Statistician for sport science researchers: repeated-measures ANOVA, effect size (Cohen’s d), reliability (ICC) and power analysis. PhD theses and Q1/Q2.
Statistics for sport science that understands real training trials
PhD theses, Q1/Q2 articles and reviewer responses in sport science, sport sciences degrees, physical activity and performance. Modest-N training studies, mixed models for repeated measures, reliable change index, sociograms and team network analysis.
Sport science combines small samples, repeated measures and large individual variability. Each one has specific method.
You ran an 8-12-week protocol with experimental and control group. Sample is modest and t-tests don't convince the reviewer.
Training effects vary enormously between subjects. The group mean masks meaningful individual changes: you need RCI or individual trajectories.
Your study analyses interactions, cohesion or leadership in a sports team. Classical inferential statistics don't apply: you need network analysis.
2×3 designs (group × time), Greenhouse-Geisser correction, specific contrasts and mixed models when there's drop-out.
Cohen's d with 95% CI, partial eta-squared, clinical interpretation of magnitudes and why reviewers no longer accept p-values alone.
How many subjects changed reliably, not just whether the mean changed. Reporting responders vs non-responders.
Group cohesion, centrality, informal leadership, communities in sports teams and team comparison.
Realistic a priori sample size for your protocol, sample-size justification for reviewers and post-hoc analysis when requested.
Test-retest reliability (ICC), standard error of measurement, minimal detectable change and measurement invariance across populations (elite vs amateur).
No clock running on your tab. We agree on scope, timeline and a fixed price upfront: no inflated hours, no surprise invoice at the end. Before delivery, every analysis goes through a careful review on my side: I rerun the code, re-check the assumptions and review tables and figures line by line. That's the part I obsess over: that what you receive is ready to defend without errors surfacing in peer review. Bounded projects (training trial, validation, reviewer response) fit this model with no surprises.
Illustrative example: a network of relationships within a team with centrality measures to identify leaders and isolated players. Useful in studies of cohesion, leadership and sports group dynamics.
Free resources on the analyses common in physical-activity and performance studies.
Training study, questionnaire validation, network analysis, reviewer response… Fill the form and I respond within 24h with a tentative proposal.
Biostatistics and statistical consulting for health research · All services
Possible, but you need an analytical design that doesn't collapse with a modest sample: ANCOVA with baseline instead of crude change comparison, CIs alongside p-values, effect size with 95% CI, responder analysis and transparent reporting of limitations. Many JSCR or IJSPP articles have similar Ns.
With drop-out, mixed models are methodologically superior and current reviewers prefer them. They use all available information even when a subject didn't complete every timepoint. I can deliver both analyses so you see the difference.
Yes. I have worked with sociograms in sport (cohesion, centrality, informal leadership) using R (igraph, qgraph). It's an interesting methodological niche combining classical statistics with graphs.
Yes. Sport science theses are often multi-study. I cover the quantitative part of each: biomechanical descriptives, psychometric questionnaire analysis, training models and meta-analysis if needed.