Home About us Contact
|
Home About us Contact | ||
|
|
||
Lower Variance (lower + variance)
Selected AbstractsA comparison of methods for analysing regression models with both spectral and designed variablesJOURNAL OF CHEMOMETRICS, Issue 10 2004Kjetil Jørgensen Abstract In many situations one performs designed experiments to find the relationship between a set of explanatory variables and one or more responses. Often there are other factors that influence the results in addition to the factors that are included in the design. To obtain information about these so-called nuisance factors, one can sometimes measure them using spectroscopic methods. The question then is how to analyze this kind of data, i.e. a combination of an orthogonal design matrix and a spectroscopic matrix with hundreds of highly collinear variables. In this paper we introduce a method that is an iterative combination of partial least squares (PLS) and ordinary least squares (OLS) and compare its performance with other methods such as direct PLS, OLS and a combination of principal component analysis and least squares. The methods are compared using two real data sets and using simulated data. The results show that the incorporation of external information from spectroscopic measurements gives more information from the experiment and lower variance in the parameter estimates. We also find that the introduced algorithm separates the information from the spectral and design matrices in a nice way. It also has some advantages over PLS in showing lower bias and being less influenced by the relative weighting of the design and spectroscopic variables. Copyright © 2005 John Wiley & Sons, Ltd. [source] Costly State Verification with Varying Risk Preferences and LiabilityJOURNAL OF ECONOMIC SURVEYS, Issue 1 2006Gaia Garino Abstract., In the scenario of loan contracts with costly state verification, we examine how the properties of the set of states, different risk preferences of debtors and varying liability of lenders affect the structure of optimal repayments. In particular, we show that with risk-averse debtors, a general set of states, a constant observation cost and both unlimited and limited lender liability, the debtor is strictly better off revealing the true state of nature when his realized revenue is low, which implies that optimal debtor consumption has a downward jump around the single switch from observed to unobserved states. If the debtor can destroy revenue or if the debtor is risk neutral, this non-monotonicity of consumption disappears. Moreover, given the loan size, there is more monitoring under debtor-risk aversion than risk neutrality. We present simulations showing that a contract with unlimited lender liability and debtor-risk aversion has a higher expected observation cost but a lower variance of consumption than a contract with limited lender liability. Finally, we discuss the problems of commitment to verification and contract renegotiation in this framework. [source] Is the productivity of vegetation plots higher or lower when there are more species?OIKOS, Issue 2 2003Variable predictions from interaction of the, competitive dominance effect' on the habitat templet, sampling effect' Using a habitat templet model, we predict that the productivity (total biomass) of plots within a plant community may be positively, negatively or not at all related to variation in the number of species per plot, depending on successional stage (time since major disturbance) and habitat carrying capacity (reflecting the total resource supplying power of the habitat). For plots of a given size, a positive relationship between productivity and species richness is predicted in recently disturbed habitats because local neighbourhoods here will have been assembled largely stochastically, usually from a pool of available species with a right-skewed size frequency distribution. Hence, in the earliest stages of succession, plots will have relatively high total biomass only if they contain at least some of the relatively uncommon larger species which will, in turn, be more likely in those neighbourhoods that contain more species (the sampling effect). Among these will also be some of the more common smaller species; hence, these high biomass, species-rich plots should have relatively low species evenness, in contrast to what is predicted under effects involving species complementarity. In late succession, the plots with high total biomass will still be those that contain relatively large species but these plots will now contain relatively few species owing to increased competitive exclusion over time (the competitive dominance effect). In intermediate stages of succession, no relationship between plot productivity and species richness is predicted because the opposing sampling and competitive dominance effects cancel each other out. We predict that the intensity of both the sampling and competitive dominance effects on the productivity/species richness relationship will decrease with decreasing habitat carrying capacity (e.g. decreasing substrate fertility) owing to the inherently lower variance in between-plot productivity that is predicted for more resource-impoverished habitats. [source] Parentage versus two-generation analyses for estimating pollen-mediated gene flow in plant populationsMOLECULAR ECOLOGY, Issue 8 2005JAROSLAW BURCZYK Abstract Assessment of contemporary pollen-mediated gene flow in plants is important for various aspects of plant population biology, genetic conservation and breeding. Here, through simulations we compare the two alternative approaches for measuring pollen-mediated gene flow: (i) the neighborhood model , a representative of parentage analyses, and (ii) the recently developed twogener analysis of pollen pool structure. We investigate their properties in estimating the effective number of pollen parents (Nep) and the mean pollen dispersal distance (,). We demonstrate that both methods provide very congruent estimates of Nep and ,, when the methods' assumptions considering the shape of pollen dispersal curve and the mating system follow those used in data simulations, although the neighborhood model exhibits generally lower variances of the estimates. The violations of the assumptions, especially increased selfing or long-distance pollen dispersal, affect the two methods to a different degree; however, they are still capable to provide comparable estimates of Nep. The neighborhood model inherently allows to estimate both self-fertilization and outcrossing due to the long-distance pollen dispersal; however, the twogener method is particularly sensitive to inflated selfing levels, which in turn may confound and suppress the effects of distant pollen movement. As a solution we demonstrate that in case of twogener it is possible to extract the fraction of intraclass correlation that results from outcrossing only, which seems to be very relevant for measuring pollen-mediated gene flow. The two approaches differ in estimation precision and experimental efforts but they seem to be complementary depending on the main research focus and type of a population studied. [source] | ||||||||||