Measurement of the branching ratios for 6P(1/2) decays to 6S(1/2) and 5D(3/2) in Ba-138(+) are reported with the decay probability from 6P(1/2) to 5D(3/2) measured to be p = 0.268177 +/- (37)(stat)-(20)(sys). This result differs from a recent report by 12 sigma. A detailed account of systematics is given, and the likely source of the discrepancy is identified. The new value of the branching reported here is combined with previous experimental results to give a new estimate of tau = 7.855(10) ns for the 6P(1/2) lifetime. In addition, ratios of matrix elements calculated from theory are combined with experimental results to provide improved theoretical estimates of the 6P(3/2) lifetime and the associated matrix elements.