Open this publication in new window or tab >>2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]
In the dynamic fluctuating economic landscape, firm policies are the guiding principles that steer market conditions and firms' behaviour. In the past, these policies were formulated based on limited data and a heavy reliance on expert opinions. However, a new era is dawning, characterised by vast amounts of data processing using advanced statistical and computer science methodologies. Data-driven decision-making uses these methodologies to consolidate and process data into actionable information, leading to firm policies. The critical data sources are the data sources on which the policies are based. The data-driven decision-making allows the data to speak for itself, relying less on expert opinions for policymaking. However, it also necessitates a higher requirement of validation. This thesis investigates five different cases of firm policy and critical data sources. Each one of them will present one aspect of this broad topic. The first paper investigates selecting auxiliary variables to estimate firm characteristics, aiming to reduce bias and improve accuracy. Simple variables outperform complex ones, and complete data enhances accuracy. The second paper introduces a methodology for quantitative inductive research on ordinal survey data by new- and traditional- penalising methods. The new methods outperformed the old and could find a significant variable, while the older models could not. The third paper examines how macro-factors impacted various Small and Medium Enterprises (SME) sectors in the European Union’s member states from 2005 to 2019. The research offers valuable insights for policymakers and business leaders, aiding in tailored policy interventions and support mechanisms to address regional disparities and economic conditions. The fourth and fifth papers investigated Short-Time Work (STW), a primary policy tool during the COVID-19 pandemic. These studies used Swedish firm-level data to assess the STW policy. In the fourth paper, STW was associated with a reduction in employee numbers and a slightly increased productivity level compared to non-STW firms. In the fifth paper, STW did not increase the survival of SMEs. In conclusion, the ever-evolving economic landscape necessitates data-driven decision-making for informed actions and policymaking. This thesis is by no means a complete investigation, and further research is needed on this topic.
Place, publisher, year, edition, pages
Borlänge: Dalarna University, 2024
Series
Dalarna Doctoral Dissertations ; 37
Keywords
Firm policies, Critical data, Large data, Data-driven decision-making, Quantitative inductive methods
National Category
Economics Business Administration Computer and Information Sciences
Identifiers
urn:nbn:se:du-48605 (URN)978-91-88679-72-7 (ISBN)
Public defence
2024-09-27, room B301, campus Borlänge, 13:00 (English)
Opponent
Supervisors
2024-06-182024-05-272024-06-18Bibliographically approved