Python Data Scientist - Continuous Time-Series Cross-Correlation & Statistics (7-day project)

We are seeking an advanced Python data scientist or statistical engineer for an accelerated, 1-week data analysis contract. The project involves processing a continuous tracking dataset for a Human-Computer Interaction (HCI) study, evaluating temporal dynamics, lag, and alignment between 28 “Observers” (split between a Test group and a Control group) and 6 unique “Target” trials. Data is sampled continuously at 1000 millisecond intervals). A total of 168 separate dyadic time-series analyses must be executed to map observer tracking alignment and calculate personalized temporal cognitive lag. 1 - MILESTONES The project is structured into two strict milestones over a 7-day period: (a) Milestone 1 (Days 1–4): Complete all data processing, calculate baseline zero-lag Pearson correlations, and execute time-lagged cross-correlation matrices bounded within a uniform window of -5 to +10 seconds. Crucially, calculations must be run iteratively at every single 1000ms increment within this window (yielding exactly 16 distinct correlation coefficients per trial). From these 16 steps, you will extract peak values and perform group-level comparative inferential modeling (e.g., LMM or Mixed-Design ANOVA). (b) Milestone 2 (Days 5–7): Delivery of a fully documented, step-by-step Jupyter Notebook (.ipynb) showing code cells alongside execution readouts, alongside a mirror production copy automatically exported as a standard Python script (.py). A more detailed project brief is attached. 2 - FREELANCER REQUIREMENTS / PROFILE We are seeking an individual with deep expertise in time-series based data and academic statistics. When applying, you must explicitly provide the following: (a) Time-Series & Cross-Correlation Portfolio Evidence (required): Please provide short code snippets or case studies demonstrating that you have successfully implemented cross-correlation coefficients and step-by-step lag modelling in Python. Applications without explicit proof of working with time-shifted cross-correlations will not be reviewed. (b) Advanced Academic Statistics Background (required): Evidence of work handling nested trial designs, signal synchronization, or mixed-effects statistical data analysis in Python before. (c) APA Style Familiarity (preferred): Please note if you have experience formatting statistical tables and data summaries in APA formatting. Candidates with strong APA formatting skills will be prioritised for a potential follow-up project to assist with the write up the final results section for journal submission. **Applicants who do not explicitly address the 3 candidate requirements above will not be considered or contacted for this project.**