Cautionary Remarks When Testing Agreement between Two Raters for Continuous Scale Measurements: A Tutorial in Clinical Epidemiology with Implementation Using R

Background: When continuous scale measurements are available, agreements between two measuring devices are assessed both graphically and analytically. In clinical investigations, Bland and Altman proposed plotting subject-wise differences between raters against subject-wise averages. In order to scientifically assess agreement, Bartko recommended combining the graphical approach with the statistical analytic procedure suggested by Bradley and Blackwood. The advantage of using this approach is that it enables significance testing and sample size estimation. We noted that the direct use of the results of the regression is misleading and we provide a correction in this regard. Methods: Graphical and linear models are used to assess agreements for continuous scale measurements. We demonstrate that software linear regression results should not be readily used and we provided correct analytic procedures. The degrees of freedom of the F-statistics are incorrectly reported, and we propose methods to overcome this problem by introducing the correct analytic form of the F statistic. Methods for sample size estimation using R-functions are also given. Results: We believe that the tutorial and the R-codes are useful tools for testing and estimating agreement between two rating protocols for continuous scale measurements. The interested reader may use the codes and apply them to their available data when the issue of agreement between two raters is the subject of interest.

A LARGE SAMPLE ESTIMATE IN MEDIAN LINEAR REGRESSION MODEL Ⅰ: NONTRUNCATED CASE

This paper uses a grouping-adjusting procedure to the data from a median linear regression model, and estimtes the regression coefficients by the method of weighted least squares. This method simplifies computation and in the meantime, preserves the same asymptotic normal distribution for the estimator, as in the ordinary minimum L_1-norm estimates.

Estimation of Boost Converter State-Space Variables Using Fast Output Sampling Method

In this paper a fast output sampling （FOS） estimator is designed for estimation of state-space variables of DC-DC boost converter. Estimated state-space variables are output voltage of the converter and its first derivative, which are suitable for model reference adaptive controllers and sliding mode controllers design. Estimator is designed for operation in continuous and discontinuous conduction modes. The simulation results show that proposed FOS estimator provides good estimation of state-space variables despite the voltage ripple caused by high frequency switching in converter and disturbances （change of load and input voltage）.

Probability estimation based on grey system theory for simulation evaluation

In the evaluation of some simulation systems, only small samples data are gotten due to the limited conditions. In allusion to the evaluation problem of small sample data, an interval estimation approach with the improved grey confidence degree is proposed.On the basis of the definition of grey distance, three kinds of definition of the grey weight for every sample element in grey estimated value are put forward, and then the improved grey confidence degree is designed. In accordance with the new concept, the grey interval estimation for small sample data is deduced. Furthermore,the bootstrap method is applied for more accurate grey confidence interval. Through resampling of the bootstrap, numerous small samples with the corresponding confidence intervals can be obtained. Then the final confidence interval is calculated from the union of these grey confidence intervals. In the end, the simulation system evaluation using the proposed method is conducted. The simulation results show that the reasonable confidence interval is acquired, which demonstrates the feasibility and effectiveness of the proposed method.

Network address translation traversal based on Bernoulli laws of large number in P2P streaming system

P2P streaming application must realize network address translation （NAT） traversal. To handle low success ratio of the existing NAT traversal algorithm, UPnP-STUN （UPUN） and port-mapping sample estimation （PMSE） algorithm are recommended in this paper. UPUN is the combination of UPnP and STUN, and PMSE utilizes port mapping samples added by symmetric NAT for different sessions to estimate regularity of port mapping of symmetric NAT, which takes advantage of the Bernoulli law of large numbers. Besides, for the situation that both peers are behind NAT, and to handle heavy relay server load when many inner peers want to communicate with each other, a peer auxiliary-relay （PAR） algorithm is presented. PAR lets outer peers with sufficient bandwidth act as relay servers to alleviate pressure of real server, which could avoid NAT traversal failure caused by single point failure of relay server. Finally, experiments show that the proposed algorithms could improve the success ratio significantly for NAT traversal in P2P streaming application as well as improve P2P streaming application applicability.

A New Economy Forecasting Method Based on Data Barycentre Forecasting Method

A new and useful method of technology economics, parameter estimation method, was presented in light of the stability of gravity center of object in this paper. This method could deal with the fitting and forecasting of economy volume and could greatly decrease the errors of the fitting and forecasting results. Moreover, the strict hypothetical conditions in least squares method were not necessary in the method presented in this paper, which overcame the shortcomings of least squares method and expanded the application of data barycentre method. Application to the steel consumption volume forecasting was presented in this paper. It was shown that the result of fitting and forecasting was satisfactory. From the comparison between data barycentre forecasting method and least squares method, we could conclude that the fitting and forecasting results using data barycentre method were more stable than those of using least squares regression forecasting method, and the computation of data barycentre forecasting method was simpler than that of least squares method. As a result, the data barycentre method was convenient to use in technical economy.

Benchmark Dose Estimation for Cadmium-Induced Renal Effects Based on a Large Sample Population from Five Chinese Provinces

A survey involving 6103 participants from five Chinese provinces was conducted to evaluate the threshold value of urinary cadmium （UCd） for renal dysfunction as benchmark dose low （BMDL）. The urinary N-acetyl-13-D-glucosaminidase （UNAG） was chosen as an effect biomarker. The UCd BMDLs for UNAG ranged from 2.18μg/g creatinine （cr） to 4.26μg/g cr in the populations of different provinces. The selection of the sample population and area affect the evaluation of the BMDL. The reference level of UCd for renal effects was further evaluated based on the data of all 6103 subjects. With benchmark responses （BMR） of 10%/5%, the overall UCd BMDLs for males in the total population were 3.73/2.08 μg/g cr. The BMD was slightly lower in females, thereby indicating that females may be relatively more sensitive to Cd exposure than are males.

Effective condition numbers and small sample statistical condition estimation for the generalized Sylvester equation

Abstract In this paper, we investigate the effective condition numbers for the generalized Sylvester equation （AX - YB, DX - YE） = （C,F）, where A,D ∈ Rm×m B,E ∈ Rn×n and C,F ∈ Rm×n. We apply the small sample statistical method for the fast condition estimation of the generalized Sylvester equation, which requires （9（m2n ＋ mn2） flops, comparing with （-O（m3 ＋ n3） flops for the generalized Schur and generalized Hessenberg- Schur methods for solving the generalized Sylvester equation. Numerical examples illustrate the sharpness of our perturbation bounds.

Static Frame Model Validation with Small Samples Solution Using Improved Kernel Density Estimation and Confidence Level Method

An improved method using kernel density estimation （KDE） and confidence level is presented for model validation with small samples. Decision making is a challenging problem because of input uncertainty and only small samples can be used due to the high costs of experimental measurements. However, model validation provides more confidence for decision makers when improving prediction accuracy at the same time. The confidence level method is introduced and the optimum sample variance is determined using a new method in kernel density estimation to increase the credibility of model validation. As a numerical example, the static frame model validation challenge problem presented by Sandia National Laboratories has been chosen. The optimum bandwidth is selected in kernel density estimation in order to build the probability model based on the calibration data. The model assessment is achieved using validation and accreditation experimental data respectively based on the probability model. Finally, the target structure prediction is performed using validated model, which are consistent with the results obtained by other researchers. The results demonstrate that the method using the improved confidence level and kernel density estimation is an effective approach to solve the model validation problem with small samples.

Unseen head pose prediction using dense multivariate label distribution

Accurate head poses are useful for many face-related tasks such as face recognition, gaze estimation,and emotion analysis. Most existing methods estimate head poses that are included in the training data(i.e.,previously seen head poses). To predict head poses that are not seen in the training data, some regression-based methods have been proposed. However, they focus on estimating continuous head pose angles, and thus do not systematically evaluate the performance on predicting unseen head poses. In this paper, we use a dense multivariate label distribution(MLD) to represent the pose angle of a face image. By incorporating both seen and unseen pose angles into MLD, the head pose predictor can estimate unseen head poses with an accuracy comparable to that of estimating seen head poses. On the Pointing'04 database, the mean absolute errors of results for yaw and pitch are 4.01?and 2.13?, respectively. In addition, experiments on the CAS-PEAL and CMU Multi-PIE databases show that the proposed dense MLD-based head pose estimation method can obtain the state-of-the-art performance when compared to some existing methods.