1
|
Swaminathan SS, Berchuck SI, Jammal AA, Rao JS, Medeiros FA. Rates of Glaucoma Progression Derived from Linear Mixed Models Using Varied Random Effect Distributions. Transl Vis Sci Technol 2022; 11:16. [PMID: 35138343 PMCID: PMC8842468 DOI: 10.1167/tvst.11.2.16] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Purpose To compare the ability of linear mixed models with different random effect distributions to estimate rates of visual field loss in glaucoma patients. Methods Eyes with five or more reliable standard automated perimetry (SAP) tests were identified from the Duke Glaucoma Registry. Mean deviation (MD) values from each visual field and associated timepoints were collected. These data were modeled using ordinary least square (OLS) regression and linear mixed models using the Gaussian, Student's t, or log-gamma (LG) distributions as the prior distribution for random effects. Model fit was compared using the Watanabe–Akaike information criterion (WAIC). Simulated eyes of varying initial disease severity and rates of progression were created to assess the accuracy of each model in predicting the rate of change and likelihood of declaring progression. Results A total of 52,900 visual fields from 6558 eyes of 3981 subjects were included. Mean follow-up period was 8.7 ± 4.0 years, with an average of 8.1 ± 3.7 visual fields per eye. The LG model produced the lowest WAIC, demonstrating optimal model fit. In simulations, the LG model declared progression earlier than OLS (P < 0.001) and had the greatest accuracy in predicted slopes (P < 0.001). The Gaussian model significantly underestimated rates of progression among fast and catastrophic progressors. Conclusions Linear mixed models using the LG distribution outperformed conventional approaches for estimating rates of SAP MD loss in a population with glaucoma. Translational Relevance Use of the LG distribution in models estimating rates of change among glaucoma patients may improve their accuracy in rapidly identifying progressors at high risk for vision loss.
Collapse
Affiliation(s)
- Swarup S Swaminathan
- Vision, Imaging and Performance Laboratory, Department of Ophthalmology, Duke Eye Center, Duke University, Durham, NC, USA.,Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Samuel I Berchuck
- Vision, Imaging and Performance Laboratory, Department of Ophthalmology, Duke Eye Center, Duke University, Durham, NC, USA.,Department of Statistical Science and Duke Forge, Duke University, Durham, NC, USA
| | - Alessandro A Jammal
- Vision, Imaging and Performance Laboratory, Department of Ophthalmology, Duke Eye Center, Duke University, Durham, NC, USA
| | - J Sunil Rao
- Department of Biostatistics, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Felipe A Medeiros
- Vision, Imaging and Performance Laboratory, Department of Ophthalmology, Duke Eye Center, Duke University, Durham, NC, USA
| |
Collapse
|
2
|
Fabio LC, Cysneiros FJA, Paula GA, Carrasco JMF. Hierarchical and multivariate regression models to fit correlated asymmetric positive continuous outcomes. Comput Stat. [DOI: 10.1007/s00180-021-01163-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
3
|
McCulloch CE, Neuhaus JM. Improving Predictions When Interest Focuses on Extreme Random Effects. J Am Stat Assoc 2021. [DOI: 10.1080/01621459.2021.1938583] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Affiliation(s)
- Charles E. McCulloch
- Division of Biostatistics, Department of Epidemiology and Biostatistics, University of California, San Francisco, CA
| | - John M. Neuhaus
- Division of Biostatistics, Department of Epidemiology and Biostatistics, University of California, San Francisco, CA
| |
Collapse
|
4
|
Bullen AL, Katz R, Jotwani V, Garimella PS, Lee AK, Estrella MM, Shlipak MG, Ix JH. Biomarkers of Kidney Tubule Health, CKD Progression, and Acute Kidney Injury in SPRINT (Systolic Blood Pressure Intervention Trial) Participants. Am J Kidney Dis 2021; 78:361-368.e1. [PMID: 33857535 DOI: 10.1053/j.ajkd.2021.01.021] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2020] [Accepted: 01/25/2021] [Indexed: 12/22/2022]
Abstract
RATIONALE & OBJECTIVE The Systolic Blood Pressure Intervention Trial (SPRINT) compared the effect of intensive versus standard systolic blood pressure targets on cardiovascular morbidity and mortality. In this ancillary study, we evaluated the use of exploratory factor analysis (EFA) to combine biomarkers of kidney tubule health in urine and plasma and then study their role in longitudinal estimated glomerular filtration rate (eGFR) change and risk of acute kidney injury (AKI). STUDY DESIGN Observational cohort nested in a clinical trial. SETTING & PARTICIPANTS 2,351 SPRINT participants with eGFR < 60 mL/min/1.73 m2 at baseline. EXPOSURE Levels of neutrophil gelatinase-associated lipocalin (NGAL), interleukin 18 (IL-18), chitinase-3-like protein (YKL-40), kidney injury molecule 1 (KIM-1), monocyte chemoattractant protein 1 (MCP-1), α1-microglobulin (A1M) and β2-microglobulin (B2M), uromodulin (UMOD), fibroblast growth factor 23 (FGF-23), and intact parathyroid hormone (PTH). OUTCOME Longitudinal changes in eGFR and risk of AKI. ANALYTICAL APPROACH We performed EFA to capture different tubule pathophysiologic processes. We used linear mixed effects models to evaluate the association of each factor with longitudinal changes in eGFR. We evaluated the association of the tubular factors scores with AKI using Cox proportional hazards regression. RESULTS From 10 biomarkers, EFA generated 4 factors reflecting tubule injury/repair (NGAL, IL-18, and YKL-40), tubule injury/fibrosis (KIM-1 and MCP-1), tubule reabsorption (A1M and B2M), and tubule reserve/mineral metabolism (UMOD, FGF-23, and PTH). Each 1-SD higher tubule reserve/mineral metabolism factor score was associated with a 0.58% (95% CI, 0.39%-0.67%) faster eGFR decline independent of baseline eGFR and albuminuria. Both the tubule injury/repair and tubule injury/fibrosis factors were independently associated with future risk of AKI (per 1 SD higher, HRs of 1.18 [95% CI, 1.10-1.37] and 1.23 [95% CI, 1.02-1.48], respectively). LIMITATIONS The factors require validation in other settings. CONCLUSIONS EFA allows parsimonious subgrouping of biomarkers into factors that are differentially associated with progressive eGFR decline and AKI. These subgroups may provide insights into the pathological processes driving adverse kidney outcomes.
Collapse
Affiliation(s)
- Alexander L Bullen
- Nephrology Section, Veterans Affairs San Diego Healthcare System, La Jolla, CA
| | - Ronit Katz
- Department of Obstetrics & Gynecology, University of Washington, Seattle, WA
| | - Vasantha Jotwani
- Kidney Health Research Collaborative, Department of Medicine, University of California-San Francisco, San Francisco, CA; Department of Medicine, San Francisco VA Medical Center, San Francisco, CA
| | - Pranav S Garimella
- Division of Nephrology and Hypertension, Department of Medicine, University of California-San Diego, San Diego, CA
| | - Alexandra K Lee
- Kidney Health Research Collaborative, Department of Medicine, University of California-San Francisco, San Francisco, CA
| | - Michelle M Estrella
- Kidney Health Research Collaborative, Department of Medicine, University of California-San Francisco, San Francisco, CA; Department of Medicine, San Francisco VA Medical Center, San Francisco, CA
| | - Michael G Shlipak
- Kidney Health Research Collaborative, Department of Medicine, University of California-San Francisco, San Francisco, CA; Department of Epidemiology and Biostatistics, University of California-San Francisco, San Francisco, CA; Department of Medicine, San Francisco VA Medical Center, San Francisco, CA
| | - Joachim H Ix
- Nephrology Section, Veterans Affairs San Diego Healthcare System, La Jolla, CA; Division of Nephrology and Hypertension, Department of Medicine, University of California-San Diego, San Diego, CA; Division of Preventive Medicine, Department of Family Medicine and Public Health, University of California-San Diego, San Diego, CA.
| |
Collapse
|
5
|
Gueorguieva R, Buta E, Morean M, Krishnan-Sarin S. Two-part models for repeatedly measured ordinal data with "don't know" category. Stat Med 2020; 39:4574-4592. [PMID: 32909252 DOI: 10.1002/sim.8739] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2019] [Revised: 08/03/2020] [Accepted: 08/08/2020] [Indexed: 11/09/2022]
Abstract
Ordinal data (eg, "low," "medium," "high"; graded response on a Likert scale) with an additional "don't know" category are frequently encountered in the medical, social, and behavioral science literature. The handling of a "don't know" option presents unique challenges as it often "destroys" the ordinal nature of the data. Commonly, nominal models are employed which ignore the partial ordering and have a complicated interpretation, especially in situations with repeatedly measured outcomes. We propose two-part models that easily accommodate longitudinal partially ordered (semiordinal) data. The most easily interpretable formulation consists of a random effect logistic submodel for "don't know" vs all the other categories combined, and a random effect ordinal submodel for the ordered categories. Correlated random effects account for statistical dependence within individual. An extension allowing for nonproportionality of odds for the predictor effects in the ordinal submodel is also considered. Maximum likelihood estimation is performed using adaptive Gaussian quadrature in SAS PROC NLMIXED. A simulation study is performed to evaluate the performance of the estimation algorithm in terms of bias and efficiency, and to compare the results of joint and separate models of the two parts, and of proportional and nonproportional model formulations. The methods are motivated and illustrated on a dataset from a study of adolescents' perceptions of nicotine strength of JUUL e-cigarettes. Using the proposed approach we show that adolescents perceive 5% nicotine content as relatively low, a misconception more pronounced among past month nonusers than among past month users of JUUL e-cigarettes.
Collapse
Affiliation(s)
- Ralitza Gueorguieva
- Department of Biostatistics, Yale Center for the Study of Tobacco Products (TCORS), Yale School of Public Health, New Haven, Connecticut, USA.,Department of Psychiatry, Yale Center for the Study of Tobacco Products (TCORS), Yale School of Medicine, New Haven, Connecticut, USA
| | - Eugenia Buta
- Department of Biostatistics, Yale Center for the Study of Tobacco Products (TCORS), Yale School of Public Health, New Haven, Connecticut, USA
| | - Meghan Morean
- Department of Psychiatry, Yale Center for the Study of Tobacco Products (TCORS), Yale School of Medicine, New Haven, Connecticut, USA
| | - Suchitra Krishnan-Sarin
- Department of Psychiatry, Yale Center for the Study of Tobacco Products (TCORS), Yale School of Medicine, New Haven, Connecticut, USA
| |
Collapse
|
6
|
Abstract
Biological systems, at all scales of organisation from nucleic acids to ecosystems, are inherently complex and variable. Biologists therefore use statistical analyses to detect signal among this systemic noise. Statistical models infer trends, find functional relationships and detect differences that exist among groups or are caused by experimental manipulations. They also use statistical relationships to help predict uncertain futures. All branches of the biological sciences now embrace the possibilities of mixed-effects modelling and its flexible toolkit for partitioning noise and signal. The mixed-effects model is not, however, a panacea for poor experimental design, and should be used with caution when inferring or deducing the importance of both fixed and random effects. Here we describe a selection of the perils and pitfalls that are widespread in the biological literature, but can be avoided by careful reflection, modelling and model-checking. We focus on situations where incautious modelling risks exposure to these pitfalls and the drawing of incorrect conclusions. Our stance is that statements of significance, information content or credibility all have their place in biological research, as long as these statements are cautious and well-informed by checks on the validity of assumptions. Our intention is to reveal potential perils and pitfalls in mixed model estimation so that researchers can use these powerful approaches with greater awareness and confidence. Our examples are ecological, but translate easily to all branches of biology.
Collapse
Affiliation(s)
- Matthew J. Silk
- Centre for Ecology and Conservation, University of Exeter, Penryn, Cornwall, UK
- Environment and Sustainability Institute, University of Exeter, Penryn, Cornwall, UK
| | - Xavier A. Harrison
- Centre for Ecology and Conservation, University of Exeter, Penryn, Cornwall, UK
| | - David J. Hodgson
- Centre for Ecology and Conservation, University of Exeter, Penryn, Cornwall, UK
| |
Collapse
|
7
|
Wei Y, Ma Y, Garcia TP, Sinha S. A consistent estimator for logistic mixed effect models. CAN J STAT 2019; 47:140-156. [PMID: 31274953 PMCID: PMC6605760 DOI: 10.1002/cjs.11482] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2018] [Accepted: 08/07/2018] [Indexed: 11/11/2022]
Abstract
We propose a consistent and locally efficient estimator to estimate the model parameters for a logistic mixed effect model with random slopes. Our approach relaxes two typical assumptions: the random effects being normally distributed, and the covariates and random effects being independent of each other. Adhering to these assumptions is particularly difficult in health studies where in many cases we have limited resources to design experiments and gather data in long-term studies, while new findings from other fields might emerge, suggesting the violation of such assumptions. So it is crucial if we could have an estimator robust to such violations and then we could make better use of current data harvested using various valuable resources. Our method generalizes the framework presented in Garcia & Ma (2016) which also deals with a logistic mixed effect model but only considers a random intercept. A simulation study reveals that our proposed estimator remains consistent even when the independence and normality assumptions are violated. This contrasts from the traditional maximum likelihood estimator which is likely to be inconsistent when there is dependence between the covariates and random effects. Application of this work to a Huntington disease study reveals that disease diagnosis can be further improved using assessments of cognitive performance.
Collapse
Affiliation(s)
- Yizheng Wei
- Department of Statistics, University of South Carolina,
Columbia, SC 29208
| | - Yanyuan Ma
- Department of Statistics, The Pennsylvania State
University, University Park, PA 16802
| | - Tanya P. Garcia
- Department of Statistics, Texas A&M University, College
Station, TX 77843
| | - Samiran Sinha
- Department of Statistics, Texas A&M University, College
Station, TX 77843
| |
Collapse
|
8
|
Xing Y, Xu L, Ma W, Zhu Z. Conditional mix-GEE models for longitudinal data with unspecified random-effects distributions. COMMUN STAT-THEOR M 2018. [DOI: 10.1080/03610926.2016.1267763] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- Yanchun Xing
- School of Mathematics and Statistics, Northeast Normal University, Changchun, Jilin, China
- School of Statistics, Jilin University of Finance and Economics, Changchun, Jilin, China
| | - Lili Xu
- School of Education and Science, Northeast Normal University, Changchun, Jilin, China
| | - Wenqing Ma
- School of Mathematics and Statistics, Northeast Normal University, Changchun, Jilin, China
| | - Zhichuan Zhu
- School of Mathematics and Statistics, Northeast Normal University, Changchun, Jilin, China
- School of Statistics, Jilin University of Finance and Economics, Changchun, Jilin, China
| |
Collapse
|
9
|
Ju W, Nair V, Smith S, Zhu L, Shedden K, Song PXK, Mariani LH, Eichinger FH, Berthier CC, Randolph A, Lai JYC, Zhou Y, Hawkins JJ, Bitzer M, Sampson MG, Thier M, Solier C, Duran-Pacheco GC, Duchateau-Nguyen G, Essioux L, Schott B, Formentini I, Magnone MC, Bobadilla M, Cohen CD, Bagnasco SM, Barisoni L, Lv J, Zhang H, Wang HY, Brosius FC, Gadegbeku CA, Kretzler M. Tissue transcriptome-driven identification of epidermal growth factor as a chronic kidney disease biomarker. Sci Transl Med 2016; 7:316ra193. [PMID: 26631632 DOI: 10.1126/scitranslmed.aac7071] [Citation(s) in RCA: 273] [Impact Index Per Article: 34.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Chronic kidney disease (CKD) affects 8 to 16% people worldwide, with an increasing incidence and prevalence of end-stage kidney disease (ESKD). The effective management of CKD is confounded by the inability to identify patients at high risk of progression while in early stages of CKD. To address this challenge, a renal biopsy transcriptome-driven approach was applied to develop noninvasive prognostic biomarkers for CKD progression. Expression of intrarenal transcripts was correlated with the baseline estimated glomerular filtration rate (eGFR) in 261 patients. Proteins encoded by eGFR-associated transcripts were tested in urine for association with renal tissue injury and baseline eGFR. The ability to predict CKD progression, defined as the composite of ESKD or 40% reduction of baseline eGFR, was then determined in three independent CKD cohorts. A panel of intrarenal transcripts, including epidermal growth factor (EGF), a tubule-specific protein critical for cell differentiation and regeneration, predicted eGFR. The amount of EGF protein in urine (uEGF) showed significant correlation (P < 0.001) with intrarenal EGF mRNA, interstitial fibrosis/tubular atrophy, eGFR, and rate of eGFR loss. Prediction of the composite renal end point by age, gender, eGFR, and albuminuria was significantly (P < 0.001) improved by addition of uEGF, with an increase of the C-statistic from 0.75 to 0.87. Outcome predictions were replicated in two independent CKD cohorts. Our approach identified uEGF as an independent risk predictor of CKD progression. Addition of uEGF to standard clinical parameters improved the prediction of disease events in diverse CKD populations with a wide spectrum of causes and stages.
Collapse
Affiliation(s)
- Wenjun Ju
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA.,Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Viji Nair
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Shahaan Smith
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Li Zhu
- Renal Division, Department of Internal Medicine, Peking University First Hospital, Peking University Institute of Nephrology, Beijing 100034, China
| | - Kerby Shedden
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA.,Department of Statistics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Peter X K Song
- Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Laura H Mariani
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA.,Arbor Research Collaborative for Health, Ann Arbor, MI 48104, USA
| | - Felix H Eichinger
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Celine C Berthier
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Ann Randolph
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Jennifer Yi-Chun Lai
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Yan Zhou
- Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Jennifer J Hawkins
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Markus Bitzer
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA
| | - Matthew G Sampson
- Department of Pediatrics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Martina Thier
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Corinne Solier
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Gonzalo C Duran-Pacheco
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | | | - Laurent Essioux
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Brigitte Schott
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Ivan Formentini
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Maria C Magnone
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Maria Bobadilla
- Roche Pharmaceutical Research and Early Development-Roche Innovation Center, 4070 Basel, Switzerland
| | - Clemens D Cohen
- Division of Nephrology, Institute of Physiology, University of Zurich, CH-8006 Zürich, Switzerland
| | - Serena M Bagnasco
- Department of Pathology, Johns Hopkins School of Medicine, Baltimore, MD 21287, USA
| | - Laura Barisoni
- Department of Pathology, Miller School of Medicine, University of Miami, Miami, FL 33136, USA
| | - Jicheng Lv
- Renal Division, Department of Internal Medicine, Peking University First Hospital, Peking University Institute of Nephrology, Beijing 100034, China
| | - Hong Zhang
- Renal Division, Department of Internal Medicine, Peking University First Hospital, Peking University Institute of Nephrology, Beijing 100034, China
| | - Hai-Yan Wang
- Renal Division, Department of Internal Medicine, Peking University First Hospital, Peking University Institute of Nephrology, Beijing 100034, China
| | - Frank C Brosius
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA.,Department of Molecular and Integrative Physiology, University of Michigan, Ann Arbor, MI 48109, USA
| | - Crystal A Gadegbeku
- Temple Clinical Research Institute, Temple University School of Medicine, Philadelphia, PA 19140, USA
| | - Matthias Kretzler
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109, USA.,Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
| | | |
Collapse
|
10
|
Zhu X, Qu A. Individualizing drug dosage with longitudinal data. Stat Med 2016; 35:4474-4488. [DOI: 10.1002/sim.7016] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2016] [Revised: 04/30/2016] [Accepted: 05/16/2016] [Indexed: 11/06/2022]
Affiliation(s)
- Xiaolu Zhu
- Department of StatisticsUniversity of Illinois at Urbana‐Champaign Champaign 61820 IL U.S.A
| | - Annie Qu
- Department of StatisticsUniversity of Illinois at Urbana‐Champaign Champaign 61820 IL U.S.A
| |
Collapse
|
11
|
Zhang P, Luo D, Li P, Sharpsten L, Medeiros FA. Log-gamma linear-mixed effects models for multiple outcomes with application to a longitudinal glaucoma study. Biom J 2015; 57:766-76. [PMID: 26075565 DOI: 10.1002/bimj.201300001] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2013] [Revised: 04/15/2015] [Accepted: 04/16/2015] [Indexed: 11/09/2022]
Abstract
Glaucoma is a progressive disease due to damage in the optic nerve with associated functional losses. Although the relationship between structural and functional progression in glaucoma is well established, there is disagreement on how this association evolves over time. In addressing this issue, we propose a new class of non-Gaussian linear-mixed models to estimate the correlations among subject-specific effects in multivariate longitudinal studies with a skewed distribution of random effects, to be used in a study of glaucoma. This class provides an efficient estimation of subject-specific effects by modeling the skewed random effects through the log-gamma distribution. It also provides more reliable estimates of the correlations between the random effects. To validate the log-gamma assumption against the usual normality assumption of the random effects, we propose a lack-of-fit test using the profile likelihood function of the shape parameter. We apply this method to data from a prospective observation study, the Diagnostic Innovations in Glaucoma Study, to present a statistically significant association between structural and functional change rates that leads to a better understanding of the progression of glaucoma over time.
Collapse
Affiliation(s)
- Peng Zhang
- Department of Mathematics, Zhejiang University, 86 Zheda Road, Hangzhou, Zhejiang, 310012, China
| | - Dandan Luo
- Bank of Montreal, Toronto M5X 1A1, Canada
| | - Pengfei Li
- Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada
| | - Lucie Sharpsten
- Hamilton Glaucoma Center, Department of Ophthalmology, University of California, San Diego, La Jolla, CA, 92093, USA
| | - Felipe A Medeiros
- Hamilton Glaucoma Center, Department of Ophthalmology, University of California, San Diego, La Jolla, CA, 92093, USA
| |
Collapse
|
12
|
Chen YH, Ferguson KK, Meeker JD, McElrath TF, Mukherjee B. Statistical methods for modeling repeated measures of maternal environmental exposure biomarkers during pregnancy in association with preterm birth. Environ Health 2015; 14:9. [PMID: 25619201 PMCID: PMC4417225 DOI: 10.1186/1476-069x-14-9] [Citation(s) in RCA: 70] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2014] [Accepted: 01/16/2015] [Indexed: 05/18/2023]
Abstract
BACKGROUND It is of critical importance to evaluate the role of environmental chemical exposures in premature birth. While a number of studies investigate this relationship, most utilize single exposure measurements during pregnancy in association with the outcome. The studies with repeated measures of exposure during pregnancy employ primarily cross-sectional analyses that may not be fully leveraging the power and additional information that the data provide. METHODS We examine 9 statistical methods that may be utilized to estimate the relationship between a longitudinal exposure and a binary, non-time-varying outcome. To exemplify these methods we utilized data from a nested case-control study examining repeated measures of urinary phthalate metabolites during pregnancy in association with preterm birth. RESULTS The methods summarized may be useful for: 1) Examining sensitive windows of exposure in association with an outcome; 2) Summarizing repeated measures to estimate the relationship between average exposure and an outcome; 3) Identifying acute exposures that may be relevant to the outcome; and 4) Understanding the contribution of temporal patterns in exposure levels to the outcome of interest. In the study of phthalates, changes in urinary metabolites over pregnancy did not appear to contribute significantly to preterm birth, making summary of average exposure across gestation optimal given the current design. CONCLUSIONS The methods exemplified may be of great use in future epidemiologic research projects intended to: 1) Elucidate the complex relationships between environmental chemical exposures and preterm birth; 2) Investigate biological mechanisms in prematurity using repeated measures of maternal factors throughout pregnancy; and 3) More generally, address the relationship between a longitudinal predictor and a binary, non-time-varying outcome.
Collapse
Affiliation(s)
- Yin-Hsiu Chen
- />Department of Biostatistics, University of Michigan School of Public Health, Ann Arbor, MI USA
| | - Kelly K Ferguson
- />Department of Environmental Health Sciences, University of Michigan School of Public Health, Ann Arbor, MI USA
| | - John D Meeker
- />Department of Environmental Health Sciences, University of Michigan School of Public Health, Ann Arbor, MI USA
| | - Thomas F McElrath
- />Division of Maternal-Fetal Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA USA
| | - Bhramar Mukherjee
- />Department of Biostatistics, University of Michigan School of Public Health, Ann Arbor, MI USA
| |
Collapse
|
13
|
Zhang J, Yu B, Zhang L, Roskos L, Richman L, Yang H. Non-Normal Random Effects Models for Immunogenicity Assay Cut Point Determination. J Biopharm Stat 2014; 25:295-306. [DOI: 10.1080/10543406.2014.972515] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
|
14
|
Leffondre K, Boucquemont J, Tripepi G, Stel VS, Heinze G, Dunkler D. Analysis of risk factors associated with renal function trajectory over time: a comparison of different statistical approaches. Nephrol Dial Transplant 2014; 30:1237-43. [PMID: 25326471 DOI: 10.1093/ndt/gfu320] [Citation(s) in RCA: 77] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2014] [Accepted: 08/30/2014] [Indexed: 11/12/2022] Open
Abstract
BACKGROUND The most commonly used methods to investigate risk factors associated with renal function trajectory over time include linear regression on individual glomerular filtration rate (GFR) slopes, linear mixed models and generalized estimating equations (GEEs). The objective of this study was to explain the principles of these three methods and to discuss their advantages and limitations in particular when renal function trajectories are not completely observable due to dropout. METHODS We generated data from a hypothetical cohort of 200 patients with chronic kidney disease at inclusion and seven subsequent annual measurements of GFR. The data were generated such that both baseline level and slope of GFR over time were associated with baseline albuminuria status. In a second version of the dataset, we assumed that patients systematically dropped out after a GFR measurement of <15 mL/min/1.73 m(2). Each dataset was analysed with the three methods. RESULTS The estimated effects of baseline albuminuria status on GFR slope were similar among the three methods when no patient dropped out. When 32.7% dropped out, standard GEE provided biased estimates of the mean GFR slope in normo-, micro- and macroalbuminuric patients. Linear regression on individual slopes and linear mixed models provided slope estimates of the same magnitude, likely because most patients had at least three GFR measurements. However, the linear mixed model was the only method to provide effect estimates on both slope and baseline level of GFR unaffected by dropout. CONCLUSION This study illustrates that the linear mixed model is the preferred method to investigate risk factors associated with renal function trajectories in studies, where patients may dropout during the study period because of initiation of renal replacement therapy.
Collapse
Affiliation(s)
- Karen Leffondre
- University of Bordeaux, ISPED, Centre INSERM U897-Epidemiology-Biostatistics, Bordeaux, France
| | - Julie Boucquemont
- University of Bordeaux, ISPED, Centre INSERM U897-Epidemiology-Biostatistics, Bordeaux, France
| | - Giovanni Tripepi
- CNR-IBIM/IFC, Clinical Epidemiology and Physiopathology of Renal Diseases and Hypertension of Reggio Calabria, Calabria, Italy
| | - Vianda S Stel
- Department of Medical Informatics, Academic Medical Center, ERA-EDTA Registry, Amsterdam, Netherlands
| | - Georg Heinze
- Medical University of Vienna, Center for Medical Statistics, Informatics and Intelligent Systems, Vienna, Austria
| | - Daniela Dunkler
- Medical University of Vienna, Center for Medical Statistics, Informatics and Intelligent Systems, Vienna, Austria
| |
Collapse
|
15
|
Neuhaus JM, McCulloch CE, Boylan R. Estimation of covariate effects in generalized linear mixed models with a misspecified distribution of random intercepts and slopes. Stat Med 2013. [PMID: 23203817 DOI: 10.1002/sim.5682] [Citation(s) in RCA: 40] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Generalized linear mixed models with random intercepts and slopes provide useful analyses of clustered and longitudinal data and typically require the specification of the distribution of the random effects. Previous work for models with only random intercepts has shown that misspecifying the shape of this distribution may bias estimates of the intercept, but typically leads to little bias in estimates of covariate effects. Very few papers have examined the effects of misspecifying the joint distribution of random intercepts and slopes. However, simulation results in a recent paper suggest that misspecifying the shape of the random slope distribution can yield severely biased estimates of all model parameters. Using analytic results, simulation studies and fits to example data, this paper examines the bias in parameter estimates due to misspecification of the shape of the joint distribution of random intercepts and slopes. Consistent with results for models with only random intercepts, and contrary to the claims of severe bias in a recent paper, we show that misspecification of the joint distribution typically yields little bias in estimates of covariate effects and is restricted to covariates associated with the misspecified random effects distributions. We also show that misspecification of the distribution of random effects has little effect on confidence interval performance. Coverage rates based on the model-based standard errors from fitted likelihoods were generally quite close to nominal.
Collapse
Affiliation(s)
- John M Neuhaus
- Department of Epidemiology and Biostatistics, University of California, San Francisco, CA 94143-0560, USA.
| | | | | |
Collapse
|
16
|
|
17
|
|
18
|
Abstract
In longitudinal biomedical studies, there is often interest in the rate functions, which describe the functional rates of change of biomarker profiles. This paper proposes a semiparametric approach to model these functions as the realizations of stochastic processes defined by stochastic differential equations. These processes are dependent on the covariates of interest and vary around a specified parametric function. An efficient Markov chain Monte Carlo algorithm is developed for inference. The proposed method is compared with several existing methods in terms of goodness-of-fit and more importantly the ability to forecast future functional data in a simulation study. The proposed methodology is applied to prostate-specific antigen profiles for illustration. Supplementary materials for this paper are available online.
Collapse
Affiliation(s)
- Bin Zhu
- Department of Statistical Science and Center for Human Genetics, Duke University, Durham, NC 27708, ( )
| | | | | |
Collapse
|
19
|
|
20
|
Abstract
Statistical models that include random effects are commonly used to analyze longitudinal and correlated data, often with the assumption that the random effects follow a Gaussian distribution. Via theoretical and numerical calculations and simulation, we investigate the impact of misspecification of this distribution on both how well the predicted values recover the true underlying distribution and the accuracy of prediction of the realized values of the random effects. We show that, although the predicted values can vary with the assumed distribution, the prediction accuracy, as measured by mean square error, is little affected for mild-to-moderate violations of the assumptions. Thus, standard approaches, readily available in statistical software, will often suffice. The results are illustrated using data from the Heart and Estrogen/Progestin Replacement Study using models to predict future blood pressure values.
Collapse
Affiliation(s)
- Charles E McCulloch
- Division of Biostatistics, Department of Epidemiology and Biostatistics, University of California, San Francisco, San Francisco, California 94107, USA
| | | |
Collapse
|