Quantitative Data Analyst, EMSRIE, Remote

Management Systems International (MSI), a Tetra Tech Company, is a Washington, D.C. metro area management consultancy with a 40-year history of delivering results for our clients. Our expertise is in the fields of monitoring and evaluation; democracy and governance; peace and stability; rule of law and accountability; education; gender and inclusion; strategic communications; and leadership and organizational development. MSI has implemented projects in 90 countries around the world such as Colombia, Indonesia, Jordan, Kenya, Mexico, Nigeria, Pakistan, Syria and Ukraine, and works domestically. We support clients ranging from the U.S. Government (e.g., the U.S. Agency for International Development, U.S. Department of Defense, U.S. Departments of State and Labor, and the Millennium Challenge Corporation) to large bilateral and multilateral donors (e.g., the World Bank and the United Nations Development Program). We also work with national and local governments, nongovernmental organizations (NGOs), think tanks, foundations and universities. For more information, please visit our website at www.msiworldwide.com.

Project Summary:

The Evidence Mapping, Systematic Review, and Impact Evaluation (EMSRIE) activity supports the United States Agency for International Development’s (USAID) Bureau for Resilience, Environment, and Food Security (REFS) and buy-in clients across the agency with systematic reviews, evidence gap maps, and impact evaluations (IEs). USAID engaged Management Systems International (MSI), a Tetra Tech company, to implement EMSRIE in partnership with a major subcontractor the International Initiative for Impact Evaluations (3ie). The contract’s five-year period of performance is from September 14, 2023, to September 13, 2028.

**Please note: U.S. work authorization is required for this position**

Position Summary:

The Quantitative Data Analyst will be a short term consultant. The Analyst will perform data cleaning and preparation, statistical analysis, create data visualizations, contribute to report writing and informing evaluation design especially power calculations to inform sampling. The Analyst will work as part of a multidisciplinary team, collaborating with Qualitative Researchers, Program Managers, and Subject Matter Experts. The role will be critical in ensuring that the evaluation produces robust, data-driven evidence of the program's impact, which will inform policy decisions and improve program effectiveness.

Responsibilities:

• Create surveys, questionnaires, and other quantitative data collection tools to capture the necessary data for the evaluation, ensure statistical soundness, and minimize potential biases.
• Determine appropriate sample sizes and sampling methods crucial for the validity of the evaluation including calculating required sample sizes to achieve sufficient statistical power, designing stratification strategies if needed, and developing methods for random selection of participants.
• Process raw data to prepare it for analysis, including identifying and handling missing data, detecting and correcting errors, standardizing variables, and creating derived variables as needed for the analysis.
• Perform various types of statistical analyses, including descriptive statistics, inferential statistics, regression analysis, propensity score matching, difference-in-differences analysis, and other advanced techniques appropriate for the evaluation design.
• Design and produce charts, graphs, tables, and other visualizations that clearly convey key insights from the analysis, ensuring effective communication of findings to diverse audiences.
• Write sections of technical reports detailing the methodologies used, presenting results, and discussing statistical findings including translating complex statistical concepts into language accessible to a broader audience.
• Calculate statistical power to ensure that the evaluation can detect meaningful program effects including determining the minimum detectable effect size given the sample size, or conversely, the sample size needed to detect a specific effect size.