2011-04-12_APPLICATION CORRESPONDENCE - C2010088

Home Browse Search

Mike Boulay -17- April 11, 2011 contrary to the definition of "random" and Cox's suggestion that the data can be collected in any order as long as the starting point is chosen in "a haphazard way." This text spends several pages discussing the "drawbacks of systematic" sampling schemes and concludes by saying [page 81] that "subjective allocation of treatments to units [sample transect location] should never be used, because the method has serious disadvantages and no compensating advantages when compared to objective randomization." Cox states [page 85] that "it is not that the systematic arrangement is necessarily less precise than the randomized one, but that the assessment of the results is on a less objective basis." Numerous other texts contain similar cautions. There is an abundance of documentation clearly showing that a "systematic sampling" approach suggested by the DRMS yields data that is more, not less biased, as are suggested by the Division and the most unbiased data is obtained from a completely randomized sampling approach. By implementing a two-stage "random sampling approach," such as was used herein, by firstly selecting purely random coordinates and then secondly, by sampling those coordinates or transects in a random manner, yields significantly less unbiased data that the "systematic sampling" approach being suggested by the DRMS. The DRMS is herein apparently suggesting that the methodology used to collect the field data is somehow flawed and that documentation must be submitted "demonstrating that the transect selection was unbiased" is totally inconsistent with numerous other vegetation sampling efforts that have conducted and accepted by the DRMS using the exact approach used herein by now having the DRMS require that documentation must now be submitted documenting why this sampling approach is acceptable. Our conclusion after careful examination of the DRMS comments along with numerous statistical references, is that the vegetation sampling approach applied herein is more unbiased and is more in harmony with the spirit and intent of the DRMS regulations and Vegetation Guideline, than the method herein being suggested by the Division. However, to clarify the exact transect sampling methodology used, clarification on the manner in which the transects were actually sampled is presented beginning on revised page 3 Exhibit 5. 28. The first paragraph on page 5 of Exhibit 5, under "Statistical Analysis of Data", notes that it was agreed that woody plant density would not be required to be sampled to statistical adequacy, but rather would be sampled in association with each cover transect. This is correct, as it was the Division's determination that a representative sample sufficient to characterize woody plant density within the affected and reference area stands could be obtained in this manner. Given the fact that disturbance to previously undisturbed habitat would be limited to a very narrow disturbance corridor (the proposed rail spur) restricted primarily to the greasewood vegetation type, it was concluded that more intensive sampling of