The demand for healthier food consumption has increased significantly in recent years. For many households, supermarket retailers are still the primary source for their food purchases. By shaping the environment in which purchasing decisions are made, retailers play a crucial role in the forming of consumers’ food purchasing behavior and habits. Recent literature has investigated how the healthiness of online grocery purchases differs from offline (in-store) purchases (Chintala et al, 2024; Harris-Lagoudakis, 2022; Huyghe et al, 2017). While online grocerybaskets tend to be healthier compared to offline baskets, it is unclear if the adoption of OGS contributes to healthier consumption or if it results in a redistribution across channels, where consumers simply shift the more healthy purchases online and purchase unhealthy products mainly offline. More research is needed that examines how households alternate between online and offline shopping trips and how they allocate their purchases across both channels. As such, the central question in this project is:
How does the transition to hybrid grocery shopping affect the healthiness of food purchases across both online and offline grocery channels?
The formal analysis examines how the healthiness of households’ grocery baskets changes once they start shopping in online channels in addition to their in-store purchases. We will employ a Difference-in-Difference (DiD) approach to compare the changes in healthiness of grocery baskets for households that transition to hybrid shopping against those that continue shopping exclusively offline. This approach allows for controlling for general trends that affect all households (e.g. COVID-19 pandemic). By using a DiD model, we can isolate the effect that OGS has on the healthiness of households’ grocery food purchases.
- README.md
- data: all raw data files used for this project
- deliverables: used for dataprep class. The deliverables provide an updated markdown file and knitted pdf file for each week
- gen: all generated files such as tables, figures, logs.
- Three parts: data_preparation, analysis, and paper.
- audit: put the resulting log/tables/figures of audit program. It has three sub-folders: figure, log, and table.
- temp : put the temporary files, such as some intermediate datasets. We may delete these filed in the end.
- output: put results, including the generated figures in sub-folder figure, log files in sub-folder log, and tables in sub-folder table.
- input: put all temporary input files
- src: all source codes used for data manipulation.
- Three parts: data_preparation, analysis, and paper. (including tex files).
This project uses R as a tool for data analysis and printing of results tables and graphs. Please follow the installation guide on Tilburg Science Hub to install R and RStudio by clicking on the following link.
To manipuate and analyse the data, this project makes use of several packages within R. These packages will be automatically installed (if not installed already) when running the full source code. The packages that are used are:
- data.table
- dplyr
- xtable
- tinytex
- ggplot2
Melle Klein Goldewijk (m.kleingoldewijk@tilburguniversity.edu)