Mixed Methods Data Analysis with Stata and NVivo Training Course

Duration 10 days 18 modules · 65 contact hours
Level Intermediate Certificate on completion
Who attends Monitoring and Evaluation Officers, Evaluation Consultants and others
Fee from USD 2,200 KSh 190,000 for Kenyan organisations
Where 52 cities + online See dates by city
Next start 16 Nov 2026 Course code SD-ME-146

Before you join: Participants should understand basic monitoring and evaluation concepts, including indicators, evaluation questions, sampling and common data-collection methods.

Dates & prices

Two start dates a month in every city, and live online on weekdays or weekends. Fees are per participant; classroom fees include tuition, materials, lunch and refreshments, and the certificate.

Suggest a date or city

Showing the next six months. Later dates, other cities and private deliveries for your team are available on request.

Course overview

Development and humanitarian programmes produce survey datasets, routine monitoring records, interview transcripts, focus-group notes and field observations. Teams often analyse these sources separately, then struggle to explain why results differ, which findings are credible, and what action follows. Mixed methods analysis brings numerical trends and participant experience into one evidence process, supporting stronger evaluations, adaptive management decisions and donor reporting.

This course teaches participants to plan, analyse, integrate and report mixed methods evidence using Stata and NVivo. Participants prepare quantitative datasets, conduct descriptive and inferential analysis, test relationships, manage missing data and produce publication-ready tables and charts in Stata. They organise qualitative materials in NVivo, develop coding frameworks, assess coding consistency, run matrix queries and identify themes, patterns and negative cases. The course then connects both evidence streams through joint displays, triangulation protocols and integrated conclusions.

Instruction combines short technical briefings with realistic monitoring and evaluation cases drawn from health, livelihoods, education, protection and humanitarian response programmes. Participants work with structured datasets and qualitative source materials from the first week, progressively building an integrated analysis. They leave with a mixed methods analysis pack containing a Stata do-file, NVivo coding framework, quantitative outputs, qualitative findings matrix, joint display and evidence-based reporting plan.

The course is suited to M&E professionals, researchers, programme analysts and evaluation teams who need to produce defensible findings from both quantitative and qualitative evidence. It is particularly relevant where programme decisions depend on understanding both measured results and the reasons behind them.

What you will be able to do

  • Design a mixed methods analysis plan linked to evaluation questions and indicators
  • Prepare, document and analyse monitoring and survey datasets using Stata
  • Produce descriptive statistics, cross-tabulations, regression models and graphical outputs in Stata
  • Develop a qualitative coding framework and code source materials in NVivo
  • Apply thematic analysis, framework analysis and negative-case analysis to qualitative evidence
  • Assess qualitative coding consistency using codebook definitions and intercoder comparison procedures
  • Integrate quantitative and qualitative findings through triangulation matrices and joint displays
  • Present a complete mixed methods evaluation analysis with defensible conclusions and recommendations

Benefits of attending

For you

  • Produce reproducible Stata analyses using documented do-files
  • Build defensible NVivo coding structures for evaluation evidence
  • Interpret conflicting quantitative and qualitative findings with clear decision rules
  • Create joint displays that communicate integrated evidence to non-technical stakeholders
  • Prepare a reusable workflow for mixed methods evaluation assignments

For your organisation

  • Improves consistency between survey findings, interview evidence and programme recommendations
  • Reduces reliance on undocumented spreadsheet analysis and ad hoc qualitative summaries
  • Strengthens audit trails for donor-funded evaluations and learning reviews
  • Produces clearer evidence for programme adaptation, targeting and resource allocation
  • Builds internal capacity to analyse mixed methods evidence without fragmented workflows

Course modules

18 modules over 10 days

Participants can select an appropriate mixed methods design for a defined evaluation problem.

  • Explanatory, exploratory and convergent mixed methods research designs
  • Evaluation questions linked to indicators, experience and causal assumptions
  • Theory of change assumptions tested through complementary evidence streams
  • OECD DAC criteria translated into quantitative and qualitative questions
  • Unit of analysis, comparison groups and respondent categories
  • Priority information needs for programme adaptation and accountability

Participants can prepare an integrated analysis plan and manage evidence responsibly.

  • Analysis plans specifying questions, data sources, methods and outputs
  • Convergent design sequencing, priority and points of integration
  • Sampling frames for surveys, interviews, focus groups and observations
  • Informed consent, confidentiality and secure handling of sensitive data
  • Unique identifiers connecting respondent records across data sources
  • Metadata, version control and audit trails for evaluation files

Participants can organise a reproducible Stata project and execute basic commands.

  • Stata interface, command syntax, help files and working directories
  • Project folders separating raw data, outputs, syntax and documentation
  • Do-files recording repeatable data management and analysis commands
  • Importing Excel, CSV and delimited files into Stata
  • Variable labels, value labels and formats supporting readable outputs
  • Log files documenting commands, results and analytical decisions

Participants can clean, recode and document evaluation datasets in Stata.

  • Data quality checks for duplicates, invalid values and inconsistent records
  • Missing-data patterns examined with tabulations and summary statistics
  • Recoding categorical responses using generate, replace and recode commands
  • Constructing binary indicators, index scores and disaggregated variables
  • Merging household, individual and facility datasets using unique identifiers
  • Reshaping wide and long datasets for repeated-measures analysis

Participants can calculate and interpret core monitoring and evaluation statistics.

  • Frequencies, proportions, means, medians and dispersion measures
  • Disaggregation by sex, age, disability, location and programme group
  • Cross-tabulations with row percentages, column percentages and chi-square tests
  • Confidence intervals for proportions, means and estimated differences
  • Weighted estimates and survey design considerations for household surveys
  • Indicator tables aligned with definitions, denominators and reporting periods

Participants can test group differences and examine relationships between variables.

  • Null hypotheses, significance levels, p-values and confidence intervals
  • T-tests comparing mean outcomes between programme participant groups
  • Chi-square tests assessing associations between categorical variables
  • Correlation coefficients interpreted with direction, strength and limitations
  • Non-parametric tests for skewed distributions and ordinal responses
  • Effect sizes reported alongside statistical significance and sample sizes

Participants can specify and interpret basic regression models for evaluation data.

  • Linear regression models for continuous outcome indicators
  • Logistic regression models for binary programme outcomes
  • Independent variables selected from theory of change assumptions
  • Confounding variables, interaction terms and model specification choices
  • Regression diagnostics using residuals, multicollinearity and influential observations
  • Predicted values and marginal effects for stakeholder interpretation

Participants can communicate quantitative findings accurately through clear outputs.

  • Bar charts, histograms, box plots and scatterplots for evaluation data
  • Trend graphs comparing baseline, midline and endline measurements
  • Table design showing denominators, disaggregation and confidence intervals
  • Exporting formatted results from Stata into Word and Excel
  • Analytical narratives distinguishing findings, interpretation and limitations
  • Data visualisation choices matched to evaluation questions and audiences

Participants can create an organised NVivo project for qualitative evaluation evidence.

  • NVivo project structure for interviews, focus groups and documents
  • Importing Word, PDF, spreadsheet, audio and transcript source files
  • Source classifications recording respondent roles, sites and demographic attributes
  • Case nodes linking individual participants to descriptive attributes
  • File naming conventions supporting traceability and secure project management
  • Memos recording analytical decisions, reflections and emerging questions

Participants can build a transparent coding framework from evaluation questions and source data.

  • Deductive codes derived from evaluation questions and theory of change
  • Inductive codes generated from repeated concepts within source material
  • Codebook definitions specifying inclusion, exclusion and example excerpts
  • Parent and child nodes organising themes at different analytical levels
  • Descriptive coding, process coding and values coding distinctions
  • Pilot coding used to refine ambiguous categories and definitions

Participants can code qualitative materials systematically and retrieve relevant evidence.

  • Applying coded references to text passages and selected source extracts
  • In-vivo coding preserving participant language for salient concepts
  • Coding stripes and highlights reviewing overlap among applied codes
  • Annotations distinguishing source context from analyst interpretation
  • Node summaries consolidating coded evidence and analytical observations
  • Framework matrices comparing cases against themes and evaluation questions

Participants can develop credible themes from coded qualitative evidence.

  • Thematic analysis stages from familiarisation through theme definition
  • Framework analysis matrices comparing cases, categories and programme locations
  • Pattern coding grouping first-cycle codes into explanatory categories
  • Negative-case analysis testing themes against contradictory participant accounts
  • Temporal analysis tracing reported changes during programme implementation
  • Theme narratives supported by selected quotations and contextual evidence

Participants can assess and document the credibility of qualitative findings.

  • Credibility, dependability, confirmability and transferability in qualitative analysis
  • Intercoder comparison procedures identifying agreement and coding differences
  • Codebook calibration meetings resolving definitions and boundary decisions
  • Reflexive memos documenting analyst assumptions and positionality
  • Data saturation assessed through recurring patterns and information adequacy
  • Audit trails linking raw sources, codes, themes and conclusions

Participants can use NVivo queries to compare themes across respondent groups and locations.

  • Text search queries locating repeated terms and participant language
  • Coding queries identifying co-occurring themes within selected source materials
  • Matrix coding queries comparing themes by sex, location and respondent type
  • Compound queries combining coded themes with case classification attributes
  • Charts and hierarchy visualisations examining coding distribution patterns
  • Query results interpreted with source context and participant representation

Participants can combine findings from both evidence streams into integrated interpretations.

  • Triangulation protocol comparing convergence, complementarity and disagreement
  • Joint displays aligning numerical results with themes and quotations
  • Meta-inferences connecting integrated findings to evaluation questions
  • Discrepant findings investigated through sampling, measurement and contextual explanations
  • Mixed methods matrices linking indicators, themes, conclusions and recommendations
  • Evidence weighting based on quality, relevance and methodological limitations

Participants can assess plausible programme contribution using integrated evidence.

  • Contribution analysis steps applied to programme theory and observed results
  • Causal claims distinguished from association, attribution and plausible contribution
  • Alternative explanations identified through stakeholder accounts and contextual data
  • Process-tracing tests examining evidence for causal mechanisms
  • Rival hypotheses assessed against quantitative patterns and qualitative accounts
  • Causal narratives expressing confidence, uncertainty and evidence limitations

Participants can write decision-focused mixed methods findings for technical and management audiences.

  • Finding statements combining statistical results, themes and contextual explanation
  • Joint display captions explaining convergence, divergence and implications
  • Recommendation chains linking evidence, decisions, owners and timeframes
  • Limitations sections covering sampling, bias, missing data and transferability
  • Evaluation report structures aligned with OECD DAC criteria
  • Management presentations using concise charts, quotations and action messages

Participants can build, review and present a complete mixed methods evaluation analysis using Stata and NVivo.

  • Complete analysis plan linked to evaluation questions and evidence sources
  • Stata do-file producing documented quantitative findings and visual outputs
  • NVivo codebook and thematic matrix supporting qualitative conclusions
  • Joint display integrating convergent, complementary and discrepant findings
  • Peer review against audit trail, validity and reporting criteria
  • Presentation of conclusions, recommendations and implementation implications

Exercises and examples are adapted to each cohort's sectors and roles.

What you take back to work

  1. Mixed methods evaluation analysis plan template
  2. Stata do-file and data-cleaning checklist
  3. Qualitative codebook and coding consistency protocol
  4. NVivo framework matrix template
  5. Triangulation protocol and joint display model
  6. Mixed methods findings and recommendations report outline

Who should attend

  • Monitoring and Evaluation Officers — need to analyse indicators alongside participant evidence
  • Evaluation Consultants — need defensible methods for mixed methods assignments
  • Programme Managers — need integrated findings for adaptation and management decisions
  • Research Officers — need practical Stata and NVivo analytical workflows
  • Data Analysts — need to add qualitative evidence to quantitative reporting
  • Humanitarian Assessment Specialists — need to combine assessment data with field narratives

Skills and tools covered

Mixed methods designStata data analysisNVivo qualitative codingThematic analysisEvidence triangulationEvaluation reporting

Tools and standards

Stata, NVivo, OECD DAC Criteria, Contribution Analysis

How the course runs

Training methodology

The course uses short instructor briefings, software demonstrations, guided case analysis, group interpretation tasks and individual application planning. Participants work with realistic monitoring datasets, interview transcripts, focus-group extracts and programme documents. Stata sessions use do-files to document data preparation and analysis steps. NVivo sessions develop codebooks, coding structures, queries and evidence matrices. Facilitated review sessions focus on interpreting outputs, testing alternative explanations and translating integrated findings into evaluation conclusions and management recommendations.

Requirements and prerequisites

Participants should understand basic monitoring and evaluation concepts, including indicators, evaluation questions, sampling and common data-collection methods. Experience working with spreadsheets, survey data, interview notes or programme reports is useful. Participants should be comfortable using a computer, managing files and interpreting simple percentages and charts. Prior use of Stata or NVivo is not required; the course introduces the working environment and core commands in both applications. Advanced statistics, programming, qualitative research degrees and prior evaluation consultancy experience are not required.

A typical training day

08:30 – 10:30First session
10:30 – 10:45Refreshment break
10:45 – 12:30Second session
12:30 – 13:30Lunch and networking
13:30 – 15:00Third session
15:00 – 15:15Refreshment break
15:15 – 16:30Workshop and daily review

Live online deliveries follow the same structure in East Africa Time, with shorter screen blocks and longer breaks.

What the fee includes

  • Instruction by a practitioner facilitator
  • Full course workbook and materials
  • Exercise files, templates and case studies
  • Refreshments and lunch on classroom deliveries
  • Certificate of completion
  • Post-course application plan

Frequently asked questions

You should understand basic monitoring and evaluation concepts and be comfortable working with spreadsheets or structured data. Prior Stata, NVivo, programming or advanced statistical experience is not required.

Bring a laptop suitable for running Stata and NVivo, together with any non-sensitive example indicators, survey instruments or interview guides you wish to review. Confirm software access and version arrangements with the course coordinator before the course.

The course is designed for M&E officers, evaluation consultants, programme managers, researchers and data analysts working in development or humanitarian programmes. It is most useful for professionals who need to combine survey findings with interviews, focus groups or field observations.

Stata-only courses focus on quantitative data management and statistical analysis, while NVivo-only courses focus on qualitative coding and retrieval. This course teaches both tools and, critically, the methods used to integrate their findings into one evaluation argument.

Participants can use the analysis plan, codebook, do-file structure and joint display templates for current evaluations, assessments and learning reviews. The course also provides practical approaches for documenting analytical decisions and presenting findings to programme decision-makers.

The first part establishes mixed methods design, data governance and practical Stata analysis, while participants begin producing structured outputs. The second part develops NVivo coding, qualitative analysis, evidence integration, reporting and a final capstone analysis presentation.

Questions about this course?

Ask about dates, fees, group bookings or running it for your team. Our training team replies by email.

Ask on WhatsApp info@skillsetdevelopment.com

More courses in Monitoring & Evaluation

Monitoring & Evaluation M&E Data Analysis with SPSS and Stata Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation MEAL Data Management Training Course 5 days · from USD 1,100 · next 16 Nov Monitoring & Evaluation MEAL Data Quality Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation Machine Learning for Monitoring and Evaluation Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation Mobile Data Collection Using CommCare Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation Mobile Data Collection Using ODK and KoboToolbox Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation Mobile Data Collection Using SurveyCTO Training Course 10 days · from USD 2,200 · next 16 Nov Monitoring & Evaluation Mobile Data Collection for Monitoring and Evaluation Training Course 10 days · from USD 2,200 · next 16 Nov