Use Of Resampling Research Articles

COMPARISON OF RESAMPLING EFFICIENCY LEVELS OF JACKKNIFE AND DOUBLE JACKKNIFE IN PATH ANALYSIS

The assumption of normality is often not fulfilled, this causes the estimation of the resulting parameters to be less efficient. The problem with assuming that normality is not satisfied can be overcome by resampling. The use of resampling allows data to be applied free of distributional assumptions. In this study, a research simulation was carried out by applying Jackknife resampling and Double Jackknife resampling in path analysis with the assumption that the normality of the residuals was not fulfilled and the number of resampling was set at 100 with the degree of closeness level of relationship between variables consisting of low closeness, medium closeness, and high closeness. Based on the simulation results, resampling with a power of 100 can overcome the problem of unfulfilled normality assumptions. In addition, the comparison of the relative efficiency level of the resampling jackknife and double jackknife in the path analysis obtained by the resampling double jackknife has more efficiency than the resampling jackknife

Resampling for estimation of parameters uncertainty in genetic algorithm based model fitting

Resampling methods draw samples from the observed data to draw certain conclusions about the population of interest.The study is the employment of resampling to the calculation of parameters uncertainty in hard model fitting of chemical and spectrochemical data, assisted by genetic algorithm. Four data sets are investigated including: a simulated two steps of complexometric spectrophotometric titration data, a real data from IgG purification by ion exchange chromatography, one 1H NMR spectrum from a real metabolomics data set, and a simulated metabolomics 1H NMR spectrum. In the first data, the logarithm of formation constants in the first and second steps were 4.500 and 7.200, respectively. The mean of estimated parameters and standard deviations using the proposed method were obtained as 4.504 ± 0.005 and 7.205 ± 0.017 by removing around half of the samples while for NGLM algorithm and Hessian matrix were 4.503 ± 0.005 and 7.203 ± 0.018. In the second data, desorption coefficient (kdes,0), equilibrium coefficient (Keq,0), and a constant parameter that describes ion exchange characteristics (β) were well estimated with root mean square error (RMSE) of 0.031 mg mL−1. In the third and last data sets, parameters including chemical shifts and intensity of each metabolite were well calculated with low relative error of 4.23 × 10−4. The estimated uncertainty of parameters were different. In some cases, the means of estimated parameters were dependent of the number of eliminated samples in resampling. Effect of number of variables in data and model deficiency on the results from resampling was investigated. Due to the complexity of the mentioned datasets, use of resampling and GA is useful and important strategy for acquiring parameter mean and uncertainty, when we are not able to determine the Hessian matrix.

Testing of statistical significance of semantic changes detected by diachronic word embedding

In recent years, methods based on word embedding models have been widely used for solving problems of semantic change estimation. The models are trained on text corpora of various years. Semantic change is detected by analyzing changes in distance between words using vector space alignment or by analyzing changes in a set of words that are most similar in meaning to a target word. Testing for statistical significance of the detected effects has not been detailly discussed in previous studies. This paper focuses on the problem of testing statistical significance of semantic change. Besides, we consider the problem of finding a confidence interval of estimates of semantic distance between words. We allow for the influence of two random factors. The first one is associated with the use of random initial conditions and stochastic optimization when training the model, the second one results from a random selection of texts for a training corpus. The proposed approach is based on the use of resampling of a training set of texts. The proposed method is tested on the COHA corpus.

Comparison of Parameter Estimator Efficiency Levels of Path Analysis with Bootstrap and Jack Knife (Delete-5) Resampling Methods on Simulation Data

In practice, the assumptions of normality are often not met, this causes the estimation of the resulting parameters to be less efficient. Problems with the assumption that normality is not met can be overcome by resampling. The use of resampling allows data to be applied free from distribution assumptions. In this study, a simulation study was carried out by applying bootstrap resampling and jackknife resampling (delete-5) on path analysis assuming that the normality of the alignment was not met and the resampling amount set at 1000 with the degree of closeness between variables consisting of low closeness, medium closeness, high closeness and closeness level representing the level low to high closeness. Based on the simulation results, the resampling 1000 magnitude is able to overcome the problem of the assumptions of unmet normality. In addition, a comparison between bootstrap and jackknife resampling for conditions of side normality assumptions is not fulfilled and the closeness of the relationship between low, medium, high and closeness variables representing low to high closeness levels, the estimation results of path analysis parameters obtained by resampling jackknife are more efficient than resampling bootstrap.

Robust Statistical Pixel Estimation

AbstractRobust statistical methods are employed to reduce the noise in Monte Carlo ray tracing. Through the use of resampling, the sample mean distribution is determined for each pixel. Because this distribution is uni‐modal and normal for a large sample size, robust estimates converge to the true mean of the pixel values. Compared to existing methods, less additional storage is required at each pixel because the sample mean distribution can be distilled down to a compact size, and fewer computations are necessary because the robust estimation process is sampling independent and needs a small input size to compute pixel values. The robust statistical pixel estimators are not only resistant to impulse noise, but they also remove general noise from fat‐tailed distributions. A substantial speedup in rendering can therefore be achieved by reducing the number of samples required for a desired image quality. The effectiveness of the proposed approach is demonstrated for path tracing simulations.

Resolution of Respect: W. Scott Overton

Resolution of Respect: W. Scott Overton

Estimation and Asymptotic Theory for Transition Probabilities in Markov Renewal Multi-State Models

In this paper we discuss estimation of transition probabilities for semi-Markov multi-state models. Non-parametric and semi-parametric estimators of the transition probabilities for a large class of models (forward going models) are proposed. Large sample theory is derived using the functional delta method and the use of resampling is proposed to derive confidence bands for the transition probabilities. The last part of the paper concerns the presentation of the main ideas of the R implementation of the proposed estimators, and data from a renal replacement study are used to illustrate the behavior of the estimators proposed.

A resampling-based meta-analysis for detection of differential gene expression in breast cancer

BackgroundAccuracy in the diagnosis of breast cancer and classification of cancer subtypes has improved over the years with the development of well-established immunohistopathological criteria. More recently, diagnostic gene-sets at the mRNA expression level have been tested as better predictors of disease state. However, breast cancer is heterogeneous in nature; thus extraction of differentially expressed gene-sets that stably distinguish normal tissue from various pathologies poses challenges. Meta-analysis of high-throughput expression data using a collection of statistical methodologies leads to the identification of robust tumor gene expression signatures.MethodsA resampling-based meta-analysis strategy, which involves the use of resampling and application of distribution statistics in combination to assess the degree of significance in differential expression between sample classes, was developed. Two independent microarray datasets that contain normal breast, invasive ductal carcinoma (IDC), and invasive lobular carcinoma (ILC) samples were used for the meta-analysis. Expression of the genes, selected from the gene list for classification of normal breast samples and breast tumors encompassing both the ILC and IDC subtypes were tested on 10 independent primary IDC samples and matched non-tumor controls by real-time qRT-PCR. Other existing breast cancer microarray datasets were used in support of the resampling-based meta-analysis.ResultsThe two independent microarray studies were found to be comparable, although differing in their experimental methodologies (Pearson correlation coefficient, R = 0.9389 and R = 0.8465 for ductal and lobular samples, respectively). The resampling-based meta-analysis has led to the identification of a highly stable set of genes for classification of normal breast samples and breast tumors encompassing both the ILC and IDC subtypes. The expression results of the selected genes obtained through real-time qRT-PCR supported the meta-analysis results.ConclusionThe proposed meta-analysis approach has the ability to detect a set of differentially expressed genes with the least amount of within-group variability, thus providing highly stable gene lists for class prediction. Increased statistical power and stringent filtering criteria used in the present study also make identification of novel candidate genes possible and may provide further insight to improve our understanding of breast cancer development.

Feature Selection Using Probabilistic Neural Networks

Selection of input variables is a key stage in building predictive models, and an important form of data mining. As exhaustive evaluation of potential input sets using full non-linear models is impractical, it is necessary to use simple fast-evaluating models and heuristic selection strategies. This paper discusses a fast, efficient, and powerful nonlinear input selection procedure using a combination of Probabilistic Neural Networks and repeated bitwise gradient descent. The algorithm is compared with forward elimination, backward elimination and genetic algorithms using a selection of real-world data sets. The algorithm has comparative performance and greatly reduced execution time with respect to these alternative approaches. It is demonstrated empirically that reliable results cannot be gained using any of these approaches without the use of resampling.

What Some Puzzling Problems Teach about the Theory of Simulation and the Use of Resampling

What Some Puzzling Problems Teach about the Theory of Simulation and the Use of Resampling

What Some Puzzling Problems Teach about the Theory of Simulation and the Use of Resampling

Abstract Simulation is simpler intellectually than the formulaic method because it does not require that one calculate the number of points in the entire sample space and the number of points in some subset. Instead, one directly samples the ratio. This article presents probabilistic problems that confound even skilled statisticians when attacking the problems deductively, yet are easy to handle correctly, and become clear intuitively, with physical simulation. This analogy demonstrates the usefulness of simulation in the form of resampling methods.