Workshop reproducibility - Berlin

Follow along

lars.vilhuber.com/p/berlin2024/

Survey for Day 2

https://forms.gle/zbLC45gEtbKGtM6q6

Day 1

Session 1

Setting yourself up for reproducibility

Session 2

Checking reproducibility yourself and other tools

Day 2

Session 3

Reproducibility when some data are confidential

Session 4

One of the following:

• JIT Preservation of research output

  • https://labordynamicsinstitute.github.io/replication-tutorial-2019/#/18
  • https://labordynamicsinstitute.github.io/tutorial-data-sharing-archiving-2021/#/2 (possibly challenging)

• Short presentation on concerns about ethics in data dissemination

• In-depth tutorial on the use of Docker for economics research

  • https://codeocean.com
  • https://wholetale.org
  • https://github.com/codespaces

Results

# download data to local location
download.file(gurl,destfile=here::here("data","berlin-google-responses.csv"))
# read file in
berlin_google_responses <- read_csv(here::here("data","berlin-google-responses.csv"))

Rows: 17 Columns: 4
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (3): Timestamp, Topic, What is the name of the instructor?
dbl (1): How many browser tabs do you have open?

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

berlin_google_responses |>
  select(Topic) |>
  group_by(Topic) |>
  summarise(Frequency=n()) |>
  ungroup() |>
  mutate(Percent = round(Frequency/nrow(berlin_google_responses)*100,2)) -> data

data |> kable()

Topic	Frequency	Percent
Ethics and Privacy in Data Dissemination (discussion)	3	17.65
In-depth Tutorial on Use of Containers	8	47.06
Just-in-time Preservation of Research Data (hands-on)	6	35.29

ggplot(data,  aes(y=Frequency, x=Topic)) +
  geom_bar(position='dodge', stat='identity')

Extras

Guidance

Some additional guidance can be found on the website of the Social Science Data Editors (URLs subject to change):

• https://social-science-data-editors.github.io/guidance/DCAS_Restricted_data.html#us-census-bureau-and-fsrdc
• https://social-science-data-editors.github.io/guidance/Requested_information_hosting.html#self-generated-repositories

Examples of replication packages

With confidential data

• https://doi.org/10.3886/E154241V2 not only code, but faces the problem that IRS data cannot have variables revealed. Their workaround is not the same one as in this tutorial.
• https://doi.org/10.3886/E162581V1

Using containers:

• Kline et al (2024) “A Discrimination Report Card: primary replication package, with container specification, image on Docker Hub, and preserved image on Zenodo.
  
• Herbert et al (2024) “Reproduce to validate”: primary replication package, container specification and preserved image on Borealis.ca.

Extra info

• This document’s source: https://github.com/larsvilhuber/workshop-reproducibility-berlin
• Licensed under