Spelling suggestions: "subject:"[een] VARIANCE"" "subject:"[enn] VARIANCE""
81 |
The investigation of cost variances modeled as a partially observable Markov processLargay, Betty Jane 08 1900 (has links)
No description available.
|
82 |
A cost optimal approach to selection of experimental designs for operational testing under conditions of constrained sample sizeRuss, Sam Wallace 05 1900 (has links)
No description available.
|
83 |
A comparison of the applicability and effectiveness of ANOVA with MANOVA for use in the operational evaluation of command and control systemsBurnette, Thomas Nelson 05 1900 (has links)
No description available.
|
84 |
Sperm Production and Variance in Sperm QualityKnudsen, JILL 26 September 2009 (has links)
An unusually high level of inter- and intraspecific variability in spermatozoa has been well documented. However, recent evidence indicates that the level of variation within spermatozoa differs markedly across taxa. In particular, it appears that the variability in spermatozoa
tends to decrease across species as the risk of sperm competition increases.
In this thesis, I present a model that explains how variability in spermatozoa may arise due to errors made during the sperm production process. In doing so, I also provide an explanation for why variability in sperm traits tends to decrease as the level of sperm competition experienced by males of a given species increases.
The model presented in this study provides a novel perspective on spermatozoa and their production. While many sperm traits are thought to be selected upon, I suggest
that variability in spermatozoa may also be the result of evolutionary forces such as sperm competition. Variability in spermatozoa, then, can be adaptive and can represent an optimal reproductive strategy. / Thesis (Master, Biology) -- Queen's University, 2009-09-25 21:53:23.172
|
85 |
A general framework for reducing variance in agent evaluationWhite, Martha Unknown Date
No description available.
|
86 |
Estimability and testability in linear modelsAlalouf, Serge. January 1975 (has links)
No description available.
|
87 |
Dependence concepts and selection criteria for lattice rulesTaniguchi, Yoshihiro January 2014 (has links)
Lemieux recently proposed a new approach that studies randomized quasi-Monte Carlothrough dependency concepts.
By analyzing the dependency structure of a rank-1 lattice,Lemieux proposed a copula-based criterion with which we can find a ???good generator??? for
the lattice.
One drawback of the criterion is that it assumes that a given function can be
well approximated by a bilinear function. It is not clear if this assumption holds in general.
In this thesis, we assess the validity and robustness of the copula-based criterion. We dothis by working with bilinear functions, some practical problems such as Asian option pricing, and perfectly non-bilinear functions. We use the quasi-regression technique to study
how bilinear a given function is.
Beside assessing the validity of the bilinear assumption,
we proposed the bilinear regression based criterion which combines the quasi-regression and the copula-based criterion. We extensively test the two criteria by comparing them to other well known criteria, such as the spectral test through numerical experiments. We
find that the copula criterion can reduce the error size by a factor of 2 when the functionis bilinear. We also find that the copula-based criterion shows competitive results evenwhen a given function does not satisfy the bilinear assumption. We also see that our newly introduced BR criterion is competitive compared to well-known criteria.
|
88 |
A general framework for reducing variance in agent evaluationWhite, Martha 06 1900 (has links)
In this work, we present a unified, general approach to variance reduction in agent evaluation using machine learning to minimize variance. Evaluating an agent's performance in a stochastic setting is necessary for agent development, scientific evaluation, and competitions. Traditionally, evaluation is done using Monte Carlo estimation (sample averages); the magnitude of the stochasticity in the domain or the high cost of sampling, however, can often prevent the approach from resulting in statistically significant conclusions. Recently, an advantage sum technique based on control variates has been proposed for constructing unbiased, low variance estimates of agent performance. The technique requires an expert to define a value function over states of the system, essentially a guess of the state's unknown value. In this work, we propose learning this value function from past interactions between agents in some target population. Our learned value functions have two key advantages: they can be applied in domains where no expert value function is available and they can result in tuned evaluation for a specific population of agents (e.g., novice versus advanced agents). This work has three main contributions. First, we consolidate previous work in using control variates for variance reduction into one unified, general framework and summarize the connections between this previous work. Second, our framework makes variance reduction practically possible in any sequential decision making task where designing the expert value function is time-consuming, difficult or essentially impossible. We prove the optimality of our approach and extend the theoretical understanding of advantage sum estimators. In addition, we significantly extend the applicability of advantage sum estimators and discuss practical methods for using our framework in real-world scenarios. Finally, we provide low-variance estimators for three poker domains previously without variance reduction and improve strategy selection in the expert-level University of Alberta poker bot.
|
89 |
Quantitative quality control and background correction for two-colour microarray dataRitchie, Matthew Edward Unknown Date (has links) (PDF)
Two-colour microarrays are a popular tool for measuring relative gene expression between RNA populations for thousands of genes simultaneously. This thesis develops methods for assessing the quality and variability of data from such experiments and for incorporating these assessments into algorithms for discovering differential expression. The variability of microarray data depends not only on the quality of the arrays, but also on how they are processed and normalised. The intimate relationship between variability of expression log-ratios and the method used for background correcting the expression values is specifically explored. The performance of different estimators of the background level and various model-based processing methods, including a novel normal-exponential convolution model are compared in search of a ‘best’ alternative. The results indicate that the choice of method should be guided by the specific question of interest; the model-based methods give gene expression measures with low bias, and do very well at choosing differentially expressed genes, while subtracting low background estimates, or not background correcting the data produces low variance estimates which are the most biased, however perform best at choosing DE genes. All of these alternatives give better results than those obtained by the standard approach of subtracting high local background estimates from the foreground signal, which is not recommended. (For complete abstract open document)
|
90 |
Variances of some truncated distributions for various points of truncation.Hayles, George Carlton, January 1966 (has links)
Thesis (M.S.)--Virginia Polytechnic Institute, 1966. / Also available via the Internet.
|
Page generated in 0.025 seconds