The potential effects of “time series errors” in longitudinal analysis are examined empirically. Using a common hypothesis (the relationship between ownership concentration and research and development (R&D) spending) and a panel of 183 Fortune 500 firms (I 985-l 988) several time series errors are calculated. These analyses are then contrasted with the results of a procedure protected from time series errors. Comparisons show that (I) results may depend upon how researchers define and measure longitudinal effects; (2) time series errors can have significant effects on empirical findings; and (3) the linkage between ownership concentration and R&D may not be as clear-cut as previous studies have suggested. Recommendations for how researchers should account, save, and tell their time are offered.