Figure 4 - uploaded by Niklas L. P. Lundström
Content may be subject to copyright.
Standard deviation of estimate as a function of the discretization parameter N for varying sample sizes n ≤ N .
Source publication
The local pivotal method (LPM) is a successful sampling method for taking well-spread samples from discrete populations. We show how the LPM can be utilized to sample from arbitrary continuous distributions and thereby give powerful variance reduction in general cases. The method creates an "automatic stratification" on any continuous distribution,...
Contexts in source publication
Context 1
... note that for LPM no effort goes into constructing the strata, something that may require considerable effort in more involved situations. Figure 4a shows how the variance of the estimate declines as a function of N for some fixed values sample sizes n. ...
Context 2
... variancê σ LP M is calculated naively by repeating the experiment m = 10 4 times andˆVandˆ andˆV ( ˆ P LP M EC ) is calculated as outlined in Section 4 using the 10 nearest neighbours. Figure 4b shows how the variance of the estimate declines as a function of the discretization parameter N for some fixed values of the sample size n. 3.2 Nonlinear dynamics: Estimating non-local stability A dynamical system (DS) is a set of differential equations governing the time dependence of a point. ...
