A Practical Guide to Statistical Tests in the Biomedical Field: From Parametric to Nonparametric, Where and How?

Healthcare decisions are based on scientific evidence obtained from medical studies by gathering data and analyzing it to obtain the best results. When analyzing data, biostatistics is a powerful tool, but healthcare professionals lack knowledge in this field. This lack of knowledge can manifest itself in situations such as choosing the wrong statistical test for the right situation or applying a statistical test without checking its assumptions, leading to inaccurate results and misleading conclusions. With the help of this “narrative review”, the aim is to bring biostatistics closer to healthcare professionals by answering certain questions: how to describe the distribution of data? how to assess the normality of data? how to transform data? and how to choose between nonparametric and parametric tests? Through this work, our hope is that the reader will be able to choose the right test for the right situation, in order to obtain the most accurate results.

Lottery Numbers and Ordered Statistics

The lottery has long captivated the imagination of players worldwide, offering the tantalizing possibility of life-changing wins. While winning the lottery is largely a matter of chance, as lottery drawings are typically random and unpredictable. Some people use the lottery terminal randomly generates numbers for them, some players choose numbers that hold personal significance to them, such as birthdays, anniversaries, or other important dates, some enthusiasts have turned to statistical analysis as a means to analyze past winning numbers identify patterns or frequencies. In this paper, we use order statistics to estimate the probability of specific order of numbers or number combinations being drawn in future drawings.

On Performance Characteristics of a Nonparametric Subset Selection Procedure with a Small Randomized Block Experimental Design

This article addresses the issue of computing the constant required to implement a specific nonparametric subset selection procedure based on ranks of data arising in a statistical randomized block experimental design. A model of three populations and two blocks is used to compute the probability distribution of the relevant statistic, the maximum of the population rank sums minus the rank sum of the “best” population. Calculations are done for populations following a normal distribution, and for populations following a bi-uniform distribution. The least favorable configuration in these cases is shown to arise when all three populations follow identical distributions. The bi-uniform distribution leads to an asymptotic counterexample to the conjecture that the least favorable configuration, i.e., that configuration minimizing the probability of a correct selection, occurs when all populations are identically distributed. These results are consistent with other large-scale simulation studies. All relevant computational R-codes are provided in appendices.

Comparison of Block Design Nonparametric Subset Selection Rules Based on Alternative Scoring Rules

This article compares the size of selected subsets using nonparametric subset selection rules with two different scoring rules for the observations. The scoring rules are based on the expected values of order statistics of the uniform distribution (yielding rank values) and of the normal distribution (yielding normal score values). The comparison is made using state motor vehicle traffic fatality rates, published in a 2016 article, with fifty-one states (including DC as a state) and over a nineteen-year period (1994 through 2012). The earlier study considered four block design selection rules—two for choosing a subset to contain the “best” population (i.e., state with lowest mean fatality rate) and two for the “worst” population (i.e., highest mean rate) with a probability of correct selection chosen to be 0.90. Two selection rules based on normal scores resulted in selected subset sizes substantially smaller than corresponding rules based on ranks (7 vs. 16 and 3 vs. 12). For two other selection rules, the subsets chosen were very close in size (within one). A comparison is also made using state homicide rates, published in a 2022 article, with fifty states and covering eight years. The results are qualitatively the same as those obtained with the motor vehicle traffic fatality rates.

Effect Evaluation of CBL Combined with Rain Classroom Teaching Method in Medical Statistics

Objective: To explore the application effect of CBL combined with rain classroom teaching method in medical statistics courses. Methods: The undergraduate students of medical imaging technology in 2019 and 2020 in a university were selected as the research objects. A cluster sampling method was used to select 79 undergraduate students from 2019 in the control group and 75 undergraduate students from 2020 in the experimental group. Traditional teaching method and CBL combined with rain classroom teaching method was used in the control group and experimental group respectively. The final examination scores of the two groups were compared. In experimental group, the correlation between the average score in the rain classroom and the final examination score was tested, and the teaching effect was evaluated. Results: The average score of final examination in experimental group and control group was 79.13 ± 10.32 points and 71.54 ± 14.752 points, respectively, which had a statistically significant difference (Z = 2.586, P = 0.012);the final examination scores of the students in the experimental group were positively correlated with the average scores of the rain classroom (r = 0.372, P = 0.001), and the proportion of satisfaction in the experimental group was 94.7%. Conclusion: The CBL combined with rain classroom teaching method can improve the teaching effectiveness of medical statistics courses.

Innovations and Challenges in Economic Census Methodology:A Study by the Bureau of Statistics

The Bureau of Statistics has demonstrated a forward-looking strategic approach in its economic census.By leveraging dual innovations in technology and management,and incorporating modern technologies such as big data,cloud computing,and the Internet of Things,it has deepened the reform of the census methodology.Additionally,the Bureau has built a multi-dimensional collaborative network that enhances international cooperation,departmental coordination,and public participation.This approach not only addresses the limitations of traditional statistical methods in a complex economic environment but also improves data quality and census efficiency,providing an accurate and reliable foundation for national economic decision-making.

Research on the Application of PBL+SPOC Blended Teaching Model in Probability and Statistics Course

To cultivate talents with an exploratory spirit and practical skills in the era of information technology,it is imperative to reform teaching methods and approaches.In the teaching process of the Probability and Statistics course,an application-oriented blended teaching model combining problem-based learning and small private online course was explored.By organizing and implementing online and offline teaching activities based on problem-based learning,a multidimensional process-oriented learning assessment system was established.Practice has shown that this model can effectively enhance classroom teaching effectiveness,benefiting the improvement of students’overall skills and mathematical literacy.

Integration of Ideological and Political Education into the Probability Theory and Mathematical Statistics Course:A Teaching Design Based on Estimation and Hypothesis Testing

With the rapid development of higher education in China,colleges and universities are facing new challenges and impacts in talent training.Probability Theory and Mathematical Statistics is one of the important courses in higher education for science and engineering majors and economics and management majors.Its critical role in cultivating students’thinking skills and improving their problem-solving skills is self-evident.Course ideological and political education construction is an important link in college talent training work.Combining ideological and political education with course teaching can help students establish correct value concepts and play a certain role in improving their comprehensive ability and quality.At present,the construction of ideological and political education in the Probability Theory and Mathematical Statistics course still faces some problems,mainly manifested in the lack of attention paid by teachers to course ideological and political education,insufficient exploitation of ideological and political elements,and the simplification of ideological and political education implementation methods.In order to comprehensively deepen the construction of course ideological and political education in line with the actual needs of Probability Theory and Mathematical Statistics course teaching,we should strengthen the construction of teacher teams,improve teachers’ability to carry out course ideological and political education,integrate educational resources,develop educational resources for ideological and political education,and innovate teaching methods to improve the overall effect of ideological and political education integration.

Reservoir parameter inversion based on weighted statistics

Variation of reservoir physical properties can cause changes in its elastic parameters. However, this is not a simple linear relation. Furthermore, the lack of observations, data overlap, noise interference, and idealized models increases the uncertainties of the inversion result. Thus, we propose an inversion method that is different from traditional statistical rock physics modeling. First, we use deterministic and stochastic rock physics models considering the uncertainties of elastic parameters obtained by prestack seismic inversion and introduce weighting coefficients to establish a weighted statistical relation between reservoir and elastic parameters. Second, based on the weighted statistical relation, we use Markov chain Monte Carlo simulations to generate the random joint distribution space of reservoir and elastic parameters that serves as a sample solution space of an objective function. Finally, we propose a fast solution criterion to maximize the posterior probability density and obtain reservoir parameters. The method has high efficiency and application potential.

The k Nearest Neighbors Estimator of the M-Regression in Functional Statistics

It is well known that the nonparametric estimation of the regression function is highly sensitive to the presence of even a small proportion of outliers in the data.To solve the problem of typical observations when the covariates of the nonparametric component are functional,the robust estimates for the regression parameter and regression operator are introduced.The main propose of the paper is to consider data-driven methods of selecting the number of neighbors in order to make the proposed processes fully automatic.We use thek Nearest Neighbors procedure(kNN)to construct the kernel estimator of the proposed robust model.Under some regularity conditions,we state consistency results for kNN functional estimators,which are uniform in the number of neighbors(UINN).Furthermore,a simulation study and an empirical application to a real data analysis of octane gasoline predictions are carried out to illustrate the higher predictive performances and the usefulness of the kNN approach.

基于statistics的316L不锈钢柠檬酸钝化工艺正交实验数据分析

从statistics的数据处理能力出发,运用统计学知识对316L不锈钢柠檬酸钝化工艺参数正交实验数据进行分析,找出钝化速率的主要影响因素;柠檬酸含量5wt%、双氧水含量5wt%、钝化时间60 min为最佳的实验方案;双氧水含量为钝化速率的主要影响因素。

Identification of Sewage Monitoring Data Based on Mathematical Statistics

In order to reduce the enormous pressure to environmental monitoring work brought by the false sewage monitoring data, Grubbs method, box plot, t test and other methods are used to make depth analysis to the data, providing a set of technological process to identify the sewage monitoring data, which is convenient and simple.

Collision statistics of clusters:from Poisson model to Poisson mixtures

Clusters traverse a gas and collide with gas particles. The gas particles are absorbed, and the clusters become hosts. If the clusters are size-selected, the number of guests will be Poisson distributed. We review this by showcasing four laboratory procedures that all rely on the validity of the Poisson model. The effects of a statistical distribution of the clusters＇ sizes in a beam of clusters are discussed. We derive the average collision rates. Additionally, we present Poisson mixture models that also involve standard deviations. We derive the collision statistics for common size distributions of hosts and also for some generalizations thereof. The models can be applied to large noble gas clusters traversing doping gas. While outlining how to fit a generalized Poisson to the statistics, we still find even these Poisson models to be often insufficient.

Using Monte Carlo Simulation Technology to Improve Intuitive Effect of Teaching Probability and Mathematical Statistics Course

With the illustration of a specific problem, this paper demonstrates that using Monte Carlo Simulation technology will improve intuitive effect of teaching Probability and Mathematical Statistics course, and save instructors' effort as well.And it is estimated that Monte Carlo Simulation technology will be one of the major teaching methods for Probability and Mathematical Statistics course in the future.

留学生Medical Statistics线上课程建设与远程教学的实践与思考

受政治、经济和全球健康等因素影响,远程教育成为高等教育的一个发展趋势。新冠疫情防控期间,受出入境限制,未能返华的留学生一直以远程教学推进学业,成为其间持续进行远程教学最久的群体。本研究总结临床专业本科留学生主干课程Medical Statistics的校级一流线上课程建设与教学实践,并比较了疫情前后,线下教学与远程教学的留学生期末考试成绩,发现远程教学成绩经历波动后逐渐稳定并接近传统线下教学。本文同时对效果影响因素进行了调研和分析,发现“充分学习和使用远程课程中丰富的资源”和“上网是否容易”是留学生学习效果的主要影响因素。提出建设丰富教学资源对促进医学统计学远程学习效果的重要影响,同时提出对策建议,以期进一步提高远程教学水平,服务高校现代化课程体系建设。

Asymptotic Analysis for U-Statistics and Its Application to Von Mises Statistics

Let - be i.i.d. random variables taking values in a measurable space ( Χ, B ). Let φ1: Χ →□ and φ: Χ2→□ be measurable functions. Assume that φ is symmetric, i.e. φ(x,y)=φ(y.x), for any x,y∈Χ . Consider U-statistic, assuming that Eφ1(Χ)=0, Eφ(x, X)=0 for all x∈X, Eφ2(x,X)<∞, Eφ21(X)<∞. We will provide bounds for ΔN=supx|F(x)-F0(x)-F1(x)|, where F is a distribution function of T and F0 , F1 are its limiting distribution function and Edgeworth correction respectively. Applications of these results are also provided for von Mises statistics case.

Apples, oranges and lemons: public sector debt statistics in the 21st century

In both academic research and policymaking,public sector debt and debt-to-GDP ratios are relied on for a multitude of important economic,political and socioeconomic decisions,especially as public sector balance sheets expand to an unprecedented size in the midst of the 2019–2020 COVID pandemic.The reliance on available data from reputable sources often overlooks the question of whether the denominator in this ratio is accurately measured or how well the denominator is understood by the audience interpreting it.Building on past work in international financial statistics,and making use of a unique and newly created dataset on media reporting of public sector debt,the purpose of this article is to examine the quality,accuracy,interpretation and overall meaningfulness of public sector financial statistics.The main findings suggest that i)most of the world’s governments still do not seem to feel sufficient pressure to voluntarily provide comprehensive financial statistics based on well-defined modern methodological frameworks and ii)high profile financial statistics,which are reported,have become increasingly numerous and complicated,making it difficult for non-experts to know which is most appropriate in the context of their analysis.

Tourism Statistics and the Business Register in Italy： A Comparative Analysis and future Outlooks for Integration

After the proposal of a possible insertion of tourism statistics （supply side） （TS） into Framework Regulation Integrating Business Statistics （FR1BS） on which an interesting debate is in progress between Eurostat and NSls, Istat （Italian Institute of Statistics） has started a costs/benefits analysis of this integration. ASIA （Statistical Register of Active Enterprises）, built up by Istat, represents in Italy the official source about the structure and the economic performance of the enterprises. ASIA, whose statistical units are enterprises of industry and services, has been developed through the statistical integration of different administrative sources, other minor archives available （covering particular sectors） and structural business statistics currently produced by Istat. The supply side TS are produced by lstat through surveys via Intermediate Bodies （Local Authorities）： each Intermediate Body has its own local register of accommodation establishments based on Local Kind-of-activity unit （LKAU）. In this paper, the results of a comparative analysis between the statistical units as recorded in ASIA and as surveyed by TS are presented; from first outcomes, considerable issues about data quality appear both at level of coverage for the three Nace groups of the TS （also underlined in the Methodological Manual on Tourism Statistics where for Italy a difference of 70% is reported） and for loss information relating to the location of the activities （switching from LKAU to Enterprises） as well as for timeliness （ASIA has two years of delay）. Then, the administrative local tourism registers （LTR） are analysed to understand： how many they are, their dissemination in the Italian territories, their primary purpose and source, the variables contained, the frequency of updates. This preliminary analysis is needed to identify the operative activities that Istat, together with the Intermediate Bodies, should start to use administrative archives for statistical purposes and to develop a unique tourism satellite archive （TSA）, facing many difficulties related to the reception of several LTR as well as methodological issues for record linkage. On the other hand, a TSA would lead numerous advantages： a unique and official list of internal accommodation establishments; a step towards integration of TS into FRIBS; a starting point to begin to use also administrative data produced by the Italian Police （mandatory communications on guests in the interests of public safety）, having a comparison term to assess their coverage.

Practice and Thoughts on due Statistics for Four Classes of Enterprises Above Designated Size

“Four classes of enterprises above designated size”(hereinafter called four-classes enterprises)refer to objects of statistical survey that have reached a certain scale in China’s current statistical method system,including four classes in national economy,namely,industrial enterprises above designated size,construction and real estate development and management enterprises above qualifications,wholesale and retail,catering and accommodation enterprises,and service enterprises above designated size,which are the primary part of national economic and social development activities.This paper is focused on analyzing the practice and difficulties in the current statistics work of four-classes enterprises,and then this paper proposes some recommendations.

Performance analysis of multi-channel order statistics detector for range-spread target

The problem of two order statistics detection schemes for the detection of a spatially distributed target in white Gaussian noise are studied.When the number of strong scattering cells is known,we first show an optimal detector,which requires many processing channels.The structure of such optimal detector is complex.Therefore,a simpler quasi-optimal detector is then introduced.The quasi-optimal detector,called the strong scattering cells’ number dependent order statistics（SND-OS） detector,takes the form of an average of maximum strong scattering cells with a known number.If the number of strong scattering cells is unknown in real situation,the multi-channel order statistics（MC-OS） detector is used.In each channel,a various number of maximums scattered from target are averaged.Then,the false alarm probability analysis and thresholds sets for each channel are given,following the detection results presented by means of Monte Carlo simulation strategy based on simulated target model and three measured targets.In particular,the theoretical analysis and simulation results highlight that the MC-OS detector can efficiently detect range-spread targets in white Gaussian noise.