Replication package for «Business disruptions from social distancing»

Replication package for "Business disruptions from social distancing"

Please cite as

Koren, Miklós and Rita Pető. 2020. "Replication package for «Business disruptions from social distancing»" [dataset] Zenodo. http://doi.org/10.5281/zenodo.4012191

License and copyright

All text (*.md, *.txt, *.tex, *.pdf) are CC-BY-4.0. All code (*.do, Makefile) are subject to the 3-clause BSD license. All derived data (data/derived/*) are subject to Open Database License. Please respect to copyright and license terms of original data vendors (data/raw/*).

Data Availability Statements

The mobility data used in this paper (SafeGraph 2020) is proprietary, but may be obtained free of charge for COVID-19-related research from the COVID-19 Consortium. The authors are not affiliated with this consortium. Researchers interested in access to the data can apply at https://www.safegraph.com/covid-19-data-consortium (data manager: Ross Epstein, ross@safegraph.com). After signing a Data Agreement, access is granted within a few days. The Consortium does not require coauthorship and does not review or approve research results before publication. Datafiles used: /monthly-patterns/patterns_backfill/2020/05/07/12/2020/02/patterns-part[1-4].csv.gz (Monthly Places Patterns for February 2020, released May 7, 2020), /monthly-patterns/patterns/2020/06/05/06/patterns-part[1-4].csv.gz (Monthly Places Patterns for February 2020, released June 5, 2020) and /core/2020/06/Core-USA-June2020-Release-CORE_POI-2020_05-2020-06-06.zip (Core Places for June 2020, released June 6, 2020). The COVID-19 Consortium will keep these datafiles accessible for researchers. The authors will assist with any reasonable replication attempts for two years following publication.

All other data used in the analysis, including raw data, are available for reuse with permissive licenses. Raw data are saved in the folder data/raw/. The Makefile in each folder shows the URLs used to download the data.

SafeGraph

Citation

SafeGraph. "Patterns [dataset]"; 2020. Downloaded 2020-06-20.

License

Proprietary, see https://shop.safegraph.com/ or https://www.safegraph.com/covid-19-data-consortium (data manager: Ross Epstein, ross@safegraph.com)

O*NET

Citation

U.S. Department of Labor/Employment and Training Administration, 2020. "O*NET Online." Downloaded 2020-03-12.

License

CC-BY-4.0 https://www.onetonline.org/help/license

Current Employment Statistics

Citation

U.S. Bureau of Labor Statistics. 2020. "Current Employment Statistics." https://www.bls.gov/ces/ Downloaded 2020-03-15.

License

Public domain: https://www.bls.gov/bls/linksite.htm

National Employment Matrix

Citation

U.S. Bureau of Labor Statistics. 2018. "National Employment Matrix." https://www.bls.gov/emp/data/occupational-data.htm Downloaded 2020-03-15.

License

Public domain: https://www.bls.gov/bls/linksite.htm

Crosswalk

Citation

U.S. Bureau of Labor Statistics. 2019. "O* NET-SOC to Occupational Outlook Handbook Crosswalk." https://www.bls.gov/emp/classifications-crosswalks/nem-onet-to-soc-crosswalk.xlsx Downloaded 2020-03-15.

License

Public domain: https://www.bls.gov/bls/linksite.htm

American Time Use Survey

Citation

U.S. Bureau of Labor Statistics. 2018. “American Time Use Survey.” https://www.bls.gov/tus/.

We are using the following files:

• Respondent File
• Activity File
• Who File
• Replicate Weights
• Leave Module 2017-18

License

Data is in public domain.

County Business Patterns

Citation

U.S. Bureau of the Census. 2017. "County Business Patterns." Available at https://www.census.gov/programs-surveys/cbp.html

License

https://www.census.gov/data/developers/about/terms-of-service.html

Dataset list

Raw data

| Data file | Source | Notes | Provided |

|-----------|--------|----------|----------|

| data/raw/bls/industry-employment/ces.txt | BLS Current Employment Statistics | Public domain | Yes |

| data/raw/bls/atus/*.dat | BLS Time Use Survey | Public domain | Yes |

| data/raw/bls/employment-matrix/matrix.xlsx | BLS National Employment Matrix | Public domain | Yes |

| data/raw/bls/crosswalk/matrix.xlsx | ONET-SOC to Occupational Outlook Handbook Crosswalk | Public domain | Yes |

| data/raw/onet/*.csv | ONET Online | Creative Commons 4.0 | Yes |

| data/raw/census/cbp/*.txt | County Business Patterns | Public domain | Yes |

| not-included/safegraph/02/*.csv| SafeGraph | Available with Data Agreement with SafeGraph | No |

| not-included/safegraph/05/*.csv| SafeGraph | Available with Data Agreement with SafeGraph | No |

Clean data

| Data file | Source | Notes | Provided |

|-----------|--------|----------|----------|

| data/clean/industry-employment/industry-employment.dta | BLS Current Employment Statistics | Public domain | Yes |

| data/clean/time-use/atus.dta | BLS Time Use Survey | Public domain | Yes |

| data/clean/employment-matrix/matrix.dta | BLS National Employment Matrix | Public domain | Yes |

| data/clean/onet/risks.csv | ONET Online | Creative Commons 4.0 | Yes |

| data/clean/cbp/zip_code_business_patterns.dta | County Business Patterns | Public domain | Yes |

Derived data

| Data file | Source | Notes | Provided |

|-----------|--------|----------|----------|

| data/derived/occupation/* | Various sources | Public domain | Yes |

| data/derived/time-use/atus_working_at_home_occupationlevel.dta | BLS Time Use Survey | Public domain | Yes |

| data/derived/crosswalk/* | Various sources | Public domain | Yes |

| not-included/safegraph/naics-zip-??.csv| SafeGraph | Available with Data Agreement with SafeGraph | Yes, with permission of SafeGraph |

| data/derived/visit/visit-change.dta| SafeGraph | Aggregated to 3-digit NAICS industries | Yes, with permission of SafeGraph |

Computational requirements

Software Requirements

• Stata (code was last run with version 16.1)
  • estout (from http://www.stata-journal.com/software/sj14-2/)
  • running make install from the root of the folder will install estout locally, and should be run once.

Portions of the code use bash scripting (make, wget, head, tail), which may require Linux or Mac OS X.

The entry point for analysis is analysis/Makefile, which can be run by GNU Make on any Unix-like system by

cd analysis
make

 

The dependence of outputs on code and input data is captured in the respective Makefiles.

We have used Mac OS X, but all the code should run on Linux and Windows platforms, too.

Hardware

The analysis takes a few minutes on a standard laptop.

Description of programs

1. Raw data are in data/raw/<vendor>/<dataset>. This data is saved as it has been received from the data publisher, downloaded by the respective Makefiles. Each folder has a README.md with data citation and license terms.
2. Clean data are in data/clean/<dataset>. Each folder has a Makefile that specifies the steps of data cleaning.
3. Analysis data are in data/derived/<topic>. Each folder has a Makefile that specifies the steps of sample specification, variable selection and modification.
4. Analysis codes are in analysis/. A Makefile specifies how the .do files have to be run to reproduce the analysis.

Instructions

After uncompressing the replication package, change the working directory to analysis/ and run the Makefile there.

unzip PONE-D-20-08910.zip
cd PONE-D-20-08910/analysis/
make

 

List of tables and programs

-------------------------

| Exhibit | File | Code |

|---------|------|------|

| headcount number in abstract | analysis/headcount.log line 60 | analysis/headcount.do |

| Table 1 | NA | NA |

| Table 2 | exhibit/table2.csv | analysis/toplist.do |

| Table 3 | exhibit/table3.tex | analysis/employment-growth.do |

| Table 4 | exhibit/table4.csv | analysis/counterfactual.do |

| Figure 1 | exhibit/fig1.eps | NA |

| Figure 2 | exhibit/fig2.eps | analysis/scatter_customers_teamwork_byoccupation.do |

| Figure 3 | exhibit/fig3.eps | analysis/scatterplot_validation_customer_atus.do |

| Figure 4 | exhibit/fig4.eps | analysis/scatterplot_validation_teamwork_atus.do |

 

 

References

1. National Center for O* NET Development. O* NET OnLine [dataset]; 2020. https://www.onetonline.org/
2. U S Bureau of the Census. County Business Patterns [dataset]; 2017. https://www.census.gov/data/datasets/2017/econ/cbp/2017-cbp.html
3. SafeGraph. Patterns [dataset]; 2020. https://www.safegraph.com/covid-19-data-consortium
4. U S Bureau of Labor Statistics. American Time Use Survey [dataset]; 2018. https://www.bls.gov/tus/#data
5. U S Bureau of Labor Statistics. Current Employment Statistics [dataset]; 2020. https://www.bls.gov/ces/
6. U S Bureau of Labor Statistics. National Employment Matrix [dataset]; 2020. https://www.bls.gov/emp/tables/industry-occupation-matrix-industry.htm