Sample sizes
Welcome to the course “Sample sizes”. This is a series of two sessions for professionals interested in learning more about choosing samples for their surveys. It is highly recommended that you watch the recordings of both webinars in their consecutive order so as to benefit from the complete course.
These are free training sessions provided by the ActivityInfo team.
Are these sessions for me?
- Are you an M&E practitioner responsible for designing surveys and data collection tools for your programmes?
- Do you wish to understand better how to choose a sample for your surveys and what to keep in mind while doing that?
- Do you want to experiment with a sample size calculator and other types of calculators?
Then, get started with these sessions!
A guide to choosing sample sizes for M&E practitioners
During this session, we focus on choosing samples for surveys.
In summary, we explore:
- Baseline surveys
- Mid term/final evaluations
- Oversampling for groups of specific interest
- Taking into consideration the costs of stratified and cluster sampling
- Understanding sampling and non-sampling error
- Introduction to using confidence intervals in the analysis
Complex survey samples in M&E and adapting sampling methods to meet field needs
During this session, we look at more complex survey samples in Monitoring and Evaluation and how sampling methods can be adapted to meet the needs and the reality of the field.
In summary, we explore:
- Cluster samples
- Stratified samples
- Multi-stage samples
- Non-sampling errors: Selection bias, Convenience sampling, Refusals
- Sampling in challenging environments: Without a well known population, Techniques for randomization (random walks, systematic sampling, etc.)
Sample size calculator for needs assessments and KAP surveys
This calculator will help you find an appropriate sample size for a needs assessment survey, a KAP survey, or any other kind of survey intended to provide a "snapshot" of a population at a given point in time.
Sample size for baseline and endline surveys
Use this calculator when you are planning two independent samples of the same population, before and after an intervention.
Calculate design effect from cluster surveys
This calculator provides a simplified estimate of ICCs for equal-sized clusters that can provide a quick indication of the ICC from survey results.