A class of test statistics for testing whether new is better than used

Interval censored (IC) failure time data are often observed in medical follow-up studies and clinical trials where subjects can only be followed periodically, and the failure time can only be known to lie in an interval. In this paper, we propose a weighted Wilcoxon-type rank test for the problem of comparing two IC samples. Under a very general sampling technique developed by Fay (1999), the mean and variance of the test statistics under the null hypothesis can be derived. Through simulation studies, we find that the performance of the proposed test is better than that of the two existing Wilcoxon-type rank tests proposed by Mantel (1967) and R. Peto and J. Peto (1972). The proposed test is illustrated by means of an example involving patients in AIDS cohort studies.

Download Full-text

Exploring the Benefit of Blogs Dependency for Assessing Students’ Intellectual Achievement

Journal of Education Society and Behavioural Science ◽

10.9734/jesbs/2021/v34i130298 ◽

2021 ◽

pp. 123-131

Author(s):

Imran Ademola Adeleke ◽

Ismail Olaniyi Muraina

Keyword(s):

Social Media ◽

High Performance ◽

Teaching And Learning ◽

Test Statistics ◽

Paper Test ◽

Traditional Assessment ◽

The Social ◽

Intellectual Achievement ◽

Teacher's Knowledge ◽

Better Than

Blogs stand out among many social media that allows teacher and students to maintain a running dialogue in various aspect of the teaching and learning process. It comes in form of thoughts, ideas, tests, short-works/homework and assignment to enhance interactivity between the teacher’s knowledge base and students’ comments and reflections. This paper promotes the use of blogs in assessing students’ intellectuals while comparing the use of blogging for assessment as well as the use of traditional assessment. The study stresses scoring on paper versus scoring on blogs, students that we're able to complete their visitation of the blogs were noted to enjoy and benefit greatly compare to those that could not finish theirs and whether the performance of male bloggers may be different from that of female bloggers. 45 students involved in this study from among degree students of Achievers University. The research study was done within a semester. The achievement test was the major instrument used to collect data from the same students that were exposed to two different tests (Paper Test/Traditional Test and Blogging Test) after proper classroom teaching. The results got were analyzed using mean, SD and T-test statistics. From the findings, it was succinctly shown that the scores of students engaged in blogs far better than when they initially tested traditionally. In the same trend, those students that completed their test on blogs demonstrated high performance than their counterparts that could not. Further, the results also made it crystal clear that students were distributed equally on blogging regardless of their gender differences. The findings from the interview conducted established the fact that the use of a blog for assessment saves student time, the distance for learning and having quick result as feedback. The student has a high interest in the use of a blog for academic purposes rather than only the social affairs of the student. The paper contributes to the existing knowledge by turning blogs as social media into academic media that can foster the academic achievement of students and can also be used to assess students better than traditional assessment.

Download Full-text

A Comparative Study of EDF Tests for Normality and Exponentiality

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.2004 ◽

2014 ◽

Vol 602-605 ◽

pp. 2004-2010

Author(s):

Yan Su ◽

Xia Ying Su

Keyword(s):

Monte Carlo ◽

Test Statistics ◽

Exponential Distributions ◽

Test Procedures ◽

Unknown Parameters ◽

Monte Carlo Algorithms ◽

Wide Range ◽

Anderson Darling ◽

Tests For Normality ◽

Better Than

In this paper, the modified EDF test procedures for testing the normal and exponential distributions with unknown parameters are suggested. The Monte Carlo algorithms are given to approximate the critical values of the EDF test statistics for a wide range of sample sizes. The power simulations show that the Anderson-Darling (AD) test is on the whole better than other EDF tests considered, in particular when the alternative departs from the true distribution in the tails.

Download Full-text

Comparison of Anti-Xa and Dilute Russell Viper Venom Time Assays in Quantifying Drug Levels in Patients on Therapeutic Doses of Rivaroxaban

Archives of Pathology & Laboratory Medicine ◽

10.5858/arpa.2013-0750-oa ◽

2014 ◽

Vol 138 (12) ◽

pp. 1680-1684 ◽

Cited By ~ 24

Author(s):

Robert C. Gosselin ◽

Dorothy M. (Adcock) Funk ◽

J. Michael Taylor ◽

Suzanne J. Francart ◽

Emily M. Hawes ◽

...

Keyword(s):

Plasma Concentrations ◽

Activated Partial Thromboplastin Time ◽

Test Statistics ◽

Coagulation Assays ◽

Routine Monitoring ◽

New Oral Anticoagulant ◽

Therapeutic Doses ◽

Paired T Test ◽

Better Than ◽

Routine Coagulation

Context Rivaroxaban is a new oral anticoagulant that functions as a direct anti-Xa inhibitor. Although routine monitoring is not required, measurement of plasma concentrations may be necessary in certain clinical situations. Routine coagulation assays, such as the prothrombin time and, to a lesser degree, activated partial thromboplastin time, correlate with drug concentration, but because of reagent variability, these methods are not reliable for determining rivaroxaban anticoagulation. Objective To compare different methods and calibrators for measuring rivaroxaban, including the chromogenic anti-Xa assay, which, when calibrated with a rivaroxaban standard, may be more appropriate for determining anticoagulation. Design We compared measured rivaroxaban concentrations with the same anti-Xa kit but used different calibrators, with different anti-Xa kits but the same calibrators, with antithrombin-supplemented anti-Xa kit versus nonsupplemented kits, and with 2 methods based on rivaroxaban-calibrated, high-phospholipid, dilute Russell viper venom time. Regression and paired t test statistics were used to determine correlation and significant differences among methods and calibrator sources. Results Although there was strong correlation, statistically significant biases existed among methods that report rivaroxaban levels. A single-source calibrator did not alleviate those differences among methods. High-phospholipid Russell viper venom reagents correlated with rivaroxaban concentration but were not better than chromogenic anti-Xa methods. Conclusions Rivaroxaban-calibrated, anti-Xa measurements correlate well, but the clinical significance of the variation with rivaroxaban measurements is uncertain. The antithrombin-supplemented, anti-Xa method should be avoided for measuring rivaroxaban.

Download Full-text

Nonparametric Tests for the Umbrella Alternative with Unknown Peak in a Mixed Design

Asian Journal of Probability and Statistics ◽

10.9734/ajpas/2020/v7i330182 ◽

2020 ◽

pp. 1-13

Author(s):

Hassan Alsuhabi ◽

Rhonda Magel

Keyword(s):

Simulation Study ◽

Nonparametric Tests ◽

Asymptotic Distributions ◽

Test Statistics ◽

Mixed Design ◽

Randomized Design ◽

Umbrella Alternative ◽

Unknown Peak ◽

Completely Randomized Design ◽

Better Than

Aims: Introducing and comparing 4 different tests for the unknown umbrella alternative in a mixed design. Study Design: Simulation study consisting of a randomized complete block portion and a completely randomized design portion for various underlying distributions. Place and Duration of Study: Simulation Study – conducted at North Dakota State University from September 2018 through December 2019. Methodology: This paper proposes four non-parametric tests for testing the umbrella alternative with unknown peak when the data are mixture of a randomized complete block and a completely randomized design. The proposed tests are various combinations of a modified (unmodified) Mack-Wolfe’s test and a modified (unmodified) Kim-Kim’s test, respectively. In this paper, the proposed tests are an extension of Magel et al. (2010) and Hassan and Magel (2020) peak known tests to the unknown peak setting. The four proposed test statistics are compared to each other. Results: When there were 3 populations, the unmodified versions of the test statistics did better than the modified versions. When there were 4 and 5 populations, the results varied. Conclusion: All of the test statistics reached their asymptotic distributions quickly. The standardize first versions of the test statistics were generally better than the standardized last version of the test statistics, which meant that it was better to place equal weights on the RCBD portion and the CRD portion.

Download Full-text

Better-than-chance classification for signal detection

Biostatistics ◽

10.1093/biostatistics/kxz035 ◽

2019 ◽

Author(s):

Jonathan D Rosenblatt ◽

Yuval Benjamini ◽

Roee Gilron ◽

Roy Mukamel ◽

Jelle J Goeman

Keyword(s):

Signal Detection ◽

Statistical Test ◽

Supervised Machine Learning ◽

Test Statistics ◽

Test Statistic ◽

Accuracy Test ◽

Bona Fide ◽

Leave One Out ◽

Signal Accuracy ◽

Better Than

Summary The estimated accuracy of a classifier is a random quantity with variability. A common practice in supervised machine learning, is thus to test if the estimated accuracy is significantly better than chance level. This method of signal detection is particularly popular in neuroimaging and genetics. We provide evidence that using a classifier’s accuracy as a test statistic can be an underpowered strategy for finding differences between populations, compared to a bona fide statistical test. It is also computationally more demanding than a statistical test. Via simulation, we compare test statistics that are based on classification accuracy, to others based on multivariate test statistics. We find that the probability of detecting differences between two distributions is lower for accuracy-based statistics. We examine several candidate causes for the low power of accuracy-tests. These causes include: the discrete nature of the accuracy-test statistic, the type of signal accuracy-tests are designed to detect, their inefficient use of the data, and their suboptimal regularization. When the purpose of the analysis is the evaluation of a particular classifier, not signal detection, we suggest several improvements to increase power. In particular, to replace V-fold cross-validation with the Leave-One-Out Bootstrap.

Download Full-text

The Implementation of Group Investigation Learning Model Through Domino Mathematics Media on the Rank Number and Root Form Materials

Malikussaleh Journal of Mathematics Learning (MJML) ◽

10.29103/mjml.v4i1.3118 ◽

2021 ◽

Vol 4 (1) ◽

pp. 28

Author(s):

Cut Yuniza Eviyanti ◽

Lia Rista ◽

Siti Hadijah ◽

A Andriani

Keyword(s):

Data Processing ◽

Learning Model ◽

Control Group ◽

Test Statistics ◽

Learning Models ◽

Entire Class ◽

Rank Number ◽

Randomized Control ◽

And Control ◽

Better Than

This study aims to find out the results of students' learning through the implementation of a group investigation learning model through mathematical domino media better than the implementation of a conventional learning model on the rank number and root form materials. The research was a quasi-experiment with the design of a randomized control group pretest-posttest. The population of this research is the entire class IX SMP Negeri 1 Lhokseumawe consisting of 9 classes. The research sample was determined by a randomized technique that made 2 classes namely experiment class (IXA) and control class (IXB). The results of the student posttest data test show that the data is distributed normally and homogeneously, so it can be analyzed with one-side t-test statistics at a significant α= 0.05. Based on the results of data processing against the posttest students obtained sig scores. (2-tailed) posttest data is 0.001 which means less than α= 0.05, this means H0 is rejected, so it can be concluded that the learning results of students taught by the group investigation learning model through domino mathematics media are better than conventional learning models on the rank number and root form materials in grade IX of SMP Negeri 1 Lhokseumawe.

Download Full-text

A comparison on two discordancy tests to detect outlier in von mises (VM) sample

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v19.i1.pp156-163 ◽

2020 ◽

Vol 19 (1) ◽

pp. 156

Author(s):

Fatin Najihah Badarisam ◽

Adzhar Rambli ◽

Mohammad Illyas Sidik

Keyword(s):

Real Data ◽

Circular Data ◽

Performance Tests ◽

Simulation Studies ◽

Test Statistics ◽

Data Set ◽

Concentration Parameter ◽

Von Mises ◽

Better Than ◽

Author Knowledge

This paper focuses on comparing two discordancy tests between robust and non-robust statistic to detect a single outlier in univariate circular data. So far, to the best author knowledge that there is no literature make a comparison between both tests of RCDu Statistic and 𝐺1 Statistic. The test statistics are based on the circular median and spacing theory. In addition, those statistics can detect multiple and patches outliers. The performance tests of RCDu Statistic and 𝐺1 Statistic are tested in outlier proportion of correct detection, masking and swamping effect. At the beginning stage, we obtained the cut-off points for the RCDu Statistic and 𝐺1 Statistic by applying Monte Carlo simulation studies. Then, generated sample from von Mises (VM) with the combination of sample size and concentration parameter. The estimating process of cut-off points for both statistics is repeated 3000 times at 10%, 5% and 1% upper percentiles. As a result, the RCDu Statistic perform well in detecting a correct single outlier. Moreover, the RCDu Statistic has a lower masking rate compared to 𝐺1 Statistic. However, the 𝐺1 Statistic is better than RCDu Statistic for swamping effect due to a lower swamping rate. Thus, RCDu Statistic performs better than 𝐺1 Statistic in detecting a single outlier for von Mises (VM) sample. As an illustration, both statistics were applied to the real data set from a conducted experiments series to investigate the northen cricket frogs homing ability.

Download Full-text

Multi-Unknown Breaks Estimates in Presence of Fractional White Noise Disturbance

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.385-386.1480 ◽

2013 ◽

Vol 385-386 ◽

pp. 1480-1483

Author(s):

Deng Lu

Keyword(s):

White Noise ◽

Limit Distribution ◽

Long Memory ◽

Alternative Hypothesis ◽

Test Statistics ◽

Finite Sample ◽

Sample Property ◽

Trend Breaks ◽

Mean Trend ◽

Better Than

This paper analyzes the distribution of breaks estimators and finite sample property of the method based on different mean break and long memory situations based on Bai and Perron (1998) multi-unknown breaks method. As to the distribution of the multiple break estimates, the property of the estimates under the alternative hypothesis is better when d is close to-0.5 that the bias and variance are smaller and the distribution are smoother even better than the BP (1998) case. Further work can be made on the limit distribution of break number test statistics in the case of d (-0.5, 0), d (0, 0.5) and to the case of three and more mean, trend breaks.

Download Full-text

Time and Latitude in South Africa

International Astronomical Union Colloquium ◽

10.1017/s0252921100026816 ◽

1972 ◽

Vol 1 ◽

pp. 27-38

Author(s):

J. Hers

Keyword(s):

South Africa ◽

Cape Town ◽

Astronomical Observations ◽

Royal Observatory ◽

The Republic ◽

Astronomical Determination ◽

Limited Accuracy ◽

Better Than

In South Africa the modern outlook towards time may be said to have started in 1948. Both the two major observatories, The Royal Observatory in Cape Town and the Union Observatory (now known as the Republic Observatory) in Johannesburg had, of course, been involved in the astronomical determination of time almost from their inception, and the Johannesburg Observatory has been responsible for the official time of South Africa since 1908. However the pendulum clocks then in use could not be relied on to provide an accuracy better than about 1/10 second, which was of the same order as that of the astronomical observations. It is doubtful if much use was made of even this limited accuracy outside the two observatories, and although there may – occasionally have been a demand for more accurate time, it was certainly not voiced.

Download Full-text