Table 5

Robustness results-alternative methodology (Bayesian regression)

VariableNCSKEWt+1DUVOLt+1
Posterior mean95% C.I.Posterior mean95% C.I.
C_COMP−5.17[−8.47, −1.88]−1.09[−1.23, 3.89]
C_DUAL−0.06[−0.13, 0.01]−0.00[−0.02, 0.01]
C_STATUS−0.06[−0.13, 0.01]−0.00[−0.01, 0.01]
C_TENURE−0.00[−0.00, 0.00]0.00[0.00, 0.00]
C_DIRECTOR−0.27[−0.39, −0.14]−0.02[−0.04, 0.00]
DTURNOVER0.00[−0.00, 5.21]2.63[−3.34, 8.59]
RET16.90[12.12, 21.68]2.77[1.86, 3.69]
M/B−0.00[−0.01, −0.00]0.00[−0.00, 0.00]
SIZE0.04[0.02, 0.06]0.01[0.00, 0.01]
LEV0.88[0.66, 1.09]0.01[−0.05, 0.03]
Constant−1.49[−1.99, −0.99]−0.21[−0.31, −0.12]
N2,3602,3602,3602,360

Note(s):C_COMP = CEO compensation; C_DUAL = CEO duality; C_STATUS = CEO status; C_TENURE = CEO tenure; C_DIRECTOR = CEO directorship; NCSKEWt+1 = negative conditional skewness measured at t+1; DUVOLt+1 = down-to-up-volatility measured at t+1; DTURNOVER = de-trended turnover; RET = company-specific weekly returns; M/B = market to book value of equity; SIZE = size of company measured by taking the natural log of market capitalisation; LEV = leverage. Bayesian regression methodology based on the Markov Chain Monte Carlo (MCMC) simulation has been applied to obtain the said test results. Total number of draws 11,000 (of which 1,000 discarded)

Source(s): Author’s calculations based on using Stata 14

or Create an Account

Close subscription notice
Close access options