Laserfiche WebLink
<br />March 23, 2005 <br />Page 4 <br /> <br />Table 3 <br />City of Roseville <br />Number of Samples Sorted <br /> <br /> Number of Number of <br /> Dual Total Average Single <br /> Stream Pounds Pounds per Stream <br /> Samples Sorted Sample Samples <br />Before Pilot 22 4,708 214 <br />During Pilot 26 7,105 273 8 <br />Data Collection <br /> <br />Total <br />Pounds <br />Sorted <br /> <br />Average <br />Pounds <br />per Sample <br /> <br />2,269 <br /> <br />284 <br /> <br />Data sheets were completed during the sampling and sorting of the recyclable materials. The <br />tare weight of the container, and the weight of the individual materials plus the tare weight, were <br />recorded on the data sheets by the sort crew supervisor. The data sheets used in the study can be <br />found in Attachment C. <br /> <br />Statistical Modeling <br /> <br />The data from the sorting events were entered into R. W. Beck's specially designed statistical <br />model (Model). The Model has been developed in Microsoft Excel for easy accessibility and <br />use. The Model statistically manipulates the data to calculate the mean, 90% confidence <br />intervals, and standard deviation for individual material categories. In addition, the Model is <br />structured to identify where specific samples could be considered statistical outliers. <br /> <br />The mean represents the mathematical average or average percent of material composing the <br />recyclable materials stream. The confidence interval is an expression of accuracy. It provides <br />the upper and lower limits of the actual mean for all the recyclables in each sample, based on the <br />sorting and sampling of the materials. For example, the 90% confidence interval represents that <br />there is a 90% level of confidence that the true population mean falls within the upper and lower <br />bounds of the confidence interval. The 90% confidence interval is the generally accepted <br />standard by the industry for solid waste and recyclable materials composition studies. In <br />general, the more samples that are sorted, the narrower the confidence interval. The narrower <br />the intervals, the less variability in the data. We believe it is critical when comparing the <br />recyclable materials composition results that the confidence intervals are considered along with <br />the mean percentages. <br /> <br />In addition, the total quantities of materials collected for each route were compiled during the <br />sorting and sampling process. This data was analyzed separately to identify the mean quantities <br />collected with the various collection methods and the applicable standard deviations. <br /> <br />01-00253-10 10 1-01 01 I 070001 I 13500 P:\13500 Ramsey Co. 2003\R T A \Roseville\F A\B 1544 * Final Data Analysis <br />