HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
Surfing a Great Wave: Data Science and Global Health
1. Surfing a great wave
Data Science and Global Health
John Spencer, MA
Peter Lance, PhD
Mark Janko
MEASURE Evaluation
University of North Carolina at Chapel Hill
January 13, 2016
2. What is data science?
How is data science
happening at USAID?
3. Global, five-year, $180M cooperative agreement
Strategic objective:
To strengthen health information systems – the
capacity to gather, interpret, and use data – so
countries can make better decisions and sustain good
health outcomes over time.
Project overview
4. MEASURE Evaluation
Phase IV Results Framework
Strengthened collection, analysis,
and use of routine health data
Improved country capacity to
manage health information
systems, resources, and staff
Methods, tools, and approaches
improved and applied to address
health information challenges and
gaps
Increased capacity for rigorous
evaluation
7. “Health policymakers, international donors, program
managers, service providers and other health system
stakeholders need reliable data to make evidence-based
decisions.”
9. “If we are going to ensure that people everywhere have access
to quality health care … we need to invest in high-quality,
timely, and accurate data and statistics.”
10. The path to better global health is in the data.
27. Data can be so complex it
can be hard to extract and
analyze
28. Lessons from the analysis
of the data can be hard to
communicate
29. The way things have worked
Question
Gather data
from traditional
siloed sources
(DHS, RHS,
Census, etc.)
Hypothesis
testing
Produce static
data product
(Lather, rinse, repeat)
34. Data science is a discipline and process that
integrates 3 key skills for surfing this Tsunami:
1. Locating and retrieving key data to that
can inform decision making
2. Turning that data into actionable
information
3. Communicating that information in the
most effective way
35.
36. Data science is the approach
used by organizations that
live and die by data
45. Quantifying seasonal population fluxes driving
rubella transmission dynamics using mobile phone
data
Wesolowski, Metcalf, et al; PNAS; Vol 112 no. 35; Sept 1 2015
50. Subnational
models using
DHS data
• Travel time to cities
• Population
• Aridity
• Elevaton data from Shuttle
• Daytime/nighttime land surface temperature
• Rainfall
• Landcover
DHS Program: Spatial Analysis Report Number 11
Covariates
51. Bayesian analysis of DHS and PEPFAR reporting data
Stay tuned….
Are PEPFAR sites
underperforming or
over performing?
54. Conclusion
More data about the world than ever before.
This data tsunami offers unprecedented
opportunities, but also challenges.
Data science is a production process for data
that can harness the data tsunami
57. Questions for audience
What are you working on where traditional data
sources and techniques are missing part of the
story?
How is data science happening at USAID?
58. MEASURE Evaluation is funded by the U.S. Agency
for International Development (USAID) under terms
of Cooperative Agreement AID-OAA-L-14-00004 and
implemented by the Carolina Population Center, University
of North Carolina at Chapel Hill in partnership with ICF
International, John Snow, Inc., Management Sciences for
Health, Palladium Group, and Tulane University. The views
expressed in this presentation do not necessarily reflect
the views of USAID or the United States government.
www.measureevaluation.org