scholarly journals Analysis of multivariate longitudinal immuno-epidemiological data using a pairwise joint modelling approach

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Lawrence Lubyayi ◽  
Patrice A. Mawa ◽  
Stephen Cose ◽  
Alison M. Elliott ◽  
Jonathan Levin ◽  
...  
Keyword(s):  
Mixed Models ◽  
Repeated Measures ◽  
Mixed Model ◽  
Epidemiological Data ◽  
Parameter Estimates ◽  
Joint Modelling ◽  
Or Groups ◽  
Longitudinal Profiles ◽  
Infant Immune Response ◽  
Modelling Approach

Abstract Background Immuno-epidemiologists are often faced with multivariate outcomes, measured repeatedly over time. Such data are characterised by complex inter- and intra-outcome relationships which must be accounted for during analysis. Scientific questions of interest might include determining the effect of a treatment on the evolution of all outcomes together, or grouping outcomes that change in the same way. Modelling the different outcomes separately may not be appropriate because it ignores the underlying relationships between outcomes. In such situations, a joint modelling strategy is necessary. This paper describes a pairwise joint modelling approach and discusses its benefits over more simple statistical analysis approaches, with application to data from a study of the response to BCG vaccination in the first year of life, conducted in Entebbe, Uganda. Methods The study aimed to determine the effect of maternal latent Mycobacterium tuberculosis infection (LTBI) on infant immune response (TNF, IFN-γ, IL-13, IL-10, IL-5, IL-17A and IL-2 responses to PPD), following immunisation with BCG. A simple analysis ignoring the correlation structure of multivariate longitudinal data is first shown. Univariate linear mixed models are then used to describe longitudinal profiles of each outcome, and are then combined into a multivariate mixed model, specifying a joint distribution for the random effects to account for correlations between the multiple outcomes. A pairwise joint modelling approach, where all possible pairs of bivariate mixed models are fitted, is then used to obtain parameter estimates. Results Univariate and pairwise longitudinal analysis approaches are consistent in finding that LTBI had no impact on the evolution of cytokine responses to PPD. Estimates from the pairwise joint modelling approach were more precise. Major advantages of the pairwise approach include the opportunity to test for the effect of LTBI on the joint evolution of all, or groups of, outcomes and the ability to estimate association structures of the outcomes. Conclusions The pairwise joint modelling approach reduces the complexity of analysis of high-dimensional multivariate repeated measures, allows for proper accounting for association structures and can improve our understanding and interpretation of longitudinal immuno-epidemiological data.

Linear mixed model better than repeated measures analysis

2019 ◽  
Vol 30 (6) ◽  
pp. NP1-NP2 ◽  
Author(s):  
Işıl Kutluturk Karagoz ◽  
Berhan Keskin ◽  
Flora Özkalaycı ◽  
Ali Karagöz
Keyword(s):  
Mixed Models ◽  
Repeated Measures ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Linear Time ◽  
Case Series ◽  
Model Fit ◽  
Repeated Measures Analysis ◽  
Technical Issues ◽  
Better Than

We have some criticism regarding some technical issues. Mixed models have begun to play a pivotal role in statistical analyses and offer many advantages over more conventional analyses regarding repeated variance analyses. First, they allow to avoid conducting multiple t-tests; second, they can accommodate for within-patient correlation; third, they allow to incorporate not only a random coefficient, but also a random slope, typically ‘linear’ time in longitudinal case series when there are enough data and patients’ trajectories vary a lot and improving model fit.

scholarly journals Application of zero-inflated negative binomial mixed model to human microbiota sequence data

2014 ◽  
Author(s):  
Rui Fang ◽  
Brandie Wagner ◽  
J. Kirk Harris ◽  
Sophie A Fillon
Keyword(s):  
Random Effects ◽  
Repeated Measures ◽  
High Throughput Sequencing ◽  
Mixed Model ◽  
Negative Binomial ◽  
Sequence Data ◽  
Repeated Measurements ◽  
Parameter Estimates ◽  
Human Microbiota ◽  
Negative Binomial Mixed Model

Identification of the majority of organisms present in human-associated microbial communities is feasible with the advent of high throughput sequencing technology. However, these data consist of non-negative, highly skewed sequence counts with a large proportion of zeros. Zero-inflated models are useful for analyzing such data. Moreover, the non-zero observations may be over-dispersed in relation to the Poisson distribution, biasing parameter estimates and underestimating standard errors. In such a circumstance, a zero-inflated negative binomial (ZINB) model better accounts for these characteristics compared to a zero-inflated Poisson (ZIP). In addition, complex study designs are possible with repeated measurements or multiple samples collected from the same subject, thus random effects are introduced to account for the within subject variation. A zero-inflated negative binomial mixed model contains components to model the probability of excess zero values and the negative binomial parameters, allowing for repeated measures using independent random effects between these two components. The objective of this study is to examine the application of a zero-inflated negative binomial mixed model to human microbiota sequence data.

Measuring growth patterns in the field: effects of sampling regime and methods on standardized estimates

2011 ◽  
Vol 89 (6) ◽  
pp. 529-537 ◽  
Author(s):  
J.G.A. Martin ◽  
F. Pelletier
Keyword(s):  
Mixed Models ◽  
Repeated Measures ◽  
Mixed Model ◽  
Linear Models ◽  
Simulated Data ◽  
Growth Patterns ◽  
Repeated Measurements ◽  
Least Squares Regression ◽  
Sampling Regime ◽  
Parturition Date

Although mixed effects models are widely used in ecology and evolution, their application to standardized traits that change within season or across ontogeny remains limited. Mixed models offer a robust way to standardize individual quantitative traits to a common condition such as body mass at a certain point in time (within a year or across ontogeny), or parturition date for a given climatic condition. Currently, however, most researchers use simple linear models to accomplish this task. We use both empirical and simulated data to underline the application of mixed models for standardizing trait values to a common environment for each individual. We show that mixed model standardizations provide more accurate estimates of mass parameters than linear models for all sampling regimes and especially for individuals with few repeated measures. Our simulations and analyses on empirical data both confirm that mixed models provide a better way to standardize trait values for individuals with repeated measurements compared with classical least squares regression. Linear regression should therefore be avoided to adjust or standardize individual measurements

Using empirical Bayes predictors from generalized linear mixed models to test and visualize associations among longitudinal outcomes

2018 ◽  
Vol 28 (5) ◽  
pp. 1399-1411 ◽  
Author(s):  
Susan K Mikulich-Gilbertson ◽  
Brandie D Wagner ◽  
Gary K Grunwald ◽  
Paula D Riggs ◽  
Gary O Zerbe
Keyword(s):  
Random Effects ◽  
Mixed Models ◽  
Empirical Bayes ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Maximum Likelihood Estimates ◽  
Parameter Estimates ◽  
P Values ◽  
Association Analyses ◽  
Second Stage

Medical research is often designed to investigate changes in a collection of response variables that are measured repeatedly on the same subjects. The multivariate generalized linear mixed model (MGLMM) can be used to evaluate random coefficient associations (e.g. simple correlations, partial regression coefficients) among outcomes that may be non-normal and differently distributed by specifying a multivariate normal distribution for their random effects and then evaluating the latent relationship between them. Empirical Bayes predictors are readily available for each subject from any mixed model and are observable and hence, plotable. Here, we evaluate whether second-stage association analyses of empirical Bayes predictors from a MGLMM, provide a good approximation and visual representation of these latent association analyses using medical examples and simulations. Additionally, we compare these results with association analyses of empirical Bayes predictors generated from separate mixed models for each outcome, a procedure that could circumvent computational problems that arise when the dimension of the joint covariance matrix of random effects is large and prohibits estimation of latent associations. As has been shown in other analytic contexts, the p-values for all second-stage coefficients that were determined by naively assuming normality of empirical Bayes predictors provide a good approximation to p-values determined via permutation analysis. Analyzing outcomes that are interrelated with separate models in the first stage and then associating the resulting empirical Bayes predictors in a second stage results in different mean and covariance parameter estimates from the maximum likelihood estimates generated by a MGLMM. The potential for erroneous inference from using results from these separate models increases as the magnitude of the association among the outcomes increases. Thus if computable, scatterplots of the conditionally independent empirical Bayes predictors from a MGLMM are always preferable to scatterplots of empirical Bayes predictors generated by separate models, unless the true association between outcomes is zero.

scholarly journals Improved Decision-Making Confidence Using Item-Based Pharmacometric Model: Illustration with a Phase II Placebo-Controlled Trial

2021 ◽  
Vol 23 (4) ◽  
Author(s):  
Carolina Llanos-Paez ◽  
Claire Ambery ◽  
Shuying Yang ◽  
Maggie Tabberer ◽  
Misba Beerahee ◽  
...  
Keyword(s):  
Sample Size ◽  
Repeated Measures ◽  
Time Course ◽  
Mixed Model ◽  
Drug Effect ◽  
Controlled Trial ◽  
Analysis Data ◽  
Step Function ◽  
Parameter Estimates ◽  
Type I

AbstractThis study aimed to illustrate how a new methodology to assess clinical trial outcome measures using a longitudinal item response theory–based model (IRM) could serve as an alternative to mixed model repeated measures (MMRM). Data from the EXACT (Exacerbation of chronic pulmonary disease tool) which is used to capture frequency, severity, and duration of exacerbations in COPD were analyzed using an IRM. The IRM included a graded response model characterizing item parameters and functions describing symptom-time course. Total scores were simulated (month 12) using uncertainty in parameter estimates. The 50th (2.5th, 97.5th) percentiles of the resulting simulated differences in average total score (drug minus placebo) represented the estimated drug effect (95%CI), which was compared with published MMRM results. Furthermore, differences in sample size, sensitivity, specificity, and type I and II errors between approaches were explored. Patients received either oral danirixin 75 mg twice daily (n = 45) or placebo (n = 48) on top of standard of care over 52 weeks. A step function best described the COPD symptoms-time course in both trial arms. The IRM improved precision of the estimated drug effect compared to MMRM, resulting in a sample size of 2.5 times larger for the MMRM analysis to achieve the IRM precision. The IRM showed a higher probability of a positive predictive value (34%) than MMRM (22%). An item model–based analysis data gave more precise estimates of drug effect than MMRM analysis for the same endpoint in this one case study.

scholarly journals Application of zero-inflated negative binomial mixed model to human microbiota sequence data

2014 ◽  
Author(s):  
Rui Fang ◽  
Brandie Wagner ◽  
J. Kirk Harris ◽  
Sophie A Fillon
Keyword(s):  
Random Effects ◽  
Repeated Measures ◽  
High Throughput Sequencing ◽  
Mixed Model ◽  
Negative Binomial ◽  
Sequence Data ◽  
Repeated Measurements ◽  
Parameter Estimates ◽  
Human Microbiota ◽  
Negative Binomial Mixed Model

Identification of the majority of organisms present in human-associated microbial communities is feasible with the advent of high throughput sequencing technology. However, these data consist of non-negative, highly skewed sequence counts with a large proportion of zeros. Zero-inflated models are useful for analyzing such data. Moreover, the non-zero observations may be over-dispersed in relation to the Poisson distribution, biasing parameter estimates and underestimating standard errors. In such a circumstance, a zero-inflated negative binomial (ZINB) model better accounts for these characteristics compared to a zero-inflated Poisson (ZIP). In addition, complex study designs are possible with repeated measurements or multiple samples collected from the same subject, thus random effects are introduced to account for the within subject variation. A zero-inflated negative binomial mixed model contains components to model the probability of excess zero values and the negative binomial parameters, allowing for repeated measures using independent random effects between these two components. The objective of this study is to examine the application of a zero-inflated negative binomial mixed model to human microbiota sequence data.

Effects of Aging on the Subcortical Encoding of Stop Consonants

2020 ◽  
Vol 29 (3) ◽  
pp. 391-403
Author(s):  
Dania Rishiq ◽  
Ashley Harkrider ◽  
Cary Springer ◽  
Mark Hedrick
Keyword(s):  
Older Adults ◽  
Repeated Measures ◽  
Mixed Model ◽  
Auditory Brainstem ◽  
Auditory Brainstem Responses ◽  
Aging Effects ◽  
Formant Frequency ◽  
Place Of Articulation ◽  
Second Formant ◽  
Effects Of Aging

Purpose The main purpose of this study was to evaluate aging effects on the predominantly subcortical (brainstem) encoding of the second-formant frequency transition, an essential acoustic cue for perceiving place of articulation. Method Synthetic consonant–vowel syllables varying in second-formant onset frequency (i.e., /ba/, /da/, and /ga/ stimuli) were used to elicit speech-evoked auditory brainstem responses (speech-ABRs) in 16 young adults ( M age = 21 years) and 11 older adults ( M age = 59 years). Repeated-measures mixed-model analyses of variance were performed on the latencies and amplitudes of the speech-ABR peaks. Fixed factors were phoneme (repeated measures on three levels: /b/ vs. /d/ vs. /g/) and age (two levels: young vs. older). Results Speech-ABR differences were observed between the two groups (young vs. older adults). Specifically, older listeners showed generalized amplitude reductions for onset and major peaks. Significant Phoneme × Group interactions were not observed. Conclusions Results showed aging effects in speech-ABR amplitudes that may reflect diminished subcortical encoding of consonants in older listeners. These aging effects were not phoneme dependent as observed using the statistical methods of this study.

Power of Modified Brown-Forsythe and Mixed-Model Approaches in Split-Plot Designs

Methodology ◽  
2017 ◽  
Vol 13 (1) ◽  
pp. 9-22 ◽  
Author(s):  
Pablo Livacic-Rojas ◽  
Guillermo Vallejo ◽  
Paula Fernández ◽  
Ellián Tuero-Herrero
Keyword(s):  
Repeated Measures ◽  
Statistical Power ◽  
Mixed Model ◽  
Covariance Structure ◽  
Simulation Method ◽  
Future Research ◽  
Repeated Measures Design ◽  
Fixed And Random Effects ◽  
Split Plot ◽  
High Level

Abstract. Low precision of the inferences of data analyzed with univariate or multivariate models of the Analysis of Variance (ANOVA) in repeated-measures design is associated to the absence of normality distribution of data, nonspherical covariance structures and free variation of the variance and covariance, the lack of knowledge of the error structure underlying the data, and the wrong choice of covariance structure from different selectors. In this study, levels of statistical power presented the Modified Brown Forsythe (MBF) and two procedures with the Mixed-Model Approaches (the Akaike’s Criterion, the Correctly Identified Model [CIM]) are compared. The data were analyzed using Monte Carlo simulation method with the statistical package SAS 9.2, a split-plot design, and considering six manipulated variables. The results show that the procedures exhibit high statistical power levels for within and interactional effects, and moderate and low levels for the between-groups effects under the different conditions analyzed. For the latter, only the Modified Brown Forsythe shows high level of power mainly for groups with 30 cases and Unstructured (UN) and Autoregressive Heterogeneity (ARH) matrices. For this reason, we recommend using this procedure since it exhibits higher levels of power for all effects and does not require a matrix type that underlies the structure of the data. Future research needs to be done in order to compare the power with corrected selectors using single-level and multilevel designs for fixed and random effects.

Long-term seizure outcomes after pediatric temporal lobectomy: does brain MRI lesion matter?

2019 ◽  
Vol 24 (2) ◽  
pp. 200-208
Author(s):  
Ravindra Arya ◽  
Francesco T. Mangano ◽  
Paul S. Horn ◽  
Sabrina K. Kaul ◽  
Serena K. Kaul ◽  
...  
Keyword(s):  
Repeated Measures ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Hippocampal Sclerosis ◽  
Brain Mri ◽  
Temporal Lobectomy ◽  
Seizure Freedom ◽  
Seizure Onset

OBJECTIVEThere is emerging data that adults with temporal lobe epilepsy (TLE) without a discrete lesion on brain MRI have surgical outcomes comparable to those with hippocampal sclerosis (HS). However, pediatric TLE is different from its adult counterpart. In this study, the authors investigated if the presence of a potentially epileptogenic lesion on presurgical brain MRI influences the long-term seizure outcomes after pediatric temporal lobectomy.METHODSChildren who underwent temporal lobectomy between 2007 and 2015 and had at least 1 year of seizure outcomes data were identified. These were classified into lesional and MRI-negative groups based on whether an epilepsy-protocol brain MRI showed a lesion sufficiently specific to guide surgical decisions. These patients were also categorized into pure TLE and temporal plus epilepsies based on the neurophysiological localization of the seizure-onset zone. Seizure outcomes at each follow-up visit were incorporated into a repeated-measures generalized linear mixed model (GLMM) with MRI status as a grouping variable. Clinical variables were incorporated into GLMM as covariates.RESULTSOne hundred nine patients (44 females) were included, aged 5 to 21 years, and were classified as lesional (73%), MRI negative (27%), pure TLE (56%), and temporal plus (44%). After a mean follow-up of 3.2 years (range 1.2–8.8 years), 66% of the patients were seizure free for ≥ 1 year at last follow-up. GLMM analysis revealed that lesional patients were more likely to be seizure free over the long term compared to MRI-negative patients for the overall cohort (OR 2.58, p < 0.0001) and for temporal plus epilepsies (OR 1.85, p = 0.0052). The effect of MRI lesion was not significant for pure TLE (OR 2.64, p = 0.0635). Concordance of ictal electroencephalography (OR 3.46, p < 0.0001), magnetoencephalography (OR 4.26, p < 0.0001), and later age of seizure onset (OR 1.05, p = 0.0091) were associated with a higher likelihood of seizure freedom. The most common histological findings included cortical dysplasia types 1B and 2A, HS (40% with dual pathology), and tuberous sclerosis.CONCLUSIONSA lesion on presurgical brain MRI is an important determinant of long-term seizure freedom after pediatric temporal lobectomy. Pediatric TLE is heterogeneous regarding etiologies and organization of seizure-onset zones with many patients qualifying for temporal plus nosology. The presence of an MRI lesion determined seizure outcomes in patients with temporal plus epilepsies. However, pure TLE had comparable surgical seizure outcomes for lesional and MRI-negative groups.

Sign in / Sign up

Export Citation Format

Share Document