How to Construct Nationally Representative Firm Level Data from the ORBIS Global Database

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in Sevcan Yeşiltaş Johns Hopkins University September 2015Abstract Firm-level data on productivity, financial activity and firms' international linkages have become essential for research in the fields of macro, international finance and growth. This paper describes the development of a firm-level global panel dataset for public and private companies based on the administrative micro-dataset ORBIS, provided commercially by Bureau van Dijk Electronic Publishing (BvD). The ORBIS database provides data on firms' financial and productive activities from balance sheets and income statements together with detailed information on firms' domestic and international ownership structure for over 130 million companies across the world. Researchers need to overcome several challenges before making the database usable for research. First, the database is not designed for large downloads that is essential for an econometric analysis. Second, there are several inherent biases in the database that affect the download process and lead to missing information. Third, the raw data may contain a number of irregularities which, if not dealt with, will result in data loss during a standard cleaning procedure. In combination, these issues cause minimal coverage of small firms, extensive missing data, and poor national representation. We give detailed instructions on the data gathering process from ORBIS in terms of downloading methodology and cleaning procedure so that a researcher can construct a database that is nationally representative with minimal missing information. We provide examples from several European countries to present the process and discuss the resulting dataset in detail.

Management as a Technology?

“…8 There are of course many other ways to model this idea, and our approach is certainly not meant to represent the wide range of Design approaches, rather we see it as a simple example to illustrate the implications of a G(M i ) function which attains an interior maximum.…”

“…Notes: *** denotes significance at the 1% level, ** denotes 5% significance and * denotes 10% significance. All columns with standard errors in parentheses under coefficients (clustered by firm except (3), (4), (8) and (12) which are bootstrapped with 150 replications). All columns use OLS except columns (2), (9) and (10) that use the Blundell and Bond (2000) method; columns (4), (8) and (12) uses the Olley-Pakes ("OP") estimator (column (4) with the Ackerberg et al, "ACF" correction), column (3) the Levinsohn-Petrin ("Lev-Pet") approach.…”

Corporate debt and investment: A firm-level analysis for stressed euro area countries

“…Our dataset includes both listed and unlisted companies and contains information on financial data of about 920 thousand firms operating in five peripheral euro area countries (Italy, Spain, Portugal, Greece and Slovenia) for the 2005-2014 period. We pursue a standard cleaning procedure to account for data irregularities (Kalemli-Özcan et al, 2015b). In particular, we take care of double entries, firm-year observations with inconsistent balance sheet or income statement relations, including those with negative debt or asset holdings.…”

Credit Scoring for the Supermarket and Retailing Industry: Analysis and Application Proposal

“…Therefore, we consider it an appropriate time period to check for the robustness of our model and at the same time avoiding abnormal distortions which the financial crisis might generate to our analysis. Balance sheet data are deflated to keep track of inflation and cleaned according to standard procedure described in (Kalemli-Ozcan, 2015). The initial dataset comprises 33,397 companies.…”