Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions
Objective: The purpose of this study was to present the design, model, and data analysis of an interrupted time series (ITS) model applied to evaluate the impact of health policy, systems, or environmental interventions using count outcomes. Simulation methods were used to conduct power and sample s...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-03-01
|
| Series: | Contemporary Clinical Trials Communications |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2451865419302364 |
| _version_ | 1818486532125753344 |
|---|---|
| author | Wei Liu Shangyuan Ye Bruce A. Barton Melissa A. Fischer Colleen Lawrence Elizabeth J. Rahn Maria I. Danila Kenneth G. Saag Paul A. Harris Stephenie C. Lemon Jeroan J. Allison Bo Zhang |
| author_facet | Wei Liu Shangyuan Ye Bruce A. Barton Melissa A. Fischer Colleen Lawrence Elizabeth J. Rahn Maria I. Danila Kenneth G. Saag Paul A. Harris Stephenie C. Lemon Jeroan J. Allison Bo Zhang |
| author_sort | Wei Liu |
| collection | DOAJ |
| description | Objective: The purpose of this study was to present the design, model, and data analysis of an interrupted time series (ITS) model applied to evaluate the impact of health policy, systems, or environmental interventions using count outcomes. Simulation methods were used to conduct power and sample size calculations for these studies. Methods: We proposed the models and analyses of ITS designs for count outcomes using the Strengthening Translational Research in Diverse Enrollment (STRIDE) study as an example. The models we used were observation-driven models, which bundle a lagged term on the conditional mean of the outcome for a time series of count outcomes. Results: A simulation-based approach with ready-to-use computer programs was developed to calculate the sample size and power of two types of ITS models, Poisson and negative binomial, for count outcomes. Simulations were conducted to estimate the power of segmented autoregressive (AR) error models when autocorrelation ranged from −0.9 to 0.9, with various effect sizes. The power to detect the same magnitude of parameters varied largely, depending on the testing level change, the trend change, or both. The relationships between power and sample size and the values of the parameters were different between the two models. Conclusion: This article provides a convenient tool to allow investigators to generate sample sizes that will ensure sufficient statistical power when the ITS study design of count outcomes is implemented. Keywords: Policy evaluation, Interrupted time series, Count outcomes, Segmented regression, Quasi-experimental design, Power, Sample size calculation |
| first_indexed | 2024-12-10T16:24:14Z |
| format | Article |
| id | doaj.art-d63de003e238460c8347bc0f3664739e |
| institution | Directory Open Access Journal |
| issn | 2451-8654 |
| language | English |
| last_indexed | 2024-12-10T16:24:14Z |
| publishDate | 2020-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Contemporary Clinical Trials Communications |
| spelling | doaj.art-d63de003e238460c8347bc0f3664739e2022-12-22T01:41:44ZengElsevierContemporary Clinical Trials Communications2451-86542020-03-0117Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventionsWei Liu0Shangyuan Ye1Bruce A. Barton2Melissa A. Fischer3Colleen Lawrence4Elizabeth J. Rahn5Maria I. Danila6Kenneth G. Saag7Paul A. Harris8Stephenie C. Lemon9Jeroan J. Allison10Bo Zhang11School of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, ChinaDepartment of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA, 02115, USASchool of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, ChinaDepartment of Internal Medicine, University of Massachusetts Medical School, Worcester, MA, 01605, USA; Meyers Primary Care Institute, University of Massachusetts Medical School, Fallon Foundation, and Fallon Community Health Plan, Worcester, MA, 01605, USAVanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Nashville, TN, 37232, USADivision of Clinical Immunology and Rheumatology, University of Alabama at Birmingham, Birmingham, AL, 35294, USADivision of Clinical Immunology and Rheumatology, University of Alabama at Birmingham, Birmingham, AL, 35294, USADivision of Clinical Immunology and Rheumatology, University of Alabama at Birmingham, Birmingham, AL, 35294, USADepartment of Biomedical Informatics and Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, 37203, USASchool of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, ChinaSchool of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, ChinaDepartment of Neurology and ICCTR Biostatistics and Research Design Center, Boston Children’s Hospital and Harvard Medical School, Boston, MA, 02215, USA; Corresponding author.Objective: The purpose of this study was to present the design, model, and data analysis of an interrupted time series (ITS) model applied to evaluate the impact of health policy, systems, or environmental interventions using count outcomes. Simulation methods were used to conduct power and sample size calculations for these studies. Methods: We proposed the models and analyses of ITS designs for count outcomes using the Strengthening Translational Research in Diverse Enrollment (STRIDE) study as an example. The models we used were observation-driven models, which bundle a lagged term on the conditional mean of the outcome for a time series of count outcomes. Results: A simulation-based approach with ready-to-use computer programs was developed to calculate the sample size and power of two types of ITS models, Poisson and negative binomial, for count outcomes. Simulations were conducted to estimate the power of segmented autoregressive (AR) error models when autocorrelation ranged from −0.9 to 0.9, with various effect sizes. The power to detect the same magnitude of parameters varied largely, depending on the testing level change, the trend change, or both. The relationships between power and sample size and the values of the parameters were different between the two models. Conclusion: This article provides a convenient tool to allow investigators to generate sample sizes that will ensure sufficient statistical power when the ITS study design of count outcomes is implemented. Keywords: Policy evaluation, Interrupted time series, Count outcomes, Segmented regression, Quasi-experimental design, Power, Sample size calculationhttp://www.sciencedirect.com/science/article/pii/S2451865419302364 |
| spellingShingle | Wei Liu Shangyuan Ye Bruce A. Barton Melissa A. Fischer Colleen Lawrence Elizabeth J. Rahn Maria I. Danila Kenneth G. Saag Paul A. Harris Stephenie C. Lemon Jeroan J. Allison Bo Zhang Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions Contemporary Clinical Trials Communications |
| title | Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| title_full | Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| title_fullStr | Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| title_full_unstemmed | Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| title_short | Simulation-based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| title_sort | simulation based power and sample size calculation for designing interrupted time series analyses of count outcomes in evaluation of health policy interventions |
| url | http://www.sciencedirect.com/science/article/pii/S2451865419302364 |
| work_keys_str_mv | AT weiliu simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT shangyuanye simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT bruceabarton simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT melissaafischer simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT colleenlawrence simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT elizabethjrahn simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT mariaidanila simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT kennethgsaag simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT paulaharris simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT stephenieclemon simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT jeroanjallison simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions AT bozhang simulationbasedpowerandsamplesizecalculationfordesigninginterruptedtimeseriesanalysesofcountoutcomesinevaluationofhealthpolicyinterventions |