Applied Statistician Experimental Design & Time-Series Modeling
Posted 1 day ago by NetworkPedia LLC
Negotiable
Undetermined
Remote
Remote or California
Summary: The Applied Statistician will lead experimental design and statistical validation efforts for a utilities client developing an asset monitoring solution using advanced sensor technology. This role involves designing field experiments, establishing data frameworks, and developing statistical models to predict structural degradation in utility distribution poles. The position is remote with an option for on-site work in the Bay Area and is expected to last for 9 months. The candidate will play a crucial role in ensuring the project's success through rigorous statistical analysis and insights generation.
Key Responsibilities:
- Design statistically rigorous field experiments for sensor deployment
- Define success criteria, sample size, and statistical power
- Establish control vs. treatment conditions
- Identify confounding variables (wind, soil, vibration, temperature, etc.)
- Recommend experiment duration and baseline requirements
- Define sampling frequency and measurement resolution
- Establish data quality standards and completeness thresholds
- Recommend methods for handling missing/noisy data
- Develop metrics from sensor data (variance, drift, frequency signals)
- Build statistical models (regression, time-series, etc.)
- Perform hypothesis testing
- Evaluate model performance (sensitivity, specificity, false positives)
- Define statistical thresholds for signal validation
- Assess predictive reliability
- Identify limitations and uncertainties
- Provide recommendations for product development decisions
- Experimental Design Plan
- Data Collection Framework
- Statistical Analysis Plan
- Interim Analysis Reports
- Final Experiment Analysis Report
Key Skills:
- Advanced degree in Statistics, Data Science, Engineering, or related field
- Strong experience in experimental design (real-world/sensor data preferred)
- Expertise in statistical modeling and time-series analysis
- Ability to translate analysis into business decisions
- Experience with IoT / sensor data / infrastructure monitoring
- Background in field experiments or engineering validation
- Experience with environmental or physical system data
- Mandatory Tool: Python
- Nice to Have: R
Salary (Rate): £85/hr
City: undetermined
Country: undetermined
Working Arrangements: remote
IR35 Status: undetermined
Seniority Level: undetermined
Industry: Other
Job Title:
Applied Statistician Experimental Design & Time-Series Modeling / Lead Applied Statistician IoT Sensor Experimentation (Utility Infrastructure)
Client:Utilities Client
Duration:9 Months
Work Hours:20 30 hours/week
Work Location:Remote (Option to work onsite if local to Bay Area)
Job Description: Project Background:Our Utilities client is developing an asset monitoring solution using advanced sensor technology to detect early structural degradation in utility distribution poles. The project is currently in the Accelerate phase, focused on validating key technical assumptions required for product development and commercialization.
The team will deploy multiple sensor types across targeted poles to evaluate whether measurable changes in pole lean dynamics can predict structural degradation.
The Applied Statistician will play a key role across the first three project phases, leading experimental design and supporting statistical validation efforts.
Key Responsibilities: 1. Experimental Design- Design statistically rigorous field experiments for sensor deployment
- Define success criteria, sample size, and statistical power
- Establish control vs. treatment conditions
- Identify confounding variables (wind, soil, vibration, temperature, etc.)
- Recommend experiment duration and baseline requirements
- Define sampling frequency and measurement resolution
- Establish data quality standards and completeness thresholds
- Recommend methods for handling missing/noisy data
- Develop metrics from sensor data (variance, drift, frequency signals)
- Build statistical models (regression, time-series, etc.)
- Perform hypothesis testing
- Evaluate model performance (sensitivity, specificity, false positives)
- Define statistical thresholds for signal validation
- Assess predictive reliability
- Identify limitations and uncertainties
- Provide recommendations for product development decisions
- Experimental Design Plan
- Data Collection Framework
- Statistical Analysis Plan
- Interim Analysis Reports
- Final Experiment Analysis Report
- Advanced degree in Statistics, Data Science, Engineering, or related field
- Strong experience in experimental design (real-world/sensor data preferred)
- Expertise in statistical modeling and time-series analysis
- Ability to translate analysis into business decisions
- Experience with IoT / sensor data / infrastructure monitoring
- Background in field experiments or engineering validation
- Experience with environmental or physical system data
- Mandatory Tool: Python
- Nice to Have: R
- Statistically valid experiment design and execution
- High-quality data collection enabling signal detection
- Clear validation of hypothesis (predictive signal vs degradation)
- Actionable recommendation for product development