Principal Statistician (RWE)

Purpose

The role of the Principal Statistician is to provide leadership and expertise in the statistical components of real-world evidence (RWE) to Veramed’s clients across a range of projects, clients and therapeutic areas. 

Key Responsibilities

The Principal Statistician (RWE) will be responsible for taking the lead on the development of statistical analysis plans, providing significant input into protocols and leading analyses of RWE studies that employ anonymised patient-level data derived predominantly from electronic health records (EHRs) and medical claims datasets. They will have a deep understanding of both the benefits and challenges of using RWE data, with a particular focus on how and whether causal conclusions can be drawn.

 The Principal Statistician (RWE) is expected to both lead work projects but also to work independently (including carrying out QC checks on their own deliverables and interim outputs). The Principal Statistician (RWE) will, additionally, be expected to review outputs from other colleagues, typically those more junior to them, and to provide advice on process improvements if any errors (whether one-off or systematic) are found in other peoples’ work.

Technical

• Determine and use the most appropriate statistical analysis techniques including hypothesis testing, logistic & linear regression, mixed models, pattern mixture models for handling missing data, formal statistical techniques for measuring missingness (MCAR, MNAR etc) and propensity score methods (matching, weighting)

• Conduct survival analysis such as Kaplan-Meier curves, Cox proportional hazards models

 • Conduct meta-analysis techniques including literature reviews and network meta-analysis.

 • Provide expertise gained from hands-on experience with EHRs, claims data and patient registries (US/European/Japanese etc)

• Provide skills in data privacy, small number rules, and healthcare system context

• Carry out data management activities such as: Large dataset handling: documentation of processes for cleaning, wrangling, merging, and imputing missing data

• Designing derived variables within the analytic dataset

General

 • Effectively participate in internal and client study team meetings including presenting study updates in client meetings

 • Share scientific, technical and practical knowledge within the team and with colleagues

 • Build effective collaborative working relationships with internal and client team members

• Seek opportunities to develop innovative ideas, sharing when appropriate

 • Lead creation of, and implement internal training programmes (including materials)

• Drive internal and client process improvement initiatives including determining and resolving any systematic cause of errors

 • Be aware of all the latest developments in primary field of expertise and disseminate as appropriate • Perform work in full compliance with applicable legislation, regulations, company policies, procedures and training

People Management

• Line management of statisticians and other technical staff. Accountable for overall performance of direct reports

• Provide coaching and mentoring of staff to achieve “excellence”.

• Direct employee career development and ensure line reports receive appropriate training to perform their day-to-day jobs 

• Interview and effectively on-board and integrate new staff members

 • Provide statistical technical leadership and coaching

Minimum Qualification Requirements

• Bachelor’s degree in Computer Science, Statistics, Mathematics, Physics or other subject with high statistical content

• Master’s degree in statistics (biostatistics preferred)

 • Minimum 8 years of relevant industry experience

• Excellent R programming skills and the ability to implement complex logic

Other Information/Additional Requirements

• Pharmaceutical industry experience

• Training or experience in epidemiological methods

• Comfortable creating complex analysis data sets derived from various data sources

 • Possess excellent skills in R or SAS programming; good appreciation of SQL programming

• Be able to employ a range of techniques to address the issue of confounding in causal or comparative RWE studies

• Familiar with FDA, EMA, MHRA guidelines and ENCEPP outputs • Be familiar with common data model structures

• Possess strong communication, time management and documentation skills

• Has a careful eye for outliers and errors