This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: CountBased, DensityIndependent PVA in Excel This document describes how to use Microsoft Excel to perform the density independent, countbased PVA (Dennis et al., Ch. 3 of Morris and Doak). The example dataset used is the Yellowstone grizzly population used in Morris and Doak Ch. 3. Estimate and 2 Enter the data Set up the data in a sensible tabular format, with census index, census time, and census value. Plot the data to get a sense of whether the model makes sense. In this case, it looks like both and 2 may be increasing through time. However, apart from the early decline, the data do not look inconsistent with exponential growth. Estimate r Calculate i = N i+1 /N i and r i = log( i ). Estimate and 2 directly If the censuses occur at yearly intervals, as they do for the grizzlies, then can be estimated as the mean of r and 2 can be estimated as the variance of r. Their confidence intervals can be calculated using the t and inverse 2 distributions, respectively. Estimate and 2 from regression If the censuses occur at irregular intervals, construct two new variables, x i and y i . Now regress y on x, forcing the intercept through zero. Regression, along with a variety of other statistical tests, is found under Tools>Data Analysis. If the latter is not on your tools menu (it will be near the bottom) go to Tools>AddIns and add the Analysis Tool Pak. is estimated from the slope of the regression, and 2 is the residual mean squares. The confidence interval of mu can be calculated automatically by the regression, but the CI of 2 still has to be calculated using the inverse 2 distribution. Calculate the PDF and CDF of time to extinction...
View
Full
Document
 Winter '08
 KENDALL

Click to edit the document details