Testing the Change in Correlation Structure across Markets : High-Dimensional Data

The purpose of this study is to test whether CSR engagement provides insurance like effect even after the firm has faced an integrity questioning event. The impact of this integrity based negative event is measured as the media sentiment while reporting the event. Accordingly, we test whether prior CSR engagement prompts media to give the firm the benefit of doubt when it is accused of ‘grand corruption’. The study employs techniques of textual analysis combining various dictionaries and multiple media sources to estimate the sentiment score. Accordingly, we analyse 45,710 media reports, covering firms allegedly involved in ‘grand corruption’. The hypotheses are tested following standard panel data analysis techniques. The study finds no evidence of CSR providing an insurance like effect, particularly in the context of integrity-based negative events. Rather, the results suggest that the media may have viewed the CSR activity of sample firms as a public relations exercise and penalized them for being involved in grand corruption.