Walter T. Ambrosius
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Walter T. Ambrosius has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Mary McGrae McDermott
Northwestern University Feinberg School of Medicine
2 shared publications - Amal Asiri Wanigatunga
Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health , Baltimore, Maryland
1 shared publication Amita K. Manatunga
Department of Biostatistics, Rollins School of Public Health, Emory University, 1518 Clifton Road NE, Atlanta, GA 30322, U.S.A.
1 shared publication- Anne B. Newman
Department of Epidemiology, School of Public Health, University of Pittsburgh , Pittsburgh, Pennsylvania
1 shared publication Anthony P Marsh
Wake Forest Univ, Winston-Salem, NC
1 shared publicationBarbara A. Esser
1 shared publication
Latest Publications
- Open Access
- 5 May 2025
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 55 (8) , 1-18
Bayesian variable selection for logistic regression with a differentially misclassified binary covariate
A Bayesian approach for variable selection is developed for use in models with a misclassified binary predictor variable. We define the main outcome model containing the latent predictor, the measurement model associated with the prevalence of the predictor, and the sensitivity and specificity models of the fallible classifier conditioned on the true value of the predictor. We use binary indicator variables to execute the Gibbs sampler-based variable selection process, and we identify the highest posterior probability model given the data. We demonstrate the performance of the procedure in several simulation studies, and we utilize the selection method to optimize model performance in two datasets.
- 5 May 2025
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 55 (8) , 1-18
Open AccessBayesian variable selection for logistic regression with a differentially misclassified binary covariate
A Bayesian approach for variable selection is developed for use in models with a misclassified binary predictor variable. We define the main outcome model containing the latent predictor, the measurement model associated with the prevalence of the predictor, and the sensitivity and specificity models of the fallible classifier conditioned on the true value of the predictor. We use binary indicator variables to execute the Gibbs sampler-based variable selection process, and we identify the highest posterior probability model given the data. We demonstrate the performance of the procedure in several simulation studies, and we utilize the selection method to optimize model performance in two datasets.
- 8 April 2025
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 100 (9) , 1013-1017
The Science of Statistical Practice
Emerging technologies, such as artificial intelligence, emphasize the importance of quantitative methods and their applications when conducting increasingly data-intensive research. The scientific discipline of statistical practice is critical for achieving rigor in research addressing important domain-level questions. The misconception that statistical practice is not a science but rather a service threatens scientific rigor and compromises the quality of its contribution to clinical and translational research. The authors call on academic and research leadership to recognize statistical practice as a key scientific discipline and to further ensure that the field and its scientists are nurtured. To that end, academic homes for faculty of statistical practice and its scholarship need to be fostered with clear pathways to hire, retain, promote, and tenure faculty who are largely team scientists. This goal can be achieved inclusively by avoiding the creation of separate faculty lines that might imply differing levels of value. In contrast, we must recognize and appreciate equally significant intellectual contributions made by various types of faculty members. Additionally, engagement of statistical practitioners as peer scientists and coleaders in collaborative research will ensure higher quality and rigor of scientific endeavors. Finally, leaders of statistical practice must be included in critical discussions around strategic development for academic and other research organizations for those institutions to achieve their missions in this modern era of data-intensive research.
- 8 April 2025
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 100 (9) , 1013-1017
The Science of Statistical Practice
Emerging technologies, such as artificial intelligence, emphasize the importance of quantitative methods and their applications when conducting increasingly data-intensive research. The scientific discipline of statistical practice is critical for achieving rigor in research addressing important domain-level questions. The misconception that statistical practice is not a science but rather a service threatens scientific rigor and compromises the quality of its contribution to clinical and translational research. The authors call on academic and research leadership to recognize statistical practice as a key scientific discipline and to further ensure that the field and its scientists are nurtured. To that end, academic homes for faculty of statistical practice and its scholarship need to be fostered with clear pathways to hire, retain, promote, and tenure faculty who are largely team scientists. This goal can be achieved inclusively by avoiding the creation of separate faculty lines that might imply differing levels of value. In contrast, we must recognize and appreciate equally significant intellectual contributions made by various types of faculty members. Additionally, engagement of statistical practitioners as peer scientists and coleaders in collaborative research will ensure higher quality and rigor of scientific endeavors. Finally, leaders of statistical practice must be included in critical discussions around strategic development for academic and other research organizations for those institutions to achieve their missions in this modern era of data-intensive research.
- 26 December 2024
- Published by Oxford University Press (OUP) in American Journal of Epidemiology
- Vol. 194 (11) , 3185-3194
The effect of intensive treatment of hypertension on cardiovascular events, generalized to middle-aged to older Americans living with hypertension
The Systolic Blood Pressure Intervention Trial (SPRINT) estimated the effect of intensive systolic blood pressure treatment (target <120 mm Hg) compared to standard (<140 mm Hg) on the risk of cardiovascular events in adults aged 50 years and older. Clinical trial participants may differ from an intervention’s target population. We generalized the SPRINT results to US adults who would qualify for treatment under SPRINT eligibility criteria. We applied these eligibility criteria to participants of the National Health and Nutrition Examination Survey (NHANES) from 2011–2018 to describe the target population. We estimated Cox proportional hazards models and Kaplan–Meier risk curves, weighted with the inverse odds of sampling, to estimate hazards ratios (HRs) and 5-year risk differences for the effect of intensive treatment on cardiovascular and adverse events in the target population. The HR for cardiovascular disease events was 0.76 (95% confidence interval [CI]: 0.53, 1.08) comparing intensive to standard treatment, which is consistent with the estimates from the original SPRINT trial. The 5-year risk difference for a cardiovascular event was $-$2.2% (95% CI: $-$5.3%, 1.6%). The HR for serious adverse events was 0.97 (95% CI: 0.83, 1.13). Despite differences between the SPRINT and target populations, we estimated a similar benefit of intensive treatment and similar rates of SAEs, in the target population.
- 26 December 2024
- Published by Oxford University Press (OUP) in American Journal of Epidemiology
- Vol. 194 (11) , 3185-3194
The effect of intensive treatment of hypertension on cardiovascular events, generalized to middle-aged to older Americans living with hypertension
The Systolic Blood Pressure Intervention Trial (SPRINT) estimated the effect of intensive systolic blood pressure treatment (target <120 mm Hg) compared to standard (<140 mm Hg) on the risk of cardiovascular events in adults aged 50 years and older. Clinical trial participants may differ from an intervention’s target population. We generalized the SPRINT results to US adults who would qualify for treatment under SPRINT eligibility criteria. We applied these eligibility criteria to participants of the National Health and Nutrition Examination Survey (NHANES) from 2011–2018 to describe the target population. We estimated Cox proportional hazards models and Kaplan–Meier risk curves, weighted with the inverse odds of sampling, to estimate hazards ratios (HRs) and 5-year risk differences for the effect of intensive treatment on cardiovascular and adverse events in the target population. The HR for cardiovascular disease events was 0.76 (95% confidence interval [CI]: 0.53, 1.08) comparing intensive to standard treatment, which is consistent with the estimates from the original SPRINT trial. The 5-year risk difference for a cardiovascular event was $-$2.2% (95% CI: $-$5.3%, 1.6%). The HR for serious adverse events was 0.97 (95% CI: 0.83, 1.13). Despite differences between the SPRINT and target populations, we estimated a similar benefit of intensive treatment and similar rates of SAEs, in the target population.
- Open Access
- 1 November 2018
- Published by Oxford University Press (OUP) in Innovation in Aging
- Vol. 2 (suppl_1) , 441
ENRGISE: PRIMARY, SECONDARY, AND SAFETY RESULTS
The ENRGISE Pilot study has excellent retention and adherence. As of March 6, 2018 of the 286 randomized participants 97.2%, 98.2%, 95.5%, 89.8% have completed a 3, 6, 9, and 12 month follow-up visit, respectively, and 7.9% have a pending 12 month visit. A total of 88% of 234 participants randomized to omega 3 arms and 69% of 101 participants randomized to losartan arms reported excellent, very good, or good ability to take the study drugs. The DSMB did not raise any concerns regarding safety and recommended continuation of the study. Follow-up visits will be completed in June 2018. We will present the following outcomes according to the randomized arms: IL-6, 400 m walking speed, incidence of major mobility disability (inability to walk 400m), short physical performance battery scores (balance, 4 m walk, and chair stands tests), and strength. The pilot will inform the planning of the main ENRGISE trial.
- 1 November 2018
- Published by Oxford University Press (OUP) in Innovation in Aging
- Vol. 2 (suppl_1) , 441
Open AccessENRGISE: PRIMARY, SECONDARY, AND SAFETY RESULTS
The ENRGISE Pilot study has excellent retention and adherence. As of March 6, 2018 of the 286 randomized participants 97.2%, 98.2%, 95.5%, 89.8% have completed a 3, 6, 9, and 12 month follow-up visit, respectively, and 7.9% have a pending 12 month visit. A total of 88% of 234 participants randomized to omega 3 arms and 69% of 101 participants randomized to losartan arms reported excellent, very good, or good ability to take the study drugs. The DSMB did not raise any concerns regarding safety and recommended continuation of the study. Follow-up visits will be completed in June 2018. We will present the following outcomes according to the randomized arms: IL-6, 400 m walking speed, incidence of major mobility disability (inability to walk 400m), short physical performance battery scores (balance, 4 m walk, and chair stands tests), and strength. The pilot will inform the planning of the main ENRGISE trial.
- 25 March 2014
- Published by Wolters Kluwer Health in Circulation
- Vol. 129 (suppl_1)
Abstract MP01: Association of Objectively-measured Physical Activity with Cardiovascular Risk in Mobility-limited Older Adults
Introduction: In middle-aged adults, time spent being sedentary is associated with cardiovascular (CV) health risks independent of structured physical activity (PA). However, data are sparse regarding the impact of sedentary behavior on CV risk in older adults. The extent to which the absolute duration or intensity of daily PA reduces CV risk in older adults is also unknown. Objectives: Our objective was to examine the cross-sectional association between objectively-measured sedentary behavior and predicted CV risk among older adults in the Lifestyle Interventions and Independence for Elders (LIFE) study. The secondary objective was to evaluate associations between the duration/intensity of daily PA and predicted CV risk. Methods: LIFE is a randomized clinical trial to determine if regular PA prevents mobility disability among mobility-limited older adults. Activity data were collected by hip-worn accelerometer at baseline prior to participation in study interventions. Only participants with at least three days of accelerometry data (≥ 10 hrs wear time) were included. Unadjusted and adjusted linear regression was used to model the relationship between accelerometry measures and predicted 10-year Framingham risk of Hard Coronary Heart Disease (HCHD; i.e. myocardial infarction or coronary death). Adjusted models included demographic confounders (e.g. education, race, income) and health parameters (e.g. depression, cognition, arthritis) not in the risk score. Accelerometry cut-points were (in counts/min): sedentary behavior: < 100; low-intensity activity: 100-499; higher intensity activity: > 500. Results: Participants (n = 1170; 78.7 ± [SD] 5.3 years; 66.1% female) had a median HCHD risk of 10.3% (25th-75th%: 5.7-18.6). Over a mean accelerometer wear time of 8.1 ± 3.2 days, participants spent 77.0 ± 8.2% of their time sedentary. They also spent 16.6 ± 5.0% of their time in low-intensity PA and 6.4 ± 4.4% in higher-intensity PA. For all PA performed (> 100 counts/min), participants achieved a median of 393.4 (337.8-473.5) counts/min. In the unadjusted model, time spent sedentary (β = 2.41; 95% CI : 1.94, 2.89), in low-intensity PA (-2.56; -3.03, -2.08), and in higher-intensity PA (-1.60; -2.09, -1.11) were all associated with HCHD risk (all p’s < 0.001). These associations remained significant after adjustment. The mean intensity of daily PA was not significantly associated with HCHD risk in any model (p > 0.05). Conclusions: Daily time spent being sedentary is positively associated with predicted 10-year HCHD risk among mobility-limited older adults. Duration, but not mean intensity, of daily PA is inversely associated with HCHD risk score in this population.
- 25 March 2014
- Published by Wolters Kluwer Health in Circulation
- Vol. 129 (suppl_1)
Abstract MP01: Association of Objectively-measured Physical Activity with Cardiovascular Risk in Mobility-limited Older Adults
Introduction: In middle-aged adults, time spent being sedentary is associated with cardiovascular (CV) health risks independent of structured physical activity (PA). However, data are sparse regarding the impact of sedentary behavior on CV risk in older adults. The extent to which the absolute duration or intensity of daily PA reduces CV risk in older adults is also unknown. Objectives: Our objective was to examine the cross-sectional association between objectively-measured sedentary behavior and predicted CV risk among older adults in the Lifestyle Interventions and Independence for Elders (LIFE) study. The secondary objective was to evaluate associations between the duration/intensity of daily PA and predicted CV risk. Methods: LIFE is a randomized clinical trial to determine if regular PA prevents mobility disability among mobility-limited older adults. Activity data were collected by hip-worn accelerometer at baseline prior to participation in study interventions. Only participants with at least three days of accelerometry data (≥ 10 hrs wear time) were included. Unadjusted and adjusted linear regression was used to model the relationship between accelerometry measures and predicted 10-year Framingham risk of Hard Coronary Heart Disease (HCHD; i.e. myocardial infarction or coronary death). Adjusted models included demographic confounders (e.g. education, race, income) and health parameters (e.g. depression, cognition, arthritis) not in the risk score. Accelerometry cut-points were (in counts/min): sedentary behavior: < 100; low-intensity activity: 100-499; higher intensity activity: > 500. Results: Participants (n = 1170; 78.7 ± [SD] 5.3 years; 66.1% female) had a median HCHD risk of 10.3% (25th-75th%: 5.7-18.6). Over a mean accelerometer wear time of 8.1 ± 3.2 days, participants spent 77.0 ± 8.2% of their time sedentary. They also spent 16.6 ± 5.0% of their time in low-intensity PA and 6.4 ± 4.4% in higher-intensity PA. For all PA performed (> 100 counts/min), participants achieved a median of 393.4 (337.8-473.5) counts/min. In the unadjusted model, time spent sedentary (β = 2.41; 95% CI : 1.94, 2.89), in low-intensity PA (-2.56; -3.03, -2.08), and in higher-intensity PA (-1.60; -2.09, -1.11) were all associated with HCHD risk (all p’s < 0.001). These associations remained significant after adjustment. The mean intensity of daily PA was not significantly associated with HCHD risk in any model (p > 0.05). Conclusions: Daily time spent being sedentary is positively associated with predicted 10-year HCHD risk among mobility-limited older adults. Duration, but not mean intensity, of daily PA is inversely associated with HCHD risk score in this population.
- Open Access
- 17 June 2013
- Published by Wiley in Journal of the American Geriatrics Society
- Vol. 61 (7) , 1089-1094
Independent and Combined Effects of Physical Activity and Weight Loss on Inflammatory Biomarkers in Overweight and Obese Older Adults
Objectives: To determine the independent effect of long‐term physical activity ( PA ) and the combined effects of long‐term PA and weight loss ( WL ) on inflammation in overweight and obese older adults. Design: Eighteen‐month randomized, controlled trial. Setting: The community infrastructure of cooperative extension centers. Participants: Overweight and obese (body mass index >28.0 kg/m 2 ) community‐dwelling men and women aged 60 to 79 at risk for cardiovascular disease ( CVD ). Intervention: Physical activity + weight loss (PA + WL) (n = 98), PA only (n = 97), or successful aging ( SA ) health education (n = 93) intervention. Measurements: Biomarkers of inflammation (adiponectin, leptin, high‐sensitivity interleukin (hs IL )‐6, IL ‐6s R , IL ‐8, and soluble tumor necrosis factor receptor 1) were measured at baseline and 6 and 18 months. Results: After adjustment for baseline biomarker, wave, sex, and visit, leptin and hsIL‐6 showed a significant intervention effect. Specifically, leptin was significantly lower in the PA + WL group (21.3 ng/mL, 95% confidence interval ( CI ) = 19.7–22.9 ng/mL) than in the PA (29.3 ng/mL, 95% CI = 26.9–31.8 ng/mL) or SA (30.3 ng/mL, 95% CI = 27.9–32.8 ng/mL) group (both P < .001), and hs IL ‐6 was significantly lower in the PA + WL group (2.1 pg/mL, 95% CI = 1.9–2.3 pg/mL) than in the PA (2.5 pg/mL, 95% CI = 2.3–2.7 pg/mL) or SA (2.4 pg/mL, 95% CI = 2.2–2.6 pg/mL) group ( P = .02). Conclusion: Addition of dietary‐induced WL to PA reduced leptin and hs IL ‐6 more than PA alone and more than a SA intervention in older adults at risk for CVD . Results suggest that WL , rather than increased PA , is the lifestyle factor primarily responsible for improvement in the inflammatory profile.
- 17 June 2013
- Published by Wiley in Journal of the American Geriatrics Society
- Vol. 61 (7) , 1089-1094
Open AccessIndependent and Combined Effects of Physical Activity and Weight Loss on Inflammatory Biomarkers in Overweight and Obese Older Adults
Objectives: To determine the independent effect of long‐term physical activity ( PA ) and the combined effects of long‐term PA and weight loss ( WL ) on inflammation in overweight and obese older adults. Design: Eighteen‐month randomized, controlled trial. Setting: The community infrastructure of cooperative extension centers. Participants: Overweight and obese (body mass index >28.0 kg/m 2 ) community‐dwelling men and women aged 60 to 79 at risk for cardiovascular disease ( CVD ). Intervention: Physical activity + weight loss (PA + WL) (n = 98), PA only (n = 97), or successful aging ( SA ) health education (n = 93) intervention. Measurements: Biomarkers of inflammation (adiponectin, leptin, high‐sensitivity interleukin (hs IL )‐6, IL ‐6s R , IL ‐8, and soluble tumor necrosis factor receptor 1) were measured at baseline and 6 and 18 months. Results: After adjustment for baseline biomarker, wave, sex, and visit, leptin and hsIL‐6 showed a significant intervention effect. Specifically, leptin was significantly lower in the PA + WL group (21.3 ng/mL, 95% confidence interval ( CI ) = 19.7–22.9 ng/mL) than in the PA (29.3 ng/mL, 95% CI = 26.9–31.8 ng/mL) or SA (30.3 ng/mL, 95% CI = 27.9–32.8 ng/mL) group (both P < .001), and hs IL ‐6 was significantly lower in the PA + WL group (2.1 pg/mL, 95% CI = 1.9–2.3 pg/mL) than in the PA (2.5 pg/mL, 95% CI = 2.3–2.7 pg/mL) or SA (2.4 pg/mL, 95% CI = 2.2–2.6 pg/mL) group ( P = .02). Conclusion: Addition of dietary‐induced WL to PA reduced leptin and hs IL ‐6 more than PA alone and more than a SA intervention in older adults at risk for CVD . Results suggest that WL , rather than increased PA , is the lifestyle factor primarily responsible for improvement in the inflammatory profile.
- 11 March 2010
- Published by Wiley in Statistics in Medicine
- Vol. 29 (10) , 1137-1144
Power for studies with random group sizes
In any study it is essential to select the sample size carefully to ensure adequate power. For many studies this is simple: recruit a desired number of subjects within each group, conduct measurements, and perform the statistical test. In some studies (e.g. observational studies), however, the group membership is unknown at recruitment. In this paper we examine the effect of random group sizes on power. Additionally, we consider the situation when the group proportions are unknown and specified by a prior distribution. The problem that initially motivated this research is presented (power for a 2-by-2 table), as are examples using continuous outcomes. We find that standard estimates of power using expected group sizes can over or underestimate power. SAS macros are available at http://www.phs.wfubmc.edu/public/wambrosi/RandomPower.
- 11 March 2010
- Published by Wiley in Statistics in Medicine
- Vol. 29 (10) , 1137-1144
Power for studies with random group sizes
In any study it is essential to select the sample size carefully to ensure adequate power. For many studies this is simple: recruit a desired number of subjects within each group, conduct measurements, and perform the statistical test. In some studies (e.g. observational studies), however, the group membership is unknown at recruitment. In this paper we examine the effect of random group sizes on power. Additionally, we consider the situation when the group proportions are unknown and specified by a prior distribution. The problem that initially motivated this research is presented (power for a 2-by-2 table), as are examples using continuous outcomes. We find that standard estimates of power using expected group sizes can over or underestimate power. SAS macros are available at http://www.phs.wfubmc.edu/public/wambrosi/RandomPower.
- Open Access
- 1 March 2010
- Published by American Medical Association (AMA) in Archives of Ophthalmology (1950)
- Vol. 128 (3) , 312-318
Lack of Association Between Thiazolidinediones and Macular Edema in Type 2 Diabetes
Diabetic macular edema (DME) is one of the main causes of visual impairment in persons with diabetic retinopathy. A small number of case reports have raised the possibility that use of thiazolidinediones, which can cause fluid retention, generally, might exacerbate DME.1,2 These observations led to physician alerts or label changes by manufacturers in Canada and the United States.3-6 One report1 described a patient who developed vision loss and DME after an increase in the dosage of rosiglitazone maleate from 2 to 8 mg/d. After the dosage was reverted to 2 mg/d, the vision of the patient improved and his DME resolved itself. Ryan et al2 reported results from a retrospective medical record review of 30 patients who sought care at a single practice of retinal specialists with use of pioglitazone hydrochloride or rosiglitazone and both lower-extremity edema and DME. The authors contended that fluid overload owing to use of thiazolidinediones contributed to DME in at least 19 of 30 patients and that, in 2 patients, there was evidence of a direct cause-and-effect relationship. Finally, a case report7 of macular edema being resolved with systemic furosemide suggests that thiazolidinediones may exacerbate macular edema. In a larger study of 292 patients, Shen et al8 found no association of rosiglitazone with DME.
- 1 March 2010
- Published by American Medical Association (AMA) in Archives of Ophthalmology (1950)
- Vol. 128 (3) , 312-318
Open AccessLack of Association Between Thiazolidinediones and Macular Edema in Type 2 Diabetes
Diabetic macular edema (DME) is one of the main causes of visual impairment in persons with diabetic retinopathy. A small number of case reports have raised the possibility that use of thiazolidinediones, which can cause fluid retention, generally, might exacerbate DME.1,2 These observations led to physician alerts or label changes by manufacturers in Canada and the United States.3-6 One report1 described a patient who developed vision loss and DME after an increase in the dosage of rosiglitazone maleate from 2 to 8 mg/d. After the dosage was reverted to 2 mg/d, the vision of the patient improved and his DME resolved itself. Ryan et al2 reported results from a retrospective medical record review of 30 patients who sought care at a single practice of retinal specialists with use of pioglitazone hydrochloride or rosiglitazone and both lower-extremity edema and DME. The authors contended that fluid overload owing to use of thiazolidinediones contributed to DME in at least 19 of 30 patients and that, in 2 patients, there was evidence of a direct cause-and-effect relationship. Finally, a case report7 of macular edema being resolved with systemic furosemide suggests that thiazolidinediones may exacerbate macular edema. In a larger study of 292 patients, Shen et al8 found no association of rosiglitazone with DME.
- 24 August 2004
- Published by Wiley in Statistics in Medicine
- Vol. 23 (18) , 2845-2861
Cross calibration in longitudinal studies
In a long‐running longitudinal study using complex machinery to obtain measurements, it is sometimes necessary to replace the machine. This can result in lack of continuity in the measurements that can overwhelm any treatment effect or time trend. We propose a Bayesian procedure implemented using Markov chain Monte Carlo to calibrate the measurements on the old machine utilizing both person‐specific and population information. The goal is to convert the previous measurements to values that can be treated as though they were made on the new machine. This methodology is applied to a bone mineral density study where the first densitometer uses gadolinium as the energy source (Lunar DP‐3) and the second uses X‐rays (Hologic QDR‐1000W). Finally, simulation results are presented to show the superiority of the proposed method over existing methods of cross calibration. Copyright © 2004 John Wiley & Sons, Ltd.
- 24 August 2004
- Published by Wiley in Statistics in Medicine
- Vol. 23 (18) , 2845-2861
Cross calibration in longitudinal studies
In a long‐running longitudinal study using complex machinery to obtain measurements, it is sometimes necessary to replace the machine. This can result in lack of continuity in the measurements that can overwhelm any treatment effect or time trend. We propose a Bayesian procedure implemented using Markov chain Monte Carlo to calibrate the measurements on the old machine utilizing both person‐specific and population information. The goal is to convert the previous measurements to values that can be treated as though they were made on the new machine. This methodology is applied to a bone mineral density study where the first densitometer uses gadolinium as the energy source (Lunar DP‐3) and the second uses X‐rays (Hologic QDR‐1000W). Finally, simulation results are presented to show the superiority of the proposed method over existing methods of cross calibration. Copyright © 2004 John Wiley & Sons, Ltd.
- Open Access
- 1 April 2004
- Published by Elsevier in The American Journal of Human Genetics
- Vol. 74 (4) , 683-693
Power for Genetic Association Studies with Random Allele Frequencies and Genotype Distributions
- 1 April 2004
- Published by Elsevier in The American Journal of Human Genetics
- Vol. 74 (4) , 683-693
Open AccessPower for Genetic Association Studies with Random Allele Frequencies and Genotype Distributions