Panel A of this table reports the first-stage logit regression underlying the propensity score matching (PSM) procedure used to construct the treatment and control samples. The dependent variable is MILITARY_CEO, an indicator equal to one if the firm is led by a CEO with prior military experience and zero otherwise. The independent variables include firm characteristics commonly associated with CEO selection and earnings properties, such as firm size, leverage, book-to-market ratio, sales volatility, loss incidence, operating cycle, sales growth, operating leverage and average cash flow. The estimated coefficients are used to derive each firm’s propensity score, which forms the basis for matching firms with military CEOs to otherwise similar firms without military CEOs. Standard errors are clustered at the firm level. The z-statistics are reported in parentheses below. ***, ** and * denote two-tailed significance at the 0.01, 0.05 and 0.10 levels, respectively. All variables are defined in  Appendix 1. Panel B reports summary statistics for the matched sample. Panel C of this table reports the results from the model that examines the relationship between CEO’s military experience and income smoothing on the propensity score-matched and control sample. Standard errors are clustered at the firm level. The t-statistics are reported in parentheses below. ***, ** and * denote two-tailed significance at the 0.01, 0.05 and 0.10 levels, respectively. All variables are defined in  Appendix 1