Laserfiche WebLink
Mike Boulay <br />-13- July 8, 2011 <br />Seemingly unrecognized by the DRMS is the comment on page 16 relative to the <br />"drawbacks associated with simple random sampling..." Which are reported in <br />some instances to "be less efficient than a stratified design, and further, the <br />completely random selection of sample observation points may result in a <br />distribution in which the observations are not dispersed uniformly throughout the <br />block in a manner which appears to be 'representative.' In instances where the <br />distribution of sample observation points is skewed to such an extreme that the <br />block as a whole is not adequately represented, additional sampling may be <br />warranted." <br />Our understanding of the DRMS regulations and all associated guideline <br />documents which the DRMS has prepared over the years, is that the vegetation <br />baseline study performed on the CAM - Colorado -LLC Fruita Unit Train Loadout <br />are consistent with the regulations and the Bond Release Guideline which <br />specifically allows for operators to "give careful attention to sampling approaches <br />which minimize variation among sample observations" by using such approaches <br />such as "within- parcel stratification" That was the exact approach used herein. In <br />fact we submit that the approach used herein, yields less variation and bias in the <br />data that the approved approaches of "proportional allocation and area weighting <br />sampling" which are approved by the DRMS. <br />With respect to the suggestion made by the DRMS that "inconsistent" sampling <br />methods were used between the Greasewood Predisturbance and Greasewood <br />Reference Area we submit that this is not accurate. Random points were used <br />on both sites. The DRMS suggestion that the data must be sampled in a <br />"sequential" manner "to maintain random selection" or it is biased, cannot be <br />documented in the scientific literature we have consulted and discussions we <br />have had with numerous professionals working in this field. As we documented <br />in our previous discussion relative to the first round of Adequacy Review <br />Comments and Responses, from an extremely authoritative source, the order in <br />which the random samples are collected is irrelevant, as long as they are random <br />samples. <br />The statistical concept of "Sample Adequacy" requires that a sufficient number of <br />random sample points be collected to describe the population being sampled at <br />the 90 percent confidence interval. What is important is the number, not the <br />order in which the samples were collected. The approach being suggested by <br />the DRMS wherein random sample points must be collected and that these <br />points must be collected in a "systematic" or "sequential" order is "inconsistent" <br />with any definition of "random" we are aware off. If the regulations require that <br />random data be collected, then why can't they be collected in a random order? <br />Either the regulatory requirement found in Rule 4.15.11(1) wherein "both random <br />and systematic sample designs are acceptable" is correct or the DRMS must <br />now provide documentation why their concept of "random" sampling can only be <br />performed if the samples are sampled in systematic or "sequential" order "to <br />maintain random selection." Random, means random, nothing less, nothing <br />