Semiparametric random coefficient regression models

Linear regression models with random coefficients express the idea that each individual sampled may have a different linear response function. Technically speaking, random coefficient regression encompasses a rich variety of submodels. These include deconvolution or affine-mixture models as well as certain classical linear regression models that have heteroscedastic errors, or errors-in-variables, or random effects. This paper studies minimum distance estimates for the coefficient distributions in a general, semiparametric, random coefficient regression model. The analysis yields goodness-of-fit tests for the semiparametric model, prediction regions for future responses, and confidence regions for the distribution of the random coefficients.This research was supported in part by NSF Grant DMS 9001710.     

Über die Isotopenzusammensetzung des Schwefels in seinem natürlichen Kreislauf

Es wird ein Modell des globalen Kreislaufs der Isotope des Schwefels erarbeitet, auf dessen Grundlage die säkularen Veränderungen der Isotopenzusammensetzung des Schwefels in sedimentären Sulfiden, in organisch gebundenem Schwefel und in sedimentären Sulfaten verstanden werden können. Das Modell berücksichtigt die Venwitterung von Magmatiten und sedimentärem Schwefel unter Oxydation von Sulfid zu Sulfat, die Verwitterung sedimentärer Sulfate, die Bildung sedimentärer Sulfide und organisch gebundenen Schwefels, die Bildung sedimentärer Sulfate, die Metamorphose der Sedimente und die Überführung sedimentären Schwefels in die Ozeane durch vulkanische Prozesse. Es wird gezeigt, daß nur die Isotopieeffekte bei der mikrobiellen Reduktion von Sulfat zu Sulfid, bei der Assimilation von Sulfaten durch die Pflanze und bei der Verwitterung sedimentärer Sulfide und organisch gebundenem Schwefel unter Oxydation von Sulfid zu Sulfat Einfluß auf die globale Isotopenzusammensetzung des Schwefels in den Sedimenten haben können. Im Wechselspiel dieser Prozesse kommen die säkularen Verānderungen der δ³⁴S-Werte, insbesondere die charakteristischen Schwankungen der δ³⁴S-Werte zustande. Dabei begünstigen starke Meeresbedeckungen der Erdoberfläche und warmes Klima die mikrobielle Reduktion von Sulfat zu Sulfid in den Ozeanen und führen zum Sinken bzw. Steigen der δ³⁴S-Werte in den sedimentären Sulfiden und im organisch gebundenen Schwefel bzw. in den sedimentären Sulfaten. Regressionen der Ozeane und kaltes Klima, insbesondere Vereisungen begünstigen die Verwitterung und Oxydation von Sulfiden zu Sulfaten und führen zu einem Steigen bzw. Sinken der δ³⁴S-Werte in den sedimentären Sulfiden und im organisch gebundenen Schwefel bzw. in den sedimentären Sulfaten.     

Comparison of Makrofol-E and CR-39 as Solid State Nuclear Track Detectors

A comparison of the etching parameters as well as the neutron response for Makrofol-E and CR-39 was considered as solid state nuclear track detectors. The calculated sensitivity for both detectors was compared with the measured one. It is found that CR-39 has higher response to fast neutrons than Makrofol-E. The response increase due to decreasing the rate of layer removed and increasing the etch-pits per unit area.     

Assessing the subsequent effect of nitrogen released from tobacco-waste on maize crop using a 15N isotope technique

The investigation of the residual effect of nitrogen (N) released from tobacco-waste (TW) using isotope techniques will provide valuable data for sustainable organic farming. For this aim, a pot experiment was conducted using the ¹⁵N isotope technique. The experiment was based on a completely randomised design with four replications and was conducted on a calcareous ustochrepts soil. TW at levels of 0, 10, 20, 30 and 40 t ha^?1 and N fertiliser as (NH₄)₂SO₄ at levels of 0, 20, 40, 60 and 80 kg N ha^?1 were used for the Bezostaja-1 wheat variety. Concerning mineral N fertilisation with 20 and 80 kg N ha^?1, additional treatments with ¹⁵N-labelled (NH₄)₂SO₂ (10 at.% exc.) have been applied. Following harvesting wheat plants, the Pioneer 3377 maize variety was used to see the residual effect of TW. After harvesting, dry matter yields were recorded and total N concentrations were determined. ¹⁵N determinations and calculations were also made for ¹⁵N treatments separately. TW had a significant residual effect on the growth of corn plant under the pot condition. Increasing rates of TW significantly increased the dry matter yield of corn plant following wheat from 3.31 t ha^?1 (at control) to 7.89 t ha^?1 (at the TW treatment of 40 t ha^?1). The ¹⁵N values derived from the ¹⁵N fertiliser decreased with increasing TW application. The average values of N derived from N fertiliser (Ndff) varied from 2.14 to 3.09% at the rates of 20 and 80 kg N ha^?1, respectively. However, N derived from TW (Ndftw) significantly increased from 16.93 to 24.59% (at 20 kg N ha^?1), and it also increased from 23.06 to 28.15% (at 80 kg N ha^?1) with increasing TW applications from 20 to 40 t ha^?1, respectively.     

Superscaling predictions for neutrino-induced charged-current charged pion production at MiniBooNE

Superscaling approximation (SuSA) predictions to neutrino-induced charged-current charged pion production in the Δ-resonance region are explored under MiniBooNE experimental conditions. The results obtained within SuSA for the flux-averaged double-differential cross sections of the π⁺${\pi }^{+}$ production for the _νμ+_CH2${\nu }_{\mu }+{\mathrm{CH}}_2$ reaction as a function of the muon kinetic energy and of the scattering angle, the cross sections averaged over the angle, the total cross section for the π⁺${\pi }^{+}$ production, as well as CC1π⁺$\mathrm{CC}1{\pi }^{+}$ to CCQE cross section ratio are compared with the corresponding MiniBooNE experimental data. The SuSA predictions are in good agreement with data on neutrino flux average cross sections, but a somewhat different dependence on the neutrino energy is predicted than the one resulting from the experimental analysis.     

固定效应部分线性可加面板数据模型的惩罚二次推断估计

具有较强解释力和灵活性的部分线性可加面板数据模型在各学科领域应用广泛.针对个体内存在相关结构的固定效应部分线性可加面板数据模型,本文在结合幂样条函数和最小二乘虚拟变量(LSDV)法的基础上,利用惩罚二次推断函数(PQIF)法对模型进行估计,在一定的正则条件下,证明了参数估计的渐近正态性和非参数估计的收敛性,Monte Carlo数值模拟显示所述估计方法具有良好的有限样本表现,同时,我们还将估计技术应用于实际数据分析中.     

静态随机访问存储器型现场可编程门阵列辐照效应测试系统研制

在调研静态随机访问存储器型现场可编程门阵列(FPGA)器件空间辐照效应失效机理的基础上,详细论述FPGA辐照效应测试系统内部存储器测试、功能测试及功耗测试的实现原理,给出了系统的软硬件实现方法。所建立的系统可以测试FPGA器件的配置存储器翻转截面、块存储器翻转截面、功能失效截面、闭锁截面等多个参数,其长线传输距离达到50 m以上,最大可测门数达到了100万门,为FPGA辐照效应研究提供了测试平台。     

The impact of customer returns on pricing and order decisions

In this paper, we address the simultaneous determination of price and inventory replenishment when customers return product to the firm. We examine cases when the quantity of returned product is a function of both the quantity sold and the price, in single and multi-period problems, with and without uncertainty in demand.