1
|
Zabriskie BN, Corcoran C, Senchaudhuri P. A permutation-based approach for heterogeneous meta-analyses of rare events. Stat Med 2021; 40:5587-5604. [PMID: 34328659 DOI: 10.1002/sim.9142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2020] [Revised: 05/21/2021] [Accepted: 06/30/2021] [Indexed: 11/08/2022]
Abstract
The increasingly widespread use of meta-analysis has led to growing interest in meta-analytic methods for rare events and sparse data. Conventional approaches tend to perform very poorly in such settings. Recent work in this area has provided options for sparse data, but these are still often hampered when heterogeneity across the available studies differs based on treatment group. We propose a permutation-based approach based on conditional logistic regression that accommodates this common contingency, providing more reliable statistical tests when such patterns of heterogeneity are observed. We find that commonly used methods can yield highly inflated Type I error rates, low confidence interval coverage, and bias when events are rare and non-negligible heterogeneity is present. Our method often produces much lower Type I error rates and higher confidence interval coverage than traditional methods in these circumstances. We illustrate the utility of our method by comparing it to several other methods via a simulation study and analyzing an example data set, which assess the use of antibiotics to prevent acute rheumatic fever.
Collapse
Affiliation(s)
| | - Chris Corcoran
- Department of Data Analytics and Information Systems, Utah State University, Logan, Utah, USA
| | | |
Collapse
|
2
|
Xue X, Kim MY, Wang T, Kuniholm MH, Strickler HD. A statistical method for studying correlated rare events and their risk factors. Stat Methods Med Res 2017; 26:1416-1428. [PMID: 25854937 PMCID: PMC4879603 DOI: 10.1177/0962280215581112] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Longitudinal studies of rare events such as cervical high-grade lesions or colorectal polyps that can recur often involve correlated binary data. Risk factor for these events cannot be reliably examined using conventional statistical methods. For example, logistic regression models that incorporate generalized estimating equations often fail to converge or provide inaccurate results when analyzing data of this type. Although exact methods have been reported, they are complex and computationally difficult. The current paper proposes a mathematically straightforward and easy-to-use two-step approach involving (i) an additive model to measure associations between a rare or uncommon correlated binary event and potential risk factors and (ii) a permutation test to estimate the statistical significance of these associations. Simulation studies showed that the proposed method reliably tests and accurately estimates the associations of exposure with correlated binary rare events. This method was then applied to a longitudinal study of human leukocyte antigen (HLA) genotype and risk of cervical high grade squamous intraepithelial lesions (HSIL) among HIV-infected and HIV-uninfected women. Results showed statistically significant associations of two HLA alleles among HIV-negative but not HIV-positive women, suggesting that immune status may modify the HLA and cervical HSIL association. Overall, the proposed method avoids model nonconvergence problems and provides a computationally simple, accurate, and powerful approach for the analysis of risk factor associations with rare/uncommon correlated binary events.
Collapse
Affiliation(s)
- Xiaonan Xue
- Division of Biostatistics, Department Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Mimi Y Kim
- Division of Biostatistics, Department Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Tao Wang
- Division of Biostatistics, Department Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Mark H Kuniholm
- Division of Biostatistics, Department Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Howard D Strickler
- Division of Biostatistics, Department Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| |
Collapse
|
3
|
Shan G, Ma C. Efficient tests for one sample correlated binary data with applications. STAT METHOD APPL-GER 2013. [DOI: 10.1007/s10260-013-0251-6] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
4
|
López Á, Castejón O, Pérez L, Salazar A, Rodríguez G, Urdaneta J. Alteraciones morfológicas de las vellosidades placentarias asociadas a malformaciones fetales múltiples del sistema esquelético. REVISTA BRASILEIRA DE SAÚDE MATERNO INFANTIL 2013. [DOI: 10.1590/s1519-38292013000300002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
OBJETIVOS: describir y cuantificar alteraciones morfológicas en vellosidades placentarias de embarazadas cuyo feto desarrolló malformaciones esqueléticas múltiples. MÉTODOS: se analizaron cuatro placentas de abortos terapéuticos a las 13, 16, 20 y 38 semanas de gestación. Estas se compararon con placentas normales a la misma edad de gestación de abortos electivos por indicación médico legal. Tinción de hematoxilinaeosina se aplicó a 10 láminas de 5 regiones de cada placenta utilizando un protocolo con 4 variables cuantitativas: madurez, cambios fibrinoides, edema y fibrosis estromal y una variable cualitativa: trombosis. Los resultados cuantitativos se analizaron utilizando el análisis de varianza (ANAVAR) según arreglo completamente aleatorizado y el test de Tukey. Para la variable cualitativa se aplicó la prueba de tendencia para datos correlacionados. Se empleó el software statistix 8.0 y SAS 9.0 para Windows. RESULTADOS: existen diferencias significativas (p<0,05) entre las placentas asociadas a malformaciones múltiples del sistema esquelético y las placentas control en relación a las variables cuantitativas. No se encontraron diferencias significativas (p>0,05) en relación a la variable cualitativa. CONCLUSIONES: la población de vellosidades placentarias asociadas a malformaciones múltiples del sistema esquelético presentó un alto porcentaje de alteraciones indicando que la barrera placentaria está dañada afectando el intercambio de gases, nutrientes y metabolitos durante el desarrollo del feto.
Collapse
Affiliation(s)
| | | | - Luis Pérez
- Universidad de Carabobo Sede Aragua. Venezuela, Brasil
| | | | | | | |
Collapse
|
5
|
Bedrick EJ, Hossain A. Conditional tests for homogeneity of zero-inflated Poisson and Poisson-hurdle distributions. Comput Stat Data Anal 2013. [DOI: 10.1016/j.csda.2012.11.009] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
6
|
Minard CG, Chan W, Wetter DW, Etzel CJ. Trends in smoking cessation: a Markov model approach. J Appl Stat 2012. [DOI: 10.1080/02664763.2011.578619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|
7
|
Troxler S, Lalonde T, Wilson JR. Exact logistic models for nested binary data. Stat Med 2011; 30:866-76. [PMID: 21432880 DOI: 10.1002/sim.4157] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2009] [Accepted: 10/27/2010] [Indexed: 11/06/2022]
Abstract
The use of logistic models for independent binary data has relied first on asymptotic theory and later on exact distributions for small samples. However, the use of logistic models for dependent analysis based on exact analysis is not as common. Moreover, attention is usually given to one-stage clustering. In this paper, we extend the exact techniques to address hypothesis testing (estimation is not addressed) for data with second-stage and probably higher levels of clustering. The methods are demonstrated through a somewhat generic example using C+ + program.
Collapse
Affiliation(s)
- Steven Troxler
- Department of Statistics, University of California, 367 Evans Hall #3860, Berkeley, CA 94720-386, USA
| | | | | |
Collapse
|
8
|
Clayton JA, Vitale S, Kim J, Conry-Cantilena C, Byrne P, Reed GF, Ferris FL, Leitman SF. Prevalence of posterior subcapsular cataracts in volunteer cytapheresis donors. Transfusion 2010; 51:921-8. [PMID: 21091958 DOI: 10.1111/j.1537-2995.2010.02948.x] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
BACKGROUND Granulocyte donors routinely receive dexamethasone orally before donation. Steroids may increase the risk of posterior subcapsular cataract (PSC) formation. STUDY DESIGN AND METHODS We recruited 100 granulocyte donors (four or more granulocyte donations; any number of platelet [PLT] donations) and 100 age- and sex-matched PLT donors (zero to three granulocyte donations, any number of PLT donations) to examine the risk of PSC. PSC was assessed by a masked ophthalmologist and reading center lens photograph gradings or medical record documentation of PSC as the reason for cataract extraction. RESULTS Fourteen eyes of 10 granulocyte donors and five eyes of four PLT donors had PSCs (odds ratio [OR], 2.82; 95% confidence interval [CI], 0.83-9.61; p = 0.10). Risk of PSC increased with number of granulocyte donations: compared to zero to three donations (4.0%), the risk for four to nine, 10 to 19, and 20 or more donations was 8.6% (OR, 2.25; 95% CI, 0.31-13.99; p = 0.30), 9.5% (OR, 2.53; 95% CI, 0.44-14.20; p = 0.21), and 13.0% (OR, 3.60; 95% CI, 0.48-22.81; p = 0.11), respectively (p = 0.06 for trend). CONCLUSION We did not demonstrate a statistically significant increased risk of PSC associated with granulocyte donation. However, although this makes a large risk unlikely, we cannot rule out a small to moderate risk and there is biologic plausibility that the steroid administration associated with granulocyte donation could be associated with PSC formation. Transfusion medicine professionals should advise granulocyte apheresis donors to maintain an appropriate frequency of eye examinations.
Collapse
Affiliation(s)
- Janine A Clayton
- Division of Epidemiology and Clinical Research, National Eye Institute, National Institutes of Health, Bethesda, Maryland 20892-1863, USA
| | | | | | | | | | | | | | | |
Collapse
|
9
|
Green DM, Lange JM, Peabody EM, Grigorieva NN, Peterson SM, Kalapurakal JA, Breslow NE. Pregnancy outcome after treatment for Wilms tumor: a report from the national Wilms tumor long-term follow-up study. J Clin Oncol 2010; 28:2824-30. [PMID: 20458053 PMCID: PMC2903317 DOI: 10.1200/jco.2009.27.2922] [Citation(s) in RCA: 84] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2009] [Accepted: 03/02/2010] [Indexed: 11/20/2022] Open
Abstract
PURPOSE This study was undertaken to evaluate the effect of prior treatment with radiation therapy or chemotherapy for unilateral Wilms tumor (WT) diagnosed during childhood on pregnancy complications, birth weight, and the frequency of congenital malformations in live-born offspring. PATIENTS AND METHODS We reviewed pregnancy outcomes among female survivors and partners of male survivors of WT treated on National Wilms Tumor Studies 1, 2, 3, and 4 by using a maternal questionnaire and a review of both maternal and offspring medical records. RESULTS We received reports of 1,021 pregnancies with duration of 20 weeks or longer, including 955 live-born singletons, for whom 700 sets of maternal and offspring medical records were reviewed. Rates of hypertension complicating pregnancy (International Classification of Diseases [ICD] code 642), early or threatened labor (ICD-644) and malposition of the fetus (ICD-652) increased with increasing radiation dose in female patients. The percentages of offspring weighing less than 2,500 g at birth and of those having less than 37 weeks of gestation also increased with dose. There was no significant trend with radiation dose in the number of congenital anomalies recorded in offspring of female patients. CONCLUSION Women who receive flank radiation therapy as part of the treatment for unilateral WT are at increased risk of hypertension complicating pregnancy, fetal malposition, and premature labor. The offspring of these women are at risk for low birth weight and premature (ie, < 37 weeks gestation) birth. These risks must be considered in the obstetrical management of female survivors of WT.
Collapse
Affiliation(s)
- Daniel M Green
- Department of Epidemiology and Cancer Control, St Jude Children's Research Hospital, 262 Danny Thomas Way, Mail Stop 735, Memphis, TN 38105-2794, USA.
| | | | | | | | | | | | | |
Collapse
|
10
|
Szabo A, George EO. On the use of stochastic ordering to test for trend with clustered binary data. Biometrika 2010. [DOI: 10.1093/biomet/asp077] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
|
11
|
Scharfstein DO, Ryea JL, Caffo B. Accounting for within-patient correlation in assessing relative sensitivity of an adjunctive diagnostic test: application to lung cancer. Stat Med 2008; 27:2110-26. [PMID: 17943997 DOI: 10.1002/sim.3085] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
We address the comparison of results between two diagnostic tests applied multiple times to the same subjects. The estimand of interest is the sensitivity of the combined test (primary and adjunct) relative to a primary test. Analytical methods are first described that assume independence between the multiple observations within a subject. In order to account for the within-subject correlation introduced by the multiple measurements, analytical approaches for correlated, categorical response data are described. In the discussion of these methods, we pay particular attention to the presence of a structural zero which results from the decision rule for the combination of diagnostic tests. In a simulation study, we compare the finite sample performances of all analytical approaches in terms of confidence interval coverage rates and median lengths. Our methods are cast in the context of a diagnostic bronchoscopy technology for the detection of lung cancer.
Collapse
Affiliation(s)
- Daniel O Scharfstein
- Department of Biostatistics, The Johns Hopkins Bloomberg School of Public Health, 615 N. Wolfe Street, Baltimore, MD 21205-2179, U.S.A.
| | | | | |
Collapse
|
12
|
Gauci C, Vural G, Oncel T, Varcasia A, Damian V, Kyngdon CT, Craig PS, Anderson GA, Lightowlers MW. Vaccination with recombinant oncosphere antigens reduces the susceptibility of sheep to infection with Taenia multiceps. Int J Parasitol 2007; 38:1041-50. [PMID: 18160069 PMCID: PMC2706984 DOI: 10.1016/j.ijpara.2007.11.006] [Citation(s) in RCA: 50] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2007] [Revised: 11/09/2007] [Accepted: 11/13/2007] [Indexed: 11/28/2022]
Abstract
Taenia multiceps is a cestode parasite, the larval stage of which encysts in the brain of sheep, goats and cattle causing an often fatal condition. The parasite also causes zoonotic infections in humans. Homologues of the recombinant oncosphere vaccine antigens from Taenia ovis and other Taenia species were identified in T. multiceps. Sequencing of the associated T. multiceps genes and cloning of the encoding mRNA has revealed conserved features in the genes and proteins. The T. multiceps oncosphere proteins, designated Tm16 and Tm18, contain a predicted secretory signal and fibronectin type III domain. The recombinant Tm16 and Tm18 proteins were successfully expressed in Escherichia coli as fusion proteins with GST. The antigens, formulated with Quil A adjuvant, were tested in a vaccine trial in sheep. The antigens stimulated immunity in sheep against challenge infection with T. multiceps eggs. Five of nine control sheep died due to a challenge infection with T. multiceps whereas none of 20 vaccinated animals died as a result of the parasite challenge (P = 0.001). In addition, vaccination with the Tm16 protein, or Tm16 plus Tm18, induced significant protection against the number of parasites encysting in the brain as a result of the challenge infection (P = 0.023, P = 0.015, respectively). No clear relationship was apparent between the level of specific serum antibody in vaccinated animals and either the presence or absence of parasites or the number of parasites that occurred in some of the vaccinated animals. We believe this study is the first description of recombinant vaccine-related investigations for T. multiceps. The recombinant oncosphere antigens identified may allow development of effective vaccination strategies against T. multiceps infection in sheep. They raise the potential for the development of a combined vaccine with the Echinococcus granulosus EG95 antigen for prevention of T. multiceps as well as preventing the transmission of cystic hydatid disease.
Collapse
Affiliation(s)
- Charles Gauci
- The University of Melbourne, Department of Veterinary Science, Werribee, Vic. 3030, Australia.
| | | | | | | | | | | | | | | | | |
Collapse
|
13
|
Lee JH, Eschrich S, Beam C. An Exact Test for Detecting Inconsistency in Readers Interpretation Over Time in Screening Mammograms. Biom J 2007; 49:672-81. [PMID: 17638286 DOI: 10.1002/bimj.200610314] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Radiologists' interpretation on screening mammograms is measured by accuracy indices such as sensitivity and specificity. The hypothesis that radiologists' interpretation on screening mammograms is constant across time can be tested by measuring overdispersion. However, small sample sizes are problematic for the accuracy of asymptotic approaches. In this article, we propose an exact conditional distribution for testing overdispersion of the binomial assumption that is assumed for the accuracy indices. An exact p -value can be defined from the developed distribution. We also describe an algorithm for computing this exact test. This proposed method is applied to data from a study in reading screening mammograms in a population of US radiologists (Beam et al., 2003). The exact method is compared analytically with a currently available method based on large sample approximations.
Collapse
Affiliation(s)
- Ji-Hyun Lee
- H. Lee Moffitt Cancer Center Research Institute, University of South Florida, Tampa, FL 33612, USA.
| | | | | |
Collapse
|
14
|
Abstract
In this paper we developed exact tests for one sample correlated binary data whose cluster sizes are at most two. Although significant progress has been made in the development and implementation of the exact tests for uncorrelated data, exact tests for correlated data are rare. Lack of a tractable likelihood function has made it difficult to develop exact tests for correlated binary data. However, when cluster sizes of binary data are at most two, only three parameters are needed to characterize the problem. One parameter is fixed under the null hypothesis, while the other two parameters can be removed by both conditional and unconditional approaches, respectively, to construct exact tests. We compared the exact and asymptotic p-values in several cases. The proposed method is applied to real-life data.
Collapse
Affiliation(s)
- Seung-Ho Kang
- Department of Statistics, Ewha Womans University, 11-1, DaeHyun-Dong, SeoDaeMun-Gu, Seoul, Korea, 120-750.
| | | | | |
Collapse
|
15
|
Han KE, Catalano PJ, Senchaudhuri P, Mehta C. Exact Analysis of Dose Response for Multiple Correlated Binary Outcomes. Biometrics 2004; 60:216-24. [PMID: 15032792 DOI: 10.1111/j.0006-341x.2004.00152.x] [Citation(s) in RCA: 15] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
The neurotoxicity of a substance is often tested using animal bioassays. In the functional observational battery, animals are exposed to a test agent and multiple outcomes are recorded to assess toxicity, using approximately 40 animals measured on up to 30 different items. This design gives rise to a challenging statistical problem: a large number of outcomes for a small sample of subjects. We propose an exact test for multiple binary outcomes, under the assumption that the correlation among these items is equal. This test is based upon an exponential model described by Molenberghs and Ryan (1999, Environmetrics 10, 279-300) and extends the methods developed by Corcoran et al. (2001, Biometrics 57, 941-948) who developed an exact test for exchangeably correlated binary data for groups (clusters) of correlated observations. We present a method that computes an exact p-value testing for a joint dose-response relationship. An estimate of the parameter for dose response is also determined along with its 95% confidence bound. The method is illustrated using data from a neurotoxicity bioassay for the chemical perchlorethylene.
Collapse
Affiliation(s)
- Karen E Han
- Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts 02115, USA.
| | | | | | | |
Collapse
|
16
|
Murray DM, Varnell SP, Blitstein JL. Design and analysis of group-randomized trials: a review of recent methodological developments. Am J Public Health 2004; 94:423-32. [PMID: 14998806 PMCID: PMC1448268 DOI: 10.2105/ajph.94.3.423] [Citation(s) in RCA: 429] [Impact Index Per Article: 21.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/12/2003] [Indexed: 11/04/2022]
Abstract
We review recent developments in the design and analysis of group-randomized trials (GRTs). Regarding design, we summarize developments in estimates of intraclass correlation, power analysis, matched designs, designs involving one group per condition, and designs in which individuals are randomized to receive treatments in groups. Regarding analysis, we summarize developments in marginal and conditional models, the sandwich estimator, model-based estimators, binary data, survival analysis, randomization tests, survey methods, latent variable methods and nonlinear mixed models, time series methods, global tests for multiple endpoints, mediation effects, missing data, trial reporting, and software. We encourage investigators who conduct GRTs to become familiar with these developments and to collaborate with methodologists who can strengthen the design and analysis of their trials.
Collapse
Affiliation(s)
- David M Murray
- Department of Psychology, College of Arts and Sciences, University of Memphis, Memphis, TN, USA.
| | | | | |
Collapse
|