Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications
This paper presents a new statistical toolkit by applying three techniques for data-driven causal inference from the machine learning community that are little-known among economists and innovation scholars: a conditional independencebased approach, additive noise models, and non-algorithmic inferen...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad Nacional de Colombia
2018-12-01
|
| Series: | Cuadernos de Economía |
| Subjects: | |
| Online Access: | https://revistas.unal.edu.co/index.php/ceconomia/article/view/69832 |
| id |
doaj-b14b25c7df1644e0acc258d02dfcab27 |
|---|---|
| record_format |
Article |
| spelling |
doaj-b14b25c7df1644e0acc258d02dfcab272020-11-25T00:42:11ZengUniversidad Nacional de ColombiaCuadernos de Economía0121-47722248-43372018-12-01377577980810.15446/cuad.econ.v37n75.6983248028Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applicationsAlex Coad0CENTRUM Catolica Graduate Business School, Pontificia Universidad Catolica del PeruThis paper presents a new statistical toolkit by applying three techniques for data-driven causal inference from the machine learning community that are little-known among economists and innovation scholars: a conditional independencebased approach, additive noise models, and non-algorithmic inference by hand. We include three applications to CIS data to investigate public funding schemes for R&D investment, information sources for innovation, and innovation expenditures and firm growth. Preliminary results provide causal interpretations of some previously-observed correlations. Our statistical 'toolkit' could be a useful complement to existing techniques.https://revistas.unal.edu.co/index.php/ceconomia/article/view/69832Causal inferenceinnovation surveysmachine learningadditive noise modelsdirected acyclic graphs |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Alex Coad |
| spellingShingle |
Alex Coad Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications Cuadernos de Economía Causal inference innovation surveys machine learning additive noise models directed acyclic graphs |
| author_facet |
Alex Coad |
| author_sort |
Alex Coad |
| title |
Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications |
| title_short |
Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications |
| title_full |
Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications |
| title_fullStr |
Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications |
| title_full_unstemmed |
Tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: Theory and applications |
| title_sort |
tools for causal inference from cross-sectional innovation surveys with continuous or discrete variables: theory and applications |
| publisher |
Universidad Nacional de Colombia |
| series |
Cuadernos de Economía |
| issn |
0121-4772 2248-4337 |
| publishDate |
2018-12-01 |
| description |
This paper presents a new statistical toolkit by applying three techniques for data-driven causal inference from the machine learning community that are little-known among economists and innovation scholars: a conditional independencebased approach, additive noise models, and non-algorithmic inference by hand. We include three applications to CIS data to investigate public funding schemes for R&D investment, information sources for innovation, and innovation expenditures and firm growth. Preliminary results provide causal interpretations of some previously-observed correlations. Our statistical 'toolkit' could be a useful complement to existing techniques. |
| topic |
Causal inference innovation surveys machine learning additive noise models directed acyclic graphs |
| url |
https://revistas.unal.edu.co/index.php/ceconomia/article/view/69832 |
| work_keys_str_mv |
AT alexcoad toolsforcausalinferencefromcrosssectionalinnovationsurveyswithcontinuousordiscretevariablestheoryandapplications |
| _version_ |
1725283349305491456 |