AN EMPIRICAL DETERMINATION OF THE MINIMUM NUMBER OF MEASUREMENTS NEEDED TO ESTIMATE THE MEAN RANDOM VITRINITE REFLECTANCE OF DISSEMINATED ORGANIC-MATTER

In coal samples, published recommendations based on statistical method s suggest 100 measurements are needed to estimate the mean random vitr inite reflectance (R(v-r)) to within +/-2%. Our survey of published th ermal maturation studies indicates that those using dispersed organic matter (DOM) mostly have an objective of acquiring 50 reflectance meas urements. This smaller objective size in DOM versus that for coal samp les poses a statistical contradiction because the standard deviations of DOM reflectance distributions are typically larger indicating a gre ater sample size is needed to accurately estimate R(v-r) in DOM. Howev er, in studies of thermal maturation using DOM, even 50 measurements c an be an unrealistic requirement given the small amount of vitrinite o ften found in such samples. Furthermore, there is generally a reduced need for assuring precision like that needed for coal applications. Th erefore, a key question in thermal maturation studies using DOM is how many measurements of R(v-r) are needed to adequately estimate the mea n. Our empirical approach to this problem is to compute the reflectanc e distribution statistics: mean, standard deviation, skewness, and kur tosis in increments of 10 measurements. This study compares these inte rmediate computations of R(v-r) statistics with a final one computed u sing all measurements for that sample. Vitrinite reflectance was measu red on mudstone and sandstone samples taken from borehole M-25 in the Cerro Prieto, Mexico geothermal system which was selected because the rocks have a wide range of thermal maturation and a comparable humic D OM with depth. The results of this study suggest that after only 20-30 measurements the mean R(v-r) is generally known to within 5% and alwa ys to within 12% of the mean R(v-r) calculated using all of the measur ed particles. Thus, even in the worst case, the precision after measur ing only 20-30 particles is in good agreement with the general precisi on of one decimal place recommended for mean R(v-r) measurements on DO M. The coefficient of variation (V = standard deviation/mean) is propo sed as a statistic to indicate the reliability of the mean R(v-r) esti mates made at n much less than 20. This preliminary study suggests a V < 0.1 indicates a reliable mean and a V > 0.2 suggests an unreliable mean in such small samples.