Godwin Kipkoech Bett
Data Analyst
Email:-| Phone: + -
Summary
Professional with over five years of data analysis, data quality management, monitoring, and evaluation experience.
Key achievements include leading the data analysis component of the HJFMRI Program in ensuring data quality,
informative inferential and predictive analytics for decision-making by program leadership and proactive clinical
care of patients at health facilities. I have proficiency in analytical tools, specifically, R, Stata, SQL, and Python. I
am a motivated professional that learns fast, thrives in minimal supervision, and self-educates to master interesting
topics in science and emerging fields of Artificial Intelligence.
Education
University of Kabianga | Bachelor of Science in Applied Statistics and Computing | 2010 - 2014
Programming Languages (R, Python, C++, SQL), Data Management (Collection, Validation and Cleaning),
Exploratory Data Analysis, Machine Learning and Predictive Analytics, Inferential Statistics, Time series analysis
and Survey Methods
Key Skills
•
•
•
•
•
•
Data manipulation, Exploratory Data Analysis and Visualization using R, Microsoft Excel, and Stata
Inferential analysis utilizing hypothesis & significance tests, analysis of variance,
Machine Learning using R and Python for predictive analytics through Linear regression, Logistic
Regression, Classification with K Nearest Neighbours, Support Vector Machines, Decision Trees and
Random Forests, K-Means Clustering, Natural Language Processing and Neural Networks.
QGIS Mapping – Geospatial analysis of program performance with indicator overlays on Geographical
regions.
Tableau – Data visualization, analytics dashboards, and Geographical mapping
Proficient in developing data collection forms and survey questionnaires using Computer Aided Personal
Interview (CAPI) platforms; CS-Pro, Kobo Toolbox, SurveyCTO and ODK
Work Experience
Program Data Analyst | Henry Jackson Foundation Medical Research International (HJFMRI)
July 2022 – Present
•
•
•
•
Development of Machine Learning models for predictive analytics on HIV client data to support health
facility care providers make proactive decisions with regards to clinical care management and lead to
optimal outcomes such as adherence to treatment and subsequent viral load suppression. This has led to
improved retention rates and a significant reduction in patient attrition from 3% in 2022 to 1.2% in 2025.
Data analysis, visualization and dissemination to program and government leadership to inform decisionmaking regarding budgeting, target setting and prioritization of health facilities in need of urgent support.
Monthly data concordance checks between MOH Reporting platform (KHIS), IMPACT and the National
Data Warehouse to ensure data alignment and consistency in reporting. Currently, >95% of health facilities
have a variance within 0% to 5% in data reported in KHIS (government reporting platform) and IMPACT /
DATIM (PEPFAR Reporting platform).
Monthly outlier detection checks using Z-Scores, IQR and standard deviation to tease out outliers in reported
numbers and enable program officers perform targeted data audit of facility health records. Health facilities
with Z-Scores higher than three are prioritised for data quality audits.
•
•
•
Responsible for quarterly program performance reviews of progress towards achieving annual targets for
MER indicators.
Develop data analytics dashboards using Tableau and Apache Superset in the National Data Warehouse.
Train and mentor interns, subordinate staff, and healthcare providers in the use of the Health Information
System, KenyaEMR for patient management, drug dispensing, laboratory requests and monthly reporting.
Monitoring and Evaluation Officer | Samoei Community Development Programme
December 2019 - June 2022
•
•
•
Management of the Child Protection Information Management System (CPIMS) through regular on-the-job
training of data entry clerks, data entry, cleaning, and quarterly report generation. I supervised the entry of
10729 OVC records in less than a month and ensured compliance with donor requirements.
Routine data entry and reporting via IMPACT and DATIM for key MER Indicators
Developed CAPI data collection tools in KOBO as a solution to the inefficiencies of hardcopy tools used in
DQAs. This ensured accurate tracking of performance indicators and efficiency of collaboration with team
members due to real-time data uploads to the server. It also shortened the turnaround time of reports from
the organization’s outreach coordinators.
Monitoring, Evaluation & Learning Assistant | Heifer Project International
Eldoret | Jan 2016 – Jul 2017
•
•
•
•
•
Analysed program performance data using Microsoft Excel and STATA from Information Management
Systems reports of supported dairy cooperatives on milk collection volumes, stocks of dairy commodities
and volumes needed for procurement.
Participated in Mid and End-Term evaluations of the EADD Project and collaborated with the International
Livestock Research Institute (ILRI) and contracted consultancy firms tasked with the exercise to ensure
smooth running of data collection and reporting coordination.
Key person in the utilization of Kimetrica Information Management System for programmatic data entry
and reporting. I oversaw the entry of 59,462 unique beneficiary records, surpassing a target of 58,000
records.
Developed survey questionnaires using CS-Pro and analysed data using Stata & SPSS
Trained community facilitators to use the Kimetrica information management system for data collection and
upload tasks at household level.
Enumerator | International Livestock Research Institute (ILRI) | North & South Rift Valley
October 2015 - December 2015
•
•
•
Participated in a pretest of data collection tools and helped identify and troubleshoot issues with
questionnaires before data collection.
Sampled and interviewed dairy farmers in the North and South regions of Rift Valley Province
Maintained records of work, including hours, houses visited, surveys completed, and transport costs incurred
then used this to determine payments on a proof of work basis.