Age,blood tests and comorbidities and AIMS65 risk scores outperform Glasgow-Blatchford and pre-endoscopic Rockall score in patients with upper gastrointestinal bleeding

BACKGROUND Upper gastrointestinal(GI)bleeding is a life-threatening condition with high mortality rates.AIM To compare the performance of pre-endoscopic risk scores in predicting the following primary outcomes:In-hospital mortality,intervention(endoscopic or surgical)and length of admission(≥7 d).METHODS We performed a retrospective analysis of 363 patients presenting with upper GI bleeding from December 2020 to January 2021.We calculated and compared the area under the receiver operating characteristics curves(AUROCs)of Glasgow-Blatchford score(GBS),pre-endoscopic Rockall score(PERS),albumin,international normalized ratio,altered mental status,systolic blood pressure,age older than 65(AIMS65)and age,blood tests and comorbidities(ABC),including their optimal cut-off in variceal and non-variceal upper GI bleeding cohorts.We subsequently analyzed through a logistic binary regression model,if addition of lactate increased the score performance.RESULTS All scores had discriminative ability in predicting in-hospital mortality irrespective of study group.AIMS65 score had the best performance in the variceal bleeding group(AUROC=0.772;P<0.001),and ABC score(AUROC=0.775;P<0.001)in the non-variceal bleeding group.However,ABC score,at a cut-off value of 5.5,was the best predictor(AUROC=0.770,P=0.001)of inhospital mortality in both populations.PERS score was a good predictor for endoscopic treatment(AUC=0.604;P=0.046)in the variceal population,while GBS score,(AUROC=0.722;P=0.024),outperformed the other scores in predicting surgical intervention.Addition of lactate to AIMS65 score,increases by 5-fold the probability of in-hospital mortality(P<0.05)and by 12-fold if added to GBS score(P<0.003).No score proved to be a good predictor for length of admission.CONCLUSION ABC score is the most accurate in predicting in-hospital mortality in both mixed and non-variceal bleeding population.PERS and GBS should be used to determine need for endoscopic and surgical intervention,respectively.Lactate can be used as an additional tool to risk scores for predicting inhospital mortality.

MAXIMUM TEST FOR A SEQUENCE OF QUADRATIC FORM STATISTICS ABOUT SCORE TEST IN LOGISTIC REGRESSION MODEL

This article proposes the maximum test for a sequence of quadratic form statistics about score test in logistic regression model which can be applied to genetic and medicine fields.Theoretical properties about the maximum test are derived.Extensive simulation studies are conducted to testify powers robustness of the maximum test compared to other two existed test.We also apply the maximum test to a real dataset about multiple gene variables association analysis.

Analysis of College Students’ Test Scores Based on Two-Component Mixed Generalized Normal Distribution

In order to improve the fitting accuracy of college students’ test scores, this paper proposes two-component mixed generalized normal distribution, uses maximum likelihood estimation method and Expectation Conditional Maxinnization (ECM) algorithm to estimate parameters and conduct numerical simulation, and performs fitting analysis on the test scores of Linear Algebra and Advanced Mathematics of F University. The empirical results show that the two-component mixed generalized normal distribution is better than the commonly used two-component mixed normal distribution in fitting college students’ test data, and has good application value.

Scoring and Consequential Validity Evidence of Computer-and Paper-Based Writing Tests in Times of Change

Little is known about how the assessment modality,i.e.,computer-based(CB)and paper-based(PB)tests,affects language teachers’scorings,perceptions,and preferences and,therefore,the validity and fairness of classroom writing assessments.The present mixed-methods study used Shaw and Weir’s(2007)sociocognitive writing test validation framework to examine the scoring and consequential validity evidence of CB and PB writing tests in EFL classroom assessment in higher education.Original handwritten and word-processed texts of 38 EFL university students were transcribed to their opposite format and assessed by three language lecturers(N=456 texts,152 per teacher)to examine the scoring validity of CB and PB tests.The teachers’perceptions of text quality and preferences for assessment modality accounted for the consequential validity evidence of both tests.Findings revealed that the assessment modality impacted teachers’scorings,perceptions,and preferences.The teachers awarded higher scores to original and transcribed handwritten texts,particularly text organization and language use.The teachers’perceptions of text quality differed from their ratings,and physical,psychological,and experiential characteristics influenced their preferences for assessment modality.The results have implications for the validity and fairness of CB and PB writing tests and teachers’assessment practices.

Study on Key Biological Indicators of Diabetes Based on Statistical Tests

Normality testing is a fundamental hypothesis test in the statistical analysis of key biological indicators of diabetes.If this assumption is violated,it may cause the test results to deviate from the true value,leading to incorrect inferences and conclusions,and ultimately affecting the validity and accuracy of statistical inferences.Considering this,the study designs a unified analysis scheme for different data types based on parametric statistical test methods and non-parametric test methods.The data were grouped according to sample type and divided into discrete data and continuous data.To account for differences among subgroups,the conventional chi-squared test was used for discrete data.The normal distribution is the basis of many statistical methods;if the data does not follow a normal distribution,many statistical methods will fail or produce incorrect results.Therefore,before data analysis and modeling,the data were divided into normal and non-normal groups through normality testing.For normally distributed data,parametric statistical methods were used to judge the differences between groups.For non-normal data,non-parametric tests were employed to improve the accuracy of the analysis.Statistically significant indicators were retained according to the significance index P-value of the statistical test or corresponding statistics.These indicators were then combined with relevant medical background to further explore the etiology leading to the occurrence or transformation of diabetes status.

Testing Result Statistics-Based Rapid Testing Method for Safety-Critical System

Safety-critical system （SCS） has highly demand for dependability, which requires plenty of resource to ensure that the system under test （SUT） satisfies the dependability requirement. In this paper, a new SCS rapid testing method is proposed to improve SCS adaptive dependability testing. The result of each test execution is saved in calculation memory unit and evaluated as an algorithm model. Then the least quantity of scenario test case for next test execution will be calculated according to the promised SUT＇s confidence level. The feedback data are generated to weight controller as the guideline for the further testing. Finally, a compre- hensive experiment study demonstrates that this adaptive testing method can really work in practice. This rapid testing method, testing result statistics-based adaptive control, makes the SCS dependability testing much more effective.

Assessment of cardiovascular risk in diabetes:Risk scores and provocative testing

Cardiovascular disease(CVD) is the leading cause of morbidity and mortality among patients with diabetes mellitus,who have a risk of cardiovascular mortality two to four times that of people without diabetes.An individualised approach to cardiovascular risk estimation and management is needed.Over the past decades,many risk scores have been developed to predict CVD.However,few have been externally validated in a diabetic population and limited studies have examined the impact of applying a prediction model in clinical practice.Currently,guidelines are focused on testing for CVD in symptomatic patients.Atypical symptoms or silent ischemia are more common in the diabetic population,and with additional markers of vascular disease such as erectile dysfunction and autonomic neuropathy,these guidelines can be difficult to interpret.We propose an algorithm incorporating cardiovascular risk scores in combination with typical and atypical signs and symptoms to alert clinicians to consider further investigation with provocative testing.The modalities for investigation of CVD are discussed.

TESTS OF ELLIPTICAL SYMMETRY AND THE ASYMPTOTIC TAIL BEHAVIOR OF THE STATISTICS

In this paper, some test statistics of Kolmogorov type and Cramervon Mises type based on projection pursuit technique are proposed for testing the sphericity problem of a high\|dimensional distribution. The limiting distributions of the test statistics are derived under the null hypothesis. The asymptotic properties of Bootstrap approximation are investigated and the tail behaviors of the statistics are studied.

A Gene Score Test for Disease Association with Multiple Genes

The traditional method for creating a gene score to predict a given outcome is to use the most statistically significant single nucleotide polymorphisms (SNPs) from all SNPs which were tested. There are several disadvantages of this approach such as excluding SNPs that do not have strong single effects when tested on their own but do have strong joint effects when tested together with other SNPs. The interpretation of results from the traditional gene score may lack biological insight since the functional unit of interest is often the gene, not the single SNP. In this paper we present a new gene scoring method, which overcomes these problems as it generates a gene score for each gene, and the total gene score for all the genes available. First, we calculate a gene score for each gene and second, we test the association between this gene score and the outcome of interest (i.e. trait). Only the gene scores which are significantly associated with the outcome after multiple testing correction for the number of gene tests (not SNPs) are considered in the total gene score calculation. This method controls false positive results caused by multiple tests within genes and between genes separately, and has the advantage of identifying multi-locus genetic effects, compared with the Bonferroni correction, false discovery rate (FDR), and permutation tests for all SNPs. Another main feature of this method is that we select the SNPs, which have different effects within a gene by using adjustment in multiple regressions and then combine the information from the selected SNPs within a gene to create a gene score. A simulation study has been conducted to evaluate finite sample performance of the proposed method.

Test for Homogeneity of Odds Ratios Using <i>U</i>-Statistics

There are a few statistics testing the homogeneity of odds ratios across strata. Asymptotic statistics lose their power in the “sparse-data” setting. Both asymptotic statistics and exact tests have low power when the sample sizes are small. We created a set of U statistics and compared them with some existing statistics in testing homogeneity of OR at different data settings. We evaluated their performance in terms of the empirical size and power via Monto Carlo simulations. Our results showed that two of the U-statistics under our study had higher power for testing homogeneity of odds ratios for 2 by 2 contingency tables. The application of the tests was illustrated in two real examples.

A Comprehensive Guide for Selecting Appropriate Statistical Tests: Understanding When to Use Parametric and Nonparametric Tests

Choosing appropriate statistical tests is crucial but deciding which tests to use can be challenging. Different tests suit different types of data and research questions, so it is important to choose the right one. Knowing how to select an appropriate test can lead to more accurate results. Invalid results and misleading conclusions may be drawn from a study if an incorrect statistical test is used. Therefore, to avoid these it is essential to understand the nature of the data, the research question, and the assumptions of the tests before selecting one. This is because there are a wide variety of tests available. This paper provides a step-by-step approach to selecting the right statistical test for any study, with an explanation of when it is appropriate to use it and relevant examples of each statistical test. Furthermore, this guide provides a comprehensive overview of the assumptions of each test and what to do if these assumptions are violated.

A Comprehensive Guide for Selecting Appropriate Statistical Tests: Understanding When to Use Parametric and Nonparametric Tests

Choosing appropriate statistical tests is crucial but deciding which tests to use can be challenging. Different tests suit different types of data and research questions, so it is important to choose the right one. Knowing how to select an appropriate test can lead to more accurate results. Invalid results and misleading conclusions may be drawn from a study if an incorrect statistical test is used. Therefore, to avoid these it is essential to understand the nature of the data, the research question, and the assumptions of the tests before selecting one. This is because there are a wide variety of tests available. This paper provides a step-by-step approach to selecting the right statistical test for any study, with an explanation of when it is appropriate to use it and relevant examples of each statistical test. Furthermore, this guide provides a comprehensive overview of the assumptions of each test and what to do if these assumptions are violated.

Statistical Tests of the Validation of TCO Satellite Measurements, Recorded Simultaneously by TOMS-OMI (2005) and OMI-OMPS (2012-2018)

Two statistical validation methods were used to evaluate the confidence level of the Total Column Ozone (TCO) measurements recorded by satellite systems measuring simultaneously, one using the normal distribution and another using the Mann-Whitney test. First, the reliability of the TCO measurements was studied hemispherically. While similar coincidences and levels of significance > 0.05 were found with the two statistical tests, an enormous variability in the levels of significance throughout the year was also exposed. Then, using the same statistical comparison methods, a latitudinal study was carried out in order to elucidate the geographical distribution that gave rise to this variability. Our study reveals that between the TOMS and OMI measurements in 2005 there was only a coincidence in 50% of the latitudes, which explained the variability. This implies that for 2005, the TOMS measurements are not completely reliable, except between the -50° and -15° latitude band in the southern hemisphere and between +15° and +50° latitude band in the northern hemisphere. In the case of OMI-OMPS, we observe that between 2011 and 2016 the measurements of both satellite systems are reasonably similar with a confidence level higher than 95%. However, in 2017 a band with a width of 20° latitude centered on the equator appeared, in which the significance levels were much less than 0.05, indicating that one of the measurement systems had begun to fail. In 2018, the fault was not only located in the equator, but was also replicated in various bands in the Southern Hemisphere. We interpret this as evidence of irreversible failure in one of the measurement systems.

Multiple z-Score Based Method for Noninvasive Prenatal Test Using Cell-Free DNA in Maternal Plasma

Objective: To improve the detecting accuracy of chromosomal aneuploidy of fetus by non-invasive prenatal testing (NIPT) using next generation sequencing data of pregnant women’s cell-free DNA. Methods: We proposed the multi-Z method which uses 21 z-scores for each autosomal chromosome to detect aneuploidy of the chromosome, while the conventional NIPT method uses only one z-score. To do this, mapped read numbers of a certain chromosome were normalized by those of the other 21 chromosomes. Average and standard deviation (SD), which are used for calculating z-score of each sample, were obtained with normalized values between all autosomal chromosomes of control samples. In this way, multiple z-scores can be calculated for 21 autosomal chromosomes except oneself. Results: Multi-Z method showed 100% sensitivity and specificity for 187 samples sequenced to 3 M reads while the conventional NIPT method showed 95.1% specificity. Similarly, for 216 samples sequenced to 1 M reads, Multi-Z method showed 100% sensitivity and 95.6% specificity and the conventional NIPT method showed a result of 75.1% specificity. Conclusion: Multi-Z method showed higher accuracy and robust results than the conventional method even at low coverage reads.

现代数理统计中假设检验的教学探讨

假设检验是现代概率论与数理统计教学中的重要内容和知识点,而假设检验包含建立原假设、构造统计量、计算概率分布、确定临界值和得出结论等过程。在教学过程中,很多教师都忽视建立原假设这个方面。由于没有强调原假设设计方法,学生碰到此类问题很容易产生疑惑出错。实际上,原假设的三个选择是不可以随意互换的,需要通过阅读问题,依据“小概率事件原理”来选择合适的假设。通过对假设检验中单边检验真题案例的教学探讨和分析,完成对原假设存在的三个选择的不同分析,然后对得到的结果进行比较。分析探讨在假设检验教学中做原假设和备择假设设计时,需要结合题目要求,按照“小概率事件原理”来设计假设的方案,促进学生对此问题的理解,并且在实际教学应用中取得良好的效果。

基于Dynaform的汽车后风窗罩板成形工艺参数优化研究

文中以某汽车后风窗罩板为研究对象,解决其成形过程中的破裂和回弹缺陷。首先,运用Dynaform软件构建了符合实际工况的仿真模型;然后,选择对成形质量影响较大的模具间隙、摩擦因数、压边力和冲压速度作为主要因素,设计了4因素4水平的正交试验方案,并进行了仿真分析;接着,以最大减薄率和回弹作为评价指标进行综合评分,并采用Minitab软件对综合评分进行均值分析,获得了影响成形质量的各因素的主次关系和最优冲压工艺参数组合:摩擦因数为0.085,冲压速度为5000 mm/s,压边力为65 kN,模具间隙为1.15 mm;最后,选用上述工艺参数进行仿真分析和生产验证,产品拉延区域未出现破裂的成形缺陷,左右两端的弧形位置未见明显回弹。

电连接器用聚氨酯胶密封件贮存可靠性统计模型的加速试验验证与评估

针对电连接器用聚氨酯胶密封件在长贮条件下的寿命评估问题,从机理层面分析了聚氨酯胶密封件内聚破坏和边界破坏导致性能下降的原因。依据从机理层面建立的电连接器用聚氨酯胶密封件贮存可靠性统计模型,利用聚氨酯胶密封件温湿度综合应力加速退化试验数据,综合应用粒子群优化算法和回归分析、AD检验及拟合优度等检验方法,从数据统计层面验证了电连接器用聚氨酯胶密封件失效物理方程和退化轨迹模型的合理性。利用扫描电镜和能谱分析验证了失效机理分析的正确性。最后,利用所建模型评估了电连接器用聚氨酯胶密封件在贮存环境下的可靠寿命。

医学类本科生、硕士研究生医学统计学学习态度及其与考试成绩的关系

目的调查某医科大学医学类本科生、硕士研究生医学统计学学习态度现状,探索影响因素,分析其与考试成绩的关系,为提高医学统计学教学质量提供思路和依据。方法以内蒙古某医科大学2021年秋季学期开设医学统计学课程的本科生和硕士研究生为调查对象,调查并分析学生基本信息和医学统计学学习态度。结果多重线性回归分析显示,性别、学历与学生医学统计学学习态度无关;数学能力越强、学习时长越长,医学统计学学习态度越积极。相关性分析显示,学习时长与医学统计学考试成绩呈正相关关系。结论学生医学统计学学习态度不太积极,存在畏难情绪。数学能力、学习时长对医学统计学学习态度产生影响,学习积极性与考试成绩呈正相关关系;不同学历学生的学习时长均与考试成绩呈正相关关系。建议针对不同学历的学生开展针对性教学,在提高学习积极性的同时,利用多元化教学方式,不断进行统计学技能训练,加深学生对医学统计学知识的理解。

机器学习在人工增雨效果统计检验中的应用

利用福建省古田人工增雨试验基地2014年1月—2023年1月小时自然降水数据,结合线性拟合、多项式回归和样条回归等多种数学统计方法,开展决策树、支持向量机(SVM)和卷积神经网络(CNN)3种机器学习方法在估测目标区自然降水中的应用研究。目标区和对比区自然雨量关系模型对比结果表明:以区域平均面雨量为统计变量时,CNN和四项式回归效果相对较好,其中CNN的确定系数为0.516,均方根误差为1.097 mm;对平均面雨量进行六次方根变换后,各模型的精准度大幅提升,CNN表现最优,确定系数为0.658,其次为SVM;为克服目标区和对比区雨量时间序列效应及空间分布不均等问题,以面雨量空间格点数据作为研究对象,采用CNN 3种优化器(自适应矩估计、均方根传递和梯度随机下降)算法进行对比,发现基于自适应矩估计优化器建立目标区和对比区雨量关系模型最优,其降水估测值与实测值更接近,均方根误差最小,为0.61 mm。因此,利用CNN方法能够进一步优化目标区和对比区雨量关系模型,可为定量评估人工增雨效果提供参考。