Our research process
At Talamo, we support individuals with Special Educational Needs (SEN) by providing a reliable, accurate, and validated tool for dyslexia testing and cognitive profiling.
Designed with best-in-class methods, our tool is trusted by candidates, schools, and parents.
Process
Our stages of research
1
Creating the test material
We start by collaborating with globally renowned publishers and psychometrics experts to develop our test content. This stage aims to replicate as much of the depth of a full diagnostic assessment as possible in a more concise format. Through this collaborative process, we developed a comprehensive test battery that accurately measures various cognitive domains, including verbal, visual, and non-verbal reasoning, phonological processing, working memory, processing speed, reading, and spelling. We purposely created more content than we needed to select the most effective content for each area.
2
User testing the material
This phase involves conducting thorough user experience tests to assess the clarity, appropriateness, and difficulty of each test. We split our user testing into stages to make improvements between each session. Feedback gathered during this phase informs the refinement or removal of test content ahead of more extensive data collection, ensuring that the foundation for our assessments is solid and user-friendly.
3
Evaluating each tests sensitivity to dyslexia
A pivotal element of our validation process is the direct comparison between dyslexic and non-dyslexic groups, using a sample of both groups. This stage involves partnerships with specialist dyslexia schools (to take formally diagnosed dyslexic pupils) and collaboration with SENCos to accurately define our ‘non-dyslexic’ control group. Focusing on students aged 12-13 helps mitigate age-related variability and provides a stable basis for our analysis.
4
Creating the model
After completing Stage 3, we administered a large battery of tests, which showed statistically significant differences in differentiating between dyslexic and non-dyslexic individuals. The next stage was to build a model that would use these to accurately identify dyslexia in a new cohort. We experimented with multiple statistical methods but settled on a Logistic Regression as the most effective. With this model in place, we then used Recursive Feature Elimination to identify the tests which were most effective at spotting dyslexia (also taking into account how long the test is). We built multiple models based on this approach and then chose the final test battery based on the model's sensitivity and specificity score.
5
Age standardising
Once we had our test battery locked in and the model in place, we then began age standardising to ensure our tool's applicability across different age groups. We collected extensive data for ages 7-16 to achieve statistically valid age standardisation. By collecting data across age groups, we can adjust the difficulty of our tests and interpret results based on age. In this phase, we derive standard scores, z-scores, and percentile ranges for each age group on every scale. This precision is crucial for identifying underlying issues and providing targeted recommendations. This is where the bulk of our 1400 participants were tested (our initial standardisation).
Considerations
Care when collecting data
Our commitment to creating a diverse and representative dataset is evident in our collaborative efforts with schools across the UK, which ensure optimal testing conditions and maximise engagement. We ensured a demographically accurate spread and attended each school numerous times to oversee the collection.
What next?
Our dedication to refinement and innovation is ongoing. With each test, piece of feedback, and a new piece of research, we continually enhance the reliability and effectiveness of our tool. In June 2025, we undertook new standardization work to keep our test up-to-date with the latest definition of dyslexia, which has now been incorporated into the school's platform.
Currently, we are working on a new agentic system that will boost our accuracy further and push our system to 'think' more like a human assessor. We are also currently working on assessments for Executive Functioning, Dyscalculia, and Exam Access Arrangements. These tests are aimed to be ready for public consumption at the beginning of the 2026/27 academic year.
At Talamo, we're committed to supporting Special Education Needs through continuous innovation, research, and an in-depth understanding of the communities we serve. In other words, the work never stops, and we will continue to keep you updated as new material is released.
Latest from the team
All our latest thoughts, podcasts and updates.
See how Talamo supports families and schools
Empowering schools & SENCOs identify and support SpLDs
Talamo is used in over 350+ UK schools to screen entire classes, identify learners early and generate evidence-based reports.
Giving parents clarity and confidence on their child’s learning profile
Talamo can be used by parents to screen their child at home and get a personalised report with clear next steps - no specialist needed.
