Bayesian inference for merged panel autoregressive model. Issue 18 (17th September 2022)

• Record Type: Journal Article
• Authors: Kumar, Jitendra; Agiwal, Varun
• Is Part Of: Communications in statistics. Volume 51:Issue 18(2022)
• Page Start: 6197
• Page End: 6217
• Publication Date: 2022-09-17
• Subjects: Bayesian inference -- merger & acquisition series -- panel autoregressive model; 37M10 -- 62F15; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2020.1858101
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: This paper proposes a new panel autoregressive model named as merged panel autoregressive (M-PAR) model that explains the desired inferences of merger and acquisition (M&A) concept. Bayesian analysis of the M-PAR model is introduced to show the impact of the merger series in the acquire series and then obtain the Bayesian estimator under different loss functions. It is noticed that the conditional posterior distribution of all model parameters appears in standard distribution form, so the Gibbs sampler algorithm is applied for Bayesian computation. Various Bayesian testing procedures are performed to understand the influence of the merged variables into the acquired variable. The proposed model is evaluated based on simulation exercises, with the result shows that the merged variable has a significant impact on the M&A series. On the empirical application, banking indicators of the Indian banking system are analyzed to support our model.