Design a Mid-Term Evaluation
Plan a mid-term evaluation to check program progress, relevance, and early outcomes.
Draft: Design a Mid-Term Evaluation
Fill In Your Details (6 Blanks)
Add your information to get a tailored prompt. You can also use it as is.
Sector and Donor Context (Optional)
Your Prompt (With Your Details)
This is the complete prompt, ready to copy and paste.
You are a senior MEAL specialist. Design a comprehensive mid-term evaluation for your program to assess progress toward your intended outcomes, relevance, and early outcomes. The evaluation must be aligned with your program's theory of change.
Evaluation Design Requirements:
- Evaluation Questions: Develop clear, focused evaluation questions that address program implementation, relevance, effectiveness, and early outcomes. Ensure questions are specific and measurable.
- Methodology: Propose a mixed-methods approach (quantitative and qualitative) for data collection and analysis. Specify the evaluation methods to be used (e.g., surveys, key informant interviews, focus group discussions, document review, administrative data analysis). Include feasibility checks for all proposed methods, considering resources, time, and ethical considerations.
- Data Sources: Identify specific data sources for each evaluation question. Examples include surveys, administrative records, program monitoring data, beneficiary feedback, key informant interviews, focus group discussions, case studies, observation reports.
- Data Collection Plan: Detail the plan for collecting data, including sampling strategies, tools to be used, and data management procedures.
- Disaggregation: Ensure that data collection and analysis plans consistently incorporate relevant disaggregation variables (e.g., gender, age, geography) to understand differential impacts and experiences.
- Stakeholder Engagement: Outline a robust stakeholder engagement plan. Identify key stakeholders, including community leaders, program beneficiaries, program staff, local partners, government officials, and describe how their input will be sought and integrated throughout the evaluation process, from design to dissemination.
- Analysis Approach: Describe the approach for analyzing both quantitative and qualitative data, including statistical methods for quantitative data and thematic analysis or content analysis for qualitative data. Specify how findings will be triangulated.
- Timeline: Provide a detailed timeline with key milestones for the evaluation, from inception to final reporting.
- Reporting Structure: Define the structure of the final evaluation report, including an executive summary, introduction, methodology, findings, conclusions, recommendations, and annexes.
- Risk Mitigation: Identify potential risks to the evaluation process and propose strategies to mitigate them.
- Expected Outcomes: Briefly describe the expected outcomes of the evaluation, such as actionable recommendations for program improvement, evidence for accountability, and lessons learned for future programming.
Output Format:
Present the evaluation design in a structured format, clearly addressing each of the requirements listed above. Use clear and concise language.
Check: Score It with the Evaluation Report Scoring Rubric
The Review Prompt
Paste the draft at the bottom of this prompt and run it. It scores each criterion from 1 to 5 and says why.
You are an expert M&E evaluation quality assessor. Score the evaluation report I will provide using the rubric below.
SCORING RUBRIC - Evaluation Report Scoring Score each dimension 1-5 using these criteria:
DIMENSION 1: Methodology Rigor
- Score 5: Design stated with rationale for choosing it. Sampling section documents sample size, selection method, and representativeness. Both quantitative and qualitative analysis approaches described in replicable detail. Limitations acknowledged with discussion of implications for interpretation.
- Score 4: Design described with rationale (may be brief). Sampling documented but representativeness assumed. Analysis described. Limitations listed but their impact not discussed.
- Score 3: Design named but not described in usable detail. Sample size stated but selection method not explained. Analysis approach mentioned but not replicable from the description alone. At least one limitation acknowledged but without implications.
- Score 2: Methodology section brief or generic. Sample size and selection not justified. Analysis described in one sentence or less. Limitations section absent, OR limitations listed without their effect on findings.
- Score 1: No methodology section.
DIMENSION 2: Evidence Quality and Triangulation
- Score 5: All major findings supported by at least two independent sources. Quantitative and qualitative evidence integrated within each finding (not in separate silos). Contradictory evidence noted and explained. Each finding traceable to specific data.
- Score 4: At least 80 percent of findings have triangulation. The remainder rely on a single source with the limitation acknowledged. Both evidence types present with some integration.
- Score 3: Half or more findings have triangulation. Single-source reliance is common. Quantitative and qualitative data both present but largely reported in parallel rather than integrated.
- Score 2: Less than half of findings have triangulation, OR quantitative and qualitative are presented in fully separate sections without integration.
- Score 1: No triangulation. Findings appear to reflect evaluator opinion without documented evidence.
DIMENSION 3: Findings Presentation
- Score 5: Findings organized by evaluation question. Every finding includes magnitude and direction of change. Disaggregated by sex, age, location, or other relevant variables where data allow. Negative and unexpected findings receive equal space as positive ones.
- Score 4: Findings organized clearly (may follow program components rather than evaluation questions). At least 80 percent of findings include direction of change. Some disaggregation present. Negative findings reported but may receive less space.
- Score 3: Findings organized but not consistently aligned to evaluation questions. Half or more include magnitude. Disaggregation attempted for at least one variable. Negative findings mentioned but receive clearly less emphasis than positive ones.
- Score 2: Findings organized by data source or as a chronological narrative. Magnitude unclear for half or more findings. Disaggregation absent or limited. Negative findings minimized.
- Score 1: Qualitative narrative with no structure. No disaggregation. Reads as a success story.
DIMENSION 4: Conclusions and Recommendations
- Score 5: Every conclusion cites the finding(s) it draws on and does not exceed what the evidence supports. Every recommendation specifies action, responsible party, and timeframe. Recommendations address root causes. Total recommendations between 5 and 12. Priority recommendations distinguished from secondary.
- Score 4: Every conclusion linked to findings, though some links may be implied. At least 80 percent of recommendations are specific. Responsible parties identified for at least 80 percent.
- Score 3: Conclusions consistent with findings but links are not explicitly stated. Half or more recommendations are specific; the remainder remain general. Half or more have responsible parties named. Total recommendations between 3 and 15.
- Score 2: One or more conclusions go beyond evidence or contradict findings, OR half or more recommendations are generic, OR responsible parties not specified for half or more, OR total recommendations outside reasonable range (fewer than 3 or more than 15).
- Score 1: Conclusions contradict or ignore findings. Recommendations not actionable. No link between findings, conclusions, and recommendations.
DIMENSION 5: Ethical and Inclusive Reporting
- Score 5: Community members participated in findings validation beyond data collection. Report explicitly addresses power dynamics. Data anonymized for every potentially identifiable data point. Key conclusions communicated back to affected communities with documentation.
- Score 4: Community participation beyond data collection evidenced. Anonymization applied. Findings shared with implementing partners.
- Score 3: Some evidence of participant engagement beyond data collection. Anonymization applied for at least 80 percent of potentially identifiable data points but inconsistently. Limited documentation of inclusive process.
- Score 2: Ethical protections mentioned but inconsistently applied. Half or more of identifiable data points are not anonymized (direct quotes attributable to named individuals or locations specific enough to identify respondents). No findings validation with data providers.
- Score 1: No ethical protections documented. Individual data potentially identifiable throughout. No evidence of inclusive process or community feedback loop.
ADDITIONAL TASK: List every recommendation that lacks a named responsible party or specific action. For any that is generic or not actionable, provide a rewritten version that is specific.
OUTPUT FORMAT:
| Dimension | Score (1-5) | Evidence from Report | Priority Action |
|---|---|---|---|
| Methodology Rigor | |||
| Evidence and Triangulation | |||
| Findings Presentation | |||
| Conclusions and Recommendations | |||
| Ethical and Inclusive Reporting |
Total: X/25 Band: Strong (22-25) / Adequate (17-21) / Needs Revision (11-16) / Substantial Revision (5-10) Single Most Important Revision: [One specific sentence]
Then list all non-actionable recommendations with rewritten versions.
EVALUATION REPORT TO SCORE: [Paste your evaluation report or key sections here]
Fix: Revise What Scored Low
The Revise Prompt
Paste the draft and its scores at the bottom of this prompt. It revises the parts that scored below 4.
You are an expert M&E evaluation quality assessor. Review the draft evaluation report I will provide and fix every problem that falls below the Good (4) threshold on the Evaluation Report Scoring rubric.
WHAT TO LOOK FOR AND FIX:
Methodology problems:
- Missing design rationale - add one sentence explaining why this design was chosen
- Undocumented sampling - add a sampling section with sample size, selection method, and representativeness
- Unacknowledged limitations - add a limitations section with at least three constraints and their implications for interpretation
Evidence and triangulation problems:
- Findings with only one source - note which sources were cross-referenced, or flag as "single-source finding"
- Quantitative and qualitative evidence in separate chapters - integrate within each finding
- Contradictory evidence absent - explicitly address where data sources agreed and diverged
Findings presentation problems:
- Findings organized by data source - reorganize by evaluation question
- Magnitude of change unstated - add percentages, counts, or effect sizes
- Disaggregation absent - note where disaggregated data exist and add them; where they do not, note it as a data gap
- Negative findings absent or buried - give equal paragraph length to what did not work
Conclusions and recommendations problems:
- Conclusions that go beyond the evidence - rewrite to match what the data actually show
- Generic recommendations (e.g., "strengthen M&E capacity") - rewrite as specific actions with responsible parties and timeframes
- More than 12 recommendations - consolidate; prioritize top 5-8
- Recommendations without a named responsible party - add one
Ethical problems:
- Direct quotes attributable to identifiable individuals - anonymize with role/location only
- No mention of community findings validation - add documentation of how and when findings were shared
OUTPUT FORMAT:
- List every problem found by dimension, with original text and corrected version.
- Provide the complete revised sections (methodology, findings, and conclusions chapters) incorporating all corrections.
DRAFT EVALUATION REPORT TO REVISE: [Paste your draft report here]