Photo by 1981 Digital on Unsplash
Engineering project
From survey data to documented datasets
Turn raw survey data into documented datasets with reusable cleaning procedures and variable definitions.
The project
Data-engineering work for a large scientific survey. The assignment covers cleaning strategy, preparation routines and documentation for data users, with additional work on questionnaires and PDF documents.
Engineering approach
A survey dataset comes with variable definitions and a preparation history. Connecting processing with documentation makes the data interpretable by other specialists. The diagram separates the statistical pipeline from PDF processing, which is a distinct document workflow.
Work delivered
Data-preparation and documentation procedures, complemented by codebook generation and PDF document processing.
My contribution
- Contribution to the data-cleaning and preparation strategy, followed by implementation of processing syntax
- Documentation of preparation operations and development of a codebook-generation procedure
- Support for preparing a survey template in LimeSurvey
- Development of a PDF document anonymisation procedure; use of SPSS, Stata, R and Nesstar
Functional overview
Scientific survey data preparation with cleaning scripts, transformation documentation and codebook generation. The work also includes a LimeSurvey template and a PDF anonymisation procedure, shown as separate tools.
LimeSurvey
R
Components and flows
- Survey data and cleaning syntax produce prepared datasets using SPSS, Stata and R
- Transformation documentation and codebook generation; use of Nesstar
- Preparation of a LimeSurvey template and development of a PDF anonymisation procedure
Related capabilities
- Data platforms and warehouses
- Business intelligence and reporting
- Intelligent document processing
- Systems documentation and architecture
Services by sector
Other projects
Discuss your project
A discussion of your project’s design, development and production deployment.