This is the third and final document of our project to produce interactive figures using Shiny and data from the SSB API. The Shiny app is embedded below, but for viewing it as intended we recommend viewing it at https://andreas-olden.shinyapps.io/ssb_api/. All source code for reproducing the entire project is available for download at: https://github.com/andreasolden/ssb-api-og-shiny. You …
2/3 SSB API and Shiny- data prep
Cleaning data from SSB API Cleaning data from SSB API Andreas Olden and Erling Risa January 23, 2019 Introduction This is the second document in our series on how to make interactive figures and tables using R, Shiny apps and the SSB API. The entire project is available at: https://github.com/andreasolden/ssb-api-og-shiny Loading the data df_10594 <- …
1/3 SSB API and Shiny
Extracting data from SSB API Extracting data from SSB API Andreas Olden and Erling Risa January 23, 2019 Introduction This is the first document on a series on how to make interactive figures and tables using Shiny apps and dashboards, using the Statistics Norway (SSB) API and other online sources. The entire project is available …
What Do You Buy When No One’s Watching? The Effect of Self-Service Checkouts on the Composition of Sales in Retail. (working paper)
Buying items that are unhealthy or are of a private nature may carry a stigma and cause embarrassment. I analyze whether the anonymity provided by self-service checkouts changes customers’ shopping patterns in grocery stores. I look at a natural experiment where two stores in a grocery-chain implement self-service checkouts. Using a triple difference estimator, comparing …
Does the opportunity to voice your opinion on the tax system give taxpayers agency and increase tax compliance? A randomized field experiment. (developed)
This field experiment explores how providing taxpayers with voice and agency on the tax system impacts tax compliance. The field experiment is run on potentially the 100 000 smallest businesses in a Scandinavian country, with an expected sample size of 30 000. There are two treatment groups and a baseline group. The first treatment groups …
Fraud detection by a multinomial model. Separating honesty from unobserved fraud. A Monte Carlo simulation study (developed)
With the problem of detecting tax evasion in mind, we investigate how to identify items, e.g. individuals or companies, that are wrongly classified as honest. Normally, we observe two groups of items, labeled fradulent and honest, but suspect that many of the observationally honest items are, in fact, fraudulent. The items observed as honest are …
The triple difference estimator (developed)
Triple differences has become a widely used estimator in empirical work. A close reading of articles in top economics journals reveals that the use of the estimator to a large extent rests on intuition. The identifying assumptions are neither formally derived nor generally agreed on. We give a complete presentation of the triple difference estimator, …
The impact of perceived unfair fines for tax compliance and labor market participation rates. A panel data study. (under development)
As of the tax year 2016, the tax administration in Norway introduced steep penalties of up to USD 6000 for filing tax reports after the deadline. Late filing has traditionally been very common among small businesses, and there are hit the hardest by the new fines. This has led large incomes for the state, as …
Welcome to my new website
I have emigrated from my old website to better reflect my current interests. The old content is gone, but I hope to fill this one with newer, better and broader topics related to data science and research. Check it out and stay in touch!