Pub Date : 2019-10-10DOI: 10.6000/1929-6029.2019.08.07
R. Vecchis, A. Paccone, M. Maio
{"title":"Troubles of Atrial Mechanical Recovery after Electrical Cardioversion in Patients with Persistent or Long-Lasting Persistent Atrial Fibrillation","authors":"R. Vecchis, A. Paccone, M. Maio","doi":"10.6000/1929-6029.2019.08.07","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.07","url":null,"abstract":"","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41518698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-26DOI: 10.6000/1929-6029.2019.08.06
A. Tarsitano, I. L. Amerise
: Migraineur constitutes a multidimensional model of health disorder involving a complex combination of genetic, psychological, demographic, enviromental and economic factors. This model provides a framework to describe limitations of an individual functional ability and quality of life, and to aid in the elaboration of more adequate intervention programs for each patient. Our primary objective in this paper is a data-driven profiling of patients. The approach followed consists of examining affinity/dissimilarity between sufferers on the basis of different family of indicators and then aggregating multiple partial matrices, where each matrix expresses a particular notion of the dissimilarity of one patient from another. One important particularity of our method is the notion of multi-dimensional dissimilarity for static and dynamic indicators, without ignoring any portion of data. The partial dissimilarity matrices are assembled in the form of a global matrix, which is used as input of subsequent calculations, such as multidimensional scaling and cluster analysis. Our main contribution is to show how multi-scale, cross-section and longitudinal data from individuals involved in a migraine treatment program may optimally be combined to allow profiling migraine-affected patients.
{"title":"Multivariate Analysis of Data on Migraine Treatment","authors":"A. Tarsitano, I. L. Amerise","doi":"10.6000/1929-6029.2019.08.06","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.06","url":null,"abstract":": Migraineur constitutes a multidimensional model of health disorder involving a complex combination of genetic, psychological, demographic, enviromental and economic factors. This model provides a framework to describe limitations of an individual functional ability and quality of life, and to aid in the elaboration of more adequate intervention programs for each patient. Our primary objective in this paper is a data-driven profiling of patients. The approach followed consists of examining affinity/dissimilarity between sufferers on the basis of different family of indicators and then aggregating multiple partial matrices, where each matrix expresses a particular notion of the dissimilarity of one patient from another. One important particularity of our method is the notion of multi-dimensional dissimilarity for static and dynamic indicators, without ignoring any portion of data. The partial dissimilarity matrices are assembled in the form of a global matrix, which is used as input of subsequent calculations, such as multidimensional scaling and cluster analysis. Our main contribution is to show how multi-scale, cross-section and longitudinal data from individuals involved in a migraine treatment program may optimally be combined to allow profiling migraine-affected patients.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71263684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-08DOI: 10.6000/1929-6029.2019.08.05
C. Odhiambo, Freda Kinoti
{"title":"Evaluation and Comparison of Patterns of Maternal Complications Using Generalized Linear Models of Count Data Time Series","authors":"C. Odhiambo, Freda Kinoti","doi":"10.6000/1929-6029.2019.08.05","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.05","url":null,"abstract":"","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45983043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-08DOI: 10.6000/1929-6029.2019.08.04
Kazeem Adedayo Adeleke, A. A. Abiodun
: Often in epidemiological research, introducing a stratified Cox model can account for the existence of interactions of some inherent factors with some major/noticeable factors. This paper aims at modelling correlated variables in infant mortality with the existence of some inherent factors affecting the infant survival function. A Stratified Cox model is proposed with a view to taking care of multi-factor-level that has interactions with others. This, however, is used as a tool to model infant mortality data from Nigeria Demographic and Health Survey (NDHS) with g-level-factor (Tetanus, Polio and Breastfeeding) having correlations with main factors (Sex, infant Size and Mode of Delivery). Asymptotic properties of partial likelihood estimators of regression parameters are also studied via simulation. The proposed models are tested via data and it shows good fit and performs differently depending on the levels of the interaction of the strata variable Z*. An evidence that the baseline hazard functions and regression coefficients are not the same from stratum to stratum provides a gain in information as against the usage of the Cox model. Simulation result shows that the present method produces better estimates in terms of bias, lower standard errors, and or mean square errors.
{"title":"An Alternative Stratified Cox Model for Correlated Variables in Infant Mortality","authors":"Kazeem Adedayo Adeleke, A. A. Abiodun","doi":"10.6000/1929-6029.2019.08.04","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.04","url":null,"abstract":": Often in epidemiological research, introducing a stratified Cox model can account for the existence of interactions of some inherent factors with some major/noticeable factors. This paper aims at modelling correlated variables in infant mortality with the existence of some inherent factors affecting the infant survival function. A Stratified Cox model is proposed with a view to taking care of multi-factor-level that has interactions with others. This, however, is used as a tool to model infant mortality data from Nigeria Demographic and Health Survey (NDHS) with g-level-factor (Tetanus, Polio and Breastfeeding) having correlations with main factors (Sex, infant Size and Mode of Delivery). Asymptotic properties of partial likelihood estimators of regression parameters are also studied via simulation. The proposed models are tested via data and it shows good fit and performs differently depending on the levels of the interaction of the strata variable Z*. An evidence that the baseline hazard functions and regression coefficients are not the same from stratum to stratum provides a gain in information as against the usage of the Cox model. Simulation result shows that the present method produces better estimates in terms of bias, lower standard errors, and or mean square errors.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41750321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-05-11DOI: 10.6000/1929-6029.2019.08.03
J. Hart, Greenville South Carolina Hart Chiropractic
Introduction: Statistical analysis is typically applied at the group level. The present study analyzes data during a single office visit as a novel approach providing real-time feedback to the clinician and patient regarding efficacy of an intervention. In this study, heart rate variability (HRV) was analyzed before versus after a chiropractic spinal adjustment. Methods: The patient is an adult female who signed a consent form for the study. HRV was measured twice before a chiropractic adjustment and once afterwards using app-based technology. The three HRV values (two pre and one post) were then statistically analyzed using an online calculator for outliers using Grubbs test. Results: The two pre-adjustment HRV (rMSSD) readings were consistently low: pre 1 = 16.0 milliseconds [ms] and pre 2 = 16.2 ms. The low HRV was an indicator that the patient’s nervous system was not functioning optimally. The patient’s atlas (C1) vertebra was palpated to be slightly out of alignment. These two findings (low HRV and vertebral misalignment) indicated the presence of a chiropractic subluxation (of the atlas vertebra). The subluxation was adjusted and within minutes the HRV increased (improved) to 27.5 ms. This improvement was calculated to be a statistically significant outlier (p < 0.05). Conclusion: This study is an example of how statistical methods can be applied to the level of an individual patient during one office visit to assess neurological effectiveness of a chiropractic adjustment. Since this is a case study, the results may not apply to all patients. Therefore, further studies in other patients, and for longer follow-up times, are reasonable next steps.
{"title":"Improvement in Heart Rate Variability Following Spinal Adjustment: A Case Study in Statistical Methodology for a Single Office Visit","authors":"J. Hart, Greenville South Carolina Hart Chiropractic","doi":"10.6000/1929-6029.2019.08.03","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.03","url":null,"abstract":"Introduction: Statistical analysis is typically applied at the group level. The present study analyzes data during a single office visit as a novel approach providing real-time feedback to the clinician and patient regarding efficacy of an intervention. In this study, heart rate variability (HRV) was analyzed before versus after a chiropractic spinal adjustment. Methods: The patient is an adult female who signed a consent form for the study. HRV was measured twice before a chiropractic adjustment and once afterwards using app-based technology. The three HRV values (two pre and one post) were then statistically analyzed using an online calculator for outliers using Grubbs test. Results: The two pre-adjustment HRV (rMSSD) readings were consistently low: pre 1 = 16.0 milliseconds [ms] and pre 2 = 16.2 ms. The low HRV was an indicator that the patient’s nervous system was not functioning optimally. The patient’s atlas (C1) vertebra was palpated to be slightly out of alignment. These two findings (low HRV and vertebral misalignment) indicated the presence of a chiropractic subluxation (of the atlas vertebra). The subluxation was adjusted and within minutes the HRV increased (improved) to 27.5 ms. This improvement was calculated to be a statistically significant outlier (p < 0.05). Conclusion: This study is an example of how statistical methods can be applied to the level of an individual patient during one office visit to assess neurological effectiveness of a chiropractic adjustment. Since this is a case study, the results may not apply to all patients. Therefore, further studies in other patients, and for longer follow-up times, are reasonable next steps.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43694753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-04DOI: 10.6000/1929-6029.2019.08.02
M. Monticone, L. Frigau, C. Sconza, C. Foti, F. Mola, S. Respizzi
Background : Growing attention is being given to standardized outcome measures to improve interventions for total hip arthroplasty (THA) and total knee arthroplasty (TKA). We culturally adapt and validate the Italian version of the Risk Assessment and Prediction Tool (RAPT-I) to allow its predictive use after THA and TKA. Methods : The RAPT-I was adapted by forward–backward translation, a final review by an expert committee and a test of the pre-final version to establish its correspondence with the original version. The psychometric testing included test–retest reliability (intraclass correlation coefficient, ICC). The RAPT score was used to predict the subjects’ destination ( 9: discharge directly at home) by comparing the actual discharge destination with the predicted destination. The predictive effects of RAPT items on the discharge destination were further described by a logistic regression model (repeated leave-one-out bootstrap procedure). Results : The questionnaire was administered to 78 subjects with THA and 70 subjects with TKA and proven to be acceptable. The questionnaire showed excellent test–retest reliability (ICC = 0.839; with 95% confidence interval (CI) of 0.725–0.934 for THA; ICC = 0.973, with 95% CI of 0.930–0.997 for TKA). The RAPT-I overall predictive validity was 87.2%, and the discharge destination was directly related to living condition (odds ratio (OR) = 2.530), mobility (OR = 2.626) and age (OR = 1.332) and inversely related to gait aids (OR = 0.623) and gender (OR = 0.474). Conclusions : The RAPT-I was successfully adapted into Italian and proven to exhibit satisfactory properties, including predictive validity in determining discharge destination.
{"title":"Italian Version of the Risk Assessment and Prediction Tool: Properties and Usefulness of a Decision-Making Tool for Subjects’ Discharge after Total Hip and Knee Arthroplasty","authors":"M. Monticone, L. Frigau, C. Sconza, C. Foti, F. Mola, S. Respizzi","doi":"10.6000/1929-6029.2019.08.02","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.02","url":null,"abstract":"Background : Growing attention is being given to standardized outcome measures to improve interventions for total hip arthroplasty (THA) and total knee arthroplasty (TKA). We culturally adapt and validate the Italian version of the Risk Assessment and Prediction Tool (RAPT-I) to allow its predictive use after THA and TKA. Methods : The RAPT-I was adapted by forward–backward translation, a final review by an expert committee and a test of the pre-final version to establish its correspondence with the original version. The psychometric testing included test–retest reliability (intraclass correlation coefficient, ICC). The RAPT score was used to predict the subjects’ destination ( 9: discharge directly at home) by comparing the actual discharge destination with the predicted destination. The predictive effects of RAPT items on the discharge destination were further described by a logistic regression model (repeated leave-one-out bootstrap procedure). Results : The questionnaire was administered to 78 subjects with THA and 70 subjects with TKA and proven to be acceptable. The questionnaire showed excellent test–retest reliability (ICC = 0.839; with 95% confidence interval (CI) of 0.725–0.934 for THA; ICC = 0.973, with 95% CI of 0.930–0.997 for TKA). The RAPT-I overall predictive validity was 87.2%, and the discharge destination was directly related to living condition (odds ratio (OR) = 2.530), mobility (OR = 2.626) and age (OR = 1.332) and inversely related to gait aids (OR = 0.623) and gender (OR = 0.474). Conclusions : The RAPT-I was successfully adapted into Italian and proven to exhibit satisfactory properties, including predictive validity in determining discharge destination.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48549907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01Epub Date: 2019-04-05DOI: 10.6000/1929-6029.2019.08.01
Terrence E Murphy, Sui W Tsang, Linda S Leo-Summers, Mary Geda, Dae H Kim, Esther Oh, Heather G Allore, John Dodson, Alexandra M Hajduk, Thomas M Gill, Sarwat I Chaudhry
We describe a selection process for a multivariable risk prediction model of death within 30 days of hospital discharge in the SILVER-AMI study. This large, multi-site observational study included observational data from 2000 persons 75 years and older hospitalized for acute myocardial infarction (AMI) from 94 community and academic hospitals across the United States and featured a large number of candidate variables from demographic, cardiac, and geriatric domains, whose missing values were multiply imputed prior to model selection. Our objective was to demonstrate that Bayesian Model Averaging (BMA) represents a viable model selection approach in this context. BMA was compared to three other backward-selection approaches: Akaike information criterion, Bayesian information criterion, and traditional p-value. Traditional backward-selection was used to choose 20 candidate variables from the initial, larger pool of five imputations. Models were subsequently chosen from those candidates using the four approaches on each of 10 imputations. With average posterior effect probability ≥ 50% as the selection criterion, BMA chose the most parsimonious model with four variables, with average C statistic of 78%, good calibration, optimism of 1.3%, and heuristic shrinkage of 0.93. These findings illustrate the utility and flexibility of using BMA for selecting a multivariable risk prediction model from many candidates over multiply imputed datasets.
{"title":"Bayesian Model Averaging for Selection of a Risk Prediction Model for Death within Thirty Days of Discharge: The SILVER-AMI Study.","authors":"Terrence E Murphy, Sui W Tsang, Linda S Leo-Summers, Mary Geda, Dae H Kim, Esther Oh, Heather G Allore, John Dodson, Alexandra M Hajduk, Thomas M Gill, Sarwat I Chaudhry","doi":"10.6000/1929-6029.2019.08.01","DOIUrl":"https://doi.org/10.6000/1929-6029.2019.08.01","url":null,"abstract":"<p><p>We describe a selection process for a multivariable risk prediction model of death within 30 days of hospital discharge in the SILVER-AMI study. This large, multi-site observational study included observational data from 2000 persons 75 years and older hospitalized for acute myocardial infarction (AMI) from 94 community and academic hospitals across the United States and featured a large number of candidate variables from demographic, cardiac, and geriatric domains, whose missing values were multiply imputed prior to model selection. Our objective was to demonstrate that Bayesian Model Averaging (BMA) represents a viable model selection approach in this context. BMA was compared to three other backward-selection approaches: Akaike information criterion, Bayesian information criterion, and traditional p-value. Traditional backward-selection was used to choose 20 candidate variables from the initial, larger pool of five imputations. Models were subsequently chosen from those candidates using the four approaches on each of 10 imputations. With average posterior effect probability ≥ 50% as the selection criterion, BMA chose the most parsimonious model with four variables, with average C statistic of 78%, good calibration, optimism of 1.3%, and heuristic shrinkage of 0.93. These findings illustrate the utility and flexibility of using BMA for selecting a multivariable risk prediction model from many candidates over multiply imputed datasets.</p>","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":"8 ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/3d/86/nihms-1027580.PMC6553647.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37312669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-24DOI: 10.6000/1929-6029.2018.07.04.2
P. Karadeniz, I. Ercan
In clinical practice the event of interest does not always occur equally across the study time period. Depending on the disease being investigated, the event that is of interest can occur intensively in different periods of the follow-up time. In such cases, choosing the correct survival comparison test has importance. This study aims to examine and discuss the results of survival comparison tests under some certain circumstances. A simulation study was conducted. We discussed the result of different tests such as Logrank, Gehan-Wilcoxon, Tarone-Ware, Peto-Peto, Modified Peto-Peto tests and tests belonging to Fleming-Harrington test family with (p, q) values; (1, 0), (0.5, 0.5), (1, 1), (0, 1) ve (0.5, 2) by means of Type I error rate that obtained from simulation study, when the event of interest occurred intensively at the beginning of the study, in the middle of the study and at the end of the study time period. As a result of simulation study, Type I error rate of tests is generally lower or higher than the nominal value. In the light of the results, it is proposed to re-examine the tests for cases where events are observed intensively at the beginning, middle and late periods, to carry out new simulation studies and to develop new tests if necessary.
{"title":"On Comparing Survival Curves with Right-Censored Data According to the Events Occur at the Beginning, in the Middle and at the End of Study Period","authors":"P. Karadeniz, I. Ercan","doi":"10.6000/1929-6029.2018.07.04.2","DOIUrl":"https://doi.org/10.6000/1929-6029.2018.07.04.2","url":null,"abstract":"In clinical practice the event of interest does not always occur equally across the study time period. Depending on the disease being investigated, the event that is of interest can occur intensively in different periods of the follow-up time. In such cases, choosing the correct survival comparison test has importance. This study aims to examine and discuss the results of survival comparison tests under some certain circumstances. A simulation study was conducted. We discussed the result of different tests such as Logrank, Gehan-Wilcoxon, Tarone-Ware, Peto-Peto, Modified Peto-Peto tests and tests belonging to Fleming-Harrington test family with (p, q) values; (1, 0), (0.5, 0.5), (1, 1), (0, 1) ve (0.5, 2) by means of Type I error rate that obtained from simulation study, when the event of interest occurred intensively at the beginning of the study, in the middle of the study and at the end of the study time period. As a result of simulation study, Type I error rate of tests is generally lower or higher than the nominal value. In the light of the results, it is proposed to re-examine the tests for cases where events are observed intensively at the beginning, middle and late periods, to carry out new simulation studies and to develop new tests if necessary.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43605208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-24DOI: 10.6000/1929-6029.2018.07.04.1
K. Cunanan, M. Polley
Cancer researchers are often interested in identifying biomarkers that are indicative of poor outcomes (prognostic biomarkers) or response to specific therapies (predictive biomarkers). In designing a biomarker study, the first statistical issue encountered is the sample size requirement for adequate detection of a biomarker effect. In biomarker studies, the desired effect size is typically larger than those targeted in therapeutic trials and the biomarker prevalence is rarely near the optimal 50% . In this article, we review sample size formulas that are routinely used in designing therapeutic trials. We then conduct simulation studies to evaluate the performances of these methods when applied to biomarker studies. In particular, we examine the impact that deviations from certain statistical assumptions (i.e., biomarker positive prevalence and effect size) have on statistical power and type I error. Our simulation results indicate that when the true biomarker prevalence is close to 50% , all methods perform well in terms of power regardless of the magnitude of the targeted biomarker effect. However, when the biomarker positive prevalence rate deviates from 50% , the empirical power based on some existing methods may be substantially different from the nominal power, and this discrepancy becomes more profound for large biomarker effects. The type I error is maintained close to the 5% nominal level in all scenarios we investigate, although there is a slight inflation as the targeted effect size increases. Based on these results, we delineate the range of parameters within which the use of some sample size methods may be sufficiently robust.
{"title":"A Simulation Based Evaluation of Sample Size Methods for Biomarker Studies","authors":"K. Cunanan, M. Polley","doi":"10.6000/1929-6029.2018.07.04.1","DOIUrl":"https://doi.org/10.6000/1929-6029.2018.07.04.1","url":null,"abstract":"Cancer researchers are often interested in identifying biomarkers that are indicative of poor outcomes (prognostic biomarkers) or response to specific therapies (predictive biomarkers). In designing a biomarker study, the first statistical issue encountered is the sample size requirement for adequate detection of a biomarker effect. In biomarker studies, the desired effect size is typically larger than those targeted in therapeutic trials and the biomarker prevalence is rarely near the optimal 50% . In this article, we review sample size formulas that are routinely used in designing therapeutic trials. We then conduct simulation studies to evaluate the performances of these methods when applied to biomarker studies. In particular, we examine the impact that deviations from certain statistical assumptions (i.e., biomarker positive prevalence and effect size) have on statistical power and type I error. Our simulation results indicate that when the true biomarker prevalence is close to 50% , all methods perform well in terms of power regardless of the magnitude of the targeted biomarker effect. However, when the biomarker positive prevalence rate deviates from 50% , the empirical power based on some existing methods may be substantially different from the nominal power, and this discrepancy becomes more profound for large biomarker effects. The type I error is maintained close to the 5% nominal level in all scenarios we investigate, although there is a slight inflation as the targeted effect size increases. Based on these results, we delineate the range of parameters within which the use of some sample size methods may be sufficiently robust.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49135511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-24DOI: 10.6000/1929-6029.2018.07.04.3
V. Ravi, G. Grover, R. Das, M. Varshney, Anurag Sharma
Till now, many research papers have been published which aims to estimate the survivle time of the HIV/AIDS patients taking into consideration all the predictors viz, Age, Sex, CD4, MOT, Smoking, Weight, HB, Coinfection, Time, BMI, Location Status, Marital Status, Drug etc, although all the predictors need not to be included in the model. Since some of the predictors may be correlated/ associated and may have some influence on the outcome variable, therefore, instead of taking both the significantly correlated/ associated predictors, we may take only one of the two. In this way, we may be able to reduce the number of predictors without affecting the estimated survival time. In this paper we have tried to reduce the number of predictors by determining the highly positively correlated predictors and then evaluating the effect of correlation/ association on the survival time of HIV/AIDS patients. These predictors that we have considered in the starting are Age, Sex, State, Smoking, Alcohol, Drugs, Opportunistic Infections (OI), Living Status (LS), Occupation (OC), Marital Status (MS) and Spouse for the data collected from 2004 to 2014 of AIDS patients in an ART center of Delhi, India. We have performed one – way ANOVA to test the association between a quantitative and a categorical variable and Chi-square test to test between two categorical variables. To select one of the two highly correlated/ associated predictors, a suitable model is fitted keeping one predictor independent at a time and other dependent and the model having the smaller AIC is considered and the independent variable in the model is included in the modified model. The fitted models are logistic, linear and multinomial logistic depending on the type of the independent variable to be fitted. Then the true model (having all the predictors) and the modified model (with reduced number of predictors) are compared on the basis of their AICs and the model having minimum AIC is chosen. In this way we could reduce the number of predictors by almost 50% without affecting the estimated survival time with a reduced standard error.
{"title":"A Correlation Technique to Reduce the Number of Predictors to Estimate the Survival Time of HIV/ AIDS Patients on ART","authors":"V. Ravi, G. Grover, R. Das, M. Varshney, Anurag Sharma","doi":"10.6000/1929-6029.2018.07.04.3","DOIUrl":"https://doi.org/10.6000/1929-6029.2018.07.04.3","url":null,"abstract":"Till now, many research papers have been published which aims to estimate the survivle time of the HIV/AIDS patients taking into consideration all the predictors viz, Age, Sex, CD4, MOT, Smoking, Weight, HB, Coinfection, Time, BMI, Location Status, Marital Status, Drug etc, although all the predictors need not to be included in the model. Since some of the predictors may be correlated/ associated and may have some influence on the outcome variable, therefore, instead of taking both the significantly correlated/ associated predictors, we may take only one of the two. In this way, we may be able to reduce the number of predictors without affecting the estimated survival time. In this paper we have tried to reduce the number of predictors by determining the highly positively correlated predictors and then evaluating the effect of correlation/ association on the survival time of HIV/AIDS patients. These predictors that we have considered in the starting are Age, Sex, State, Smoking, Alcohol, Drugs, Opportunistic Infections (OI), Living Status (LS), Occupation (OC), Marital Status (MS) and Spouse for the data collected from 2004 to 2014 of AIDS patients in an ART center of Delhi, India. We have performed one – way ANOVA to test the association between a quantitative and a categorical variable and Chi-square test to test between two categorical variables. To select one of the two highly correlated/ associated predictors, a suitable model is fitted keeping one predictor independent at a time and other dependent and the model having the smaller AIC is considered and the independent variable in the model is included in the modified model. The fitted models are logistic, linear and multinomial logistic depending on the type of the independent variable to be fitted. Then the true model (having all the predictors) and the modified model (with reduced number of predictors) are compared on the basis of their AICs and the model having minimum AIC is chosen. In this way we could reduce the number of predictors by almost 50% without affecting the estimated survival time with a reduced standard error.","PeriodicalId":73480,"journal":{"name":"International journal of statistics in medical research","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43298022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：