vascular patterns but semiquantification of the power Doppler signal is now possible. We examined the intraobserver and interobserver reliability of the semiquantification of ovarian, endometrial and subendometrial blood flow using 3D-PDA, virtual organ computer-aided analysis (VOCAL) and shell-imaging. METHODS: 3D-PDA was used to acquire 20 ovarian and 20 endometrial volumes from 40 different patients at various stages of in vitro fertilization treatment. VOCAL was then used to delineate the 3D areas of interest and the 'histogram facility' employed to generate three indices of vascularity: the vascular index, the flow index and the vascularization flow index. Intraobserver and interobserver reliability was assessed by two-way, mixed, intraclass correlation coefficients (ICCs) and general linear modeling was used to examine for differences in the mean values between each observer. RESULTS: The intraobserver reliability for both observers was extremely high and there were no differences in reliability between the observers for measurements of both volume and vascularity within the ovary or endometrium and its shells. With the exception of the outside subendometrial shell volumes, there were no significant differences between the two observers in the mean values obtained for either endometrial or ovarian volume and vascularity measurements. The interobserver reliability of measurements was equally high throughout with all measurements obtaining a mean ICC of above 0.985. CONCLUSIONS: 3D-PDA and shell-imaging offer a reliable, practical and non-invasive method for the assessment of ovarian, endometrial and subendometrial blood flow. Future work should concentrate upon confirming the reliability of data acquisition and the validity of the technique before its predictive value can be truly tested in prospective clinical studies.

Endometrium↗
PubMed1993

Calorimetric studies of fully hydrated phosphatidylcholines with highly asymmetric acyl chains.

We have semi-synthesized 52 molecular species of saturated diacyl mixed-chain phosphatidylcholines. All 52 phosphatidylcholine molecules are highly asymmetrical with delta C/CL values in the range of 0.43-0.63. The aqueous dispersions of these phosphatidylcholines have been studied by the high-resolution differential scanning calorimetric (DSC) technique. Upon heating, the lipid dispersions prepared individually from these 52 phosphatidylcholines all exhibit a sharp, single, endothermic peak at a characteristic temperature or Tm, implying that the self-assembled lipid molecules in excess water undergo the mixed interdigitated gel to the liquid-crystalline phase transition. The Tm values obtained from aqueous lipid dispersions prepared from these mixed-chain phospholipids have been analyzed based on the molecular packing model of the mixed interdigitated bilayer, and a linear relationship between the Tm and (delta C)-1 for various phospholipids at a constant value of delta is observed. Based on these linear relationships, empirical equations are derived to predict the Tm values for highly asymmetrical mixed-chain phosphatidylcholines with delta C/CL values in the range of 0.43-0.63. The predictive power of these empirical equations is shown to be very good, since a comparison between the predicted and the experimental data indicates that the largest relative error in Kelvin is only 0.4%. A table containing 81 predicted Tm values for highly asymmetrical mixed-chain phosphatidylcholines is presented. The definitions of the various structural parameters such as delta C, CL, delta C/CL and delta are given in the text.

Calorimetry, Differential Scanning↗
PubMed1994

Evaluation of serum prostate-specific antigen velocity after radical prostatectomy to distinguish local recurrence from distant metastases.

OBJECTIVE: Serum prostate-specific antigen (PSA) values are most useful for prediction of disease recurrence after surgery. It is unknown whether a detectable PSA level after surgery indicates a local recurrence potentially benefiting from pelvic irradiation or distant metastases requiring hormonal treatment. METHODS: We analyzed postoperative rate of change of serum PSA levels as a predictor of local versus distant disease recurrence after radical prostatectomy. Between 1982 and 1991, 1,058 men underwent radical prostatectomy for localized prostate cancer and follow-up consisted of determining serum PSA levels and digital rectal examinations. Clinical follow-up of 542 men for four or more years and 78 men for eight or more years yielded ten-year actuarial disease recurrence rates of 4 percent for local recurrence, 8 percent for distant metastases, and 23 percent for an isolated elevation of serum PSA level only. Fifty-one patients with isolated elevations of PSA levels only were followed expectantly until they were diagnosed with either local or distant metastases. RESULTS: A linear mixed effects regression analysis was used to model these data. Using these models, the time to a serum PSA level of 0.5 ng/mL, the PSA level one year following surgery, pathologic stage, Gleason sum, and the rate of change of PSA (PSA velocity [PSAV]) were tested as predictors of local versus distant metastases. A combination of PSAV, pathologic stage, and Gleason grade best distinguished local from distant metastases. CONCLUSIONS: These data suggest that PSAV in men with an isolated elevation of PSA levels following radical prostatectomy might aid in clinical decision making.

Actuarial Analysis↗