Rank Sum Methods Research Articles

Decision Support System for Selecting Inventory Applications Using the WASPAS and Rank Sum Methods

Inventory applications can help companies monitor, manage, and optimize their inventory. However, the large number of existing inventory applications makes it difficult for companies that want to use inventory applications to choose the right application. This is because to choose an inventory application that suits the company's needs, you have to know each application one by one, so it takes a long time and is difficult to make a choice. This research aims to develop a decision support system for selecting inventory applications by applying the WASPAS (Weighted Aggregated Sum Product Assessment) and Rank Sum approaches. The WASPAS method is used to combine the weights for each criterion and calculate the assessment results based on the product of the criteria values with the appropriate weights. Meanwhile, the Rank Sum weighting technique is used to assign weights or rankings to a number of elements or objects based on their level of importance. Based on the case studies that have been carried out, the results obtained for each alternative include: Zoho Inventory (A4) obtained a value of 0.8531; Onstok (A3) obtained a value of 0.8310; Sortly: Inventory Simplified (A2) obtained a value of 0.7735; BoxHero-Inventory Management (A5) obtained a value of 0.7680; and Shelfit-Inventory Management (A2) obtained a value of 0.6613. In usability testing, we got an average score of 91%, and we can say that the system is suitable for use.

Interval-valued Fermatean fuzzy heronian mean operator-based decision-making method for urban climate change policy for transportation activities

Climate change affects the world. Due to excessive GHG emissions, urban transportation contributes to this threat. Policymakers and authorities want to reduce transportation-related GHG emissions. An imaginary urban area with high transportation-related greenhouse gas emissions, dense, interconnected transportation modes, and a high population density is considered. Istanbul, Turkey meets the criteria of this imaginary place, so the case analysis considers this city. Istanbul’s decision-makers are looking for effective strategies to prioritize urban climate change policy alternatives for transportation activities. Four alternative strategies and 13 criteria are presented in this context. Innovative multi-criteria decision-making (MCDM) method with the interval-valued Fermatean fuzzy sets (IVFFSs) strategies is proposed for advantage-prioritization so decision-makers can select the most effective strategies for policies. Utilizing the IVFFSs, the proposed method effectively tackles the qualitative/quantitative data and uncertain information that occurs in realistic applications. In this study, firstly IVFF-heronian mean operators with their desirable characteristics are presented to aggregate the IVFF information. The proposed operators can overcome the drawbacks of existing IVFF information-based operators by considering the relationships between IVFF numbers. Based on IVFF heronian mean operators, a hybrid decision-making framework is proposed by integrating criteria importance through inter-criteria correlation (CRITIC), rank sum (RS), and the double normalization-based multi-aggregation (DNMA) methods with IVFF information. In this method, the CRITIC and RS methods are implemented to derive the objective and subjective weights of the considered evaluation criteria and DNMA is applied to prioritize urban climate change policy alternatives for transportation activities. Sensitivity and comparative analyses with existing studies confirm the proposed framework. The evaluation results show that the integration of transportation sectors, strategies, and innovations across different urban areas in all regions option has the highest overall utility degree (0.731) among a set of four urban climate change policy alternatives for transportation activities.

Selection of welding robot by multi-criteria decision-making method

Welding is a method to join parts together by a stable connection. Welding is used in many different fields. The limitations of manual welding methods are gradually eliminated when using welding robots. The selection of a welding robot has a great influence on the efficiency of the welding process. Choosers (customers) often encounter problems when choosing among many products that are available in the market. During this study, seven types of robots were given to make a choice including AR700, AR900, AR1440, AR1730, AR2010, MA3120, VA1400 II. These seven options are commonly used in welding processes. There are a variety of different parameters (criteria) used to evaluate each of these robots. However, the value of the criteria in the robots is very different. The selection of a robot that is considered the best should be based on all those criteria. At this point, the selection of robots is called MCDM (Multi-Criteria Decision-Making). In this research, two MCDM methods were used to rank the types of robots: MARCOS (Measurement of Alternatives and Ranking according to COmpromise Solution) and PSI (Preference Selection Index). The determination of important quantities for the criteria has been carried out by various methods, including the MEREC (MEthod based on the Removal Effects of Criteria), EQUAL, ROC (Rank Order Centroid) and RS (Rank Sum) methods. The MARCOS method was used four times corresponding to four different sets of weights. Meanwhile, when using the PSI method, we do not need to calculate the weights for the criteria. All five ranking results indicate the same best alternative. The results indicate that MA3120 is the best one. The two methods MARCOS and PSI are reliable enough to be used when multi-criteria decision-making is required, firstly, in the selection of welding robots.

On the Statistical Testing Methods for Single Laboratory Validation of Qualitative Microbiological Assays with an Unpaired Design.

There exists several statistical methods for detecting a difference of detection rates between alternative and reference qualitative microbiological assays in a single laboratory validation study with an unpaired design. We compared performance of eight methods including Fisher's exact test, unequal variance two-sample t-test, Wilcoxon rank-sum test, z-test, and methods based on Wilson confidence intervals, complementary log-log regression, Firth's logistic regression, and ordinary logistic regression. We first compared the minimum detectable difference in the proportion of detections between the alternative and reference methods among these statistical methods for a varied number of test portions. We then compared power and size of test of these methods using simulated data. Firth's logistic regression and the unequal variance two-sample t-test had the lowest minimum detectable difference and highest power. None of these statistical methods had an estimated size of test always within a 95% confidence interval of the nominal value 0.05 with small numbers of test portions (n = 12, 20, 30). Fisher's exact test, the Wilcoxon rank-sum test, and the z-test were conservative even with a moderately large number of test portions (n = 40), while Firth's logistic regression and the unequal variance two-sample t-test had a size of test closer to 0.05 than other methods. Firth's logistic regression and the unequal variance two-sample t-test are better choices than other competing methods. We recommend the unequal variance two-sample t-test over Firth's logistic regression because the unequal variance two-sample t-test is better known and easier to use. We provide an example using real data.

Farmers knowledge of soil fertility in West-Central Bhutan

Farmers have unique indigenous knowledge on their farming practices and soil management systems which is their basis for farm-level decision making. However, studies capturing relative importance (weightage) of indicators of soil fertility are scarce. In total, 75 households or 24% of the households in Guma block in West-Central Bhutan were surveyed to capture the farmers' perceptions on the indicators of soil fertility. Further in a half-day focused group workshop, pairwise comparison between the soil fertility indicators was performed employing the Analytical Hierarchy Process (AHP) to determine the relative importance of the indicators. Rank sum and rank reciprocal methods were also used to compare with the outcomes of the AHP. The farmers' 10 most important indicators of soil fertility were: crop yield (mentioned by 100% of the households), soil texture (86.7%), soil color (92%), soil compactness (92%), soil depth (48%), response to manure/fertilizer (18.7%), stoniness (17.3%), weediness (18.7%), soil workability (12%) and land slope (14.7%). The workshop results by three methods showed the crop yield to be ≥33.3% weight (value) followed by four indicators of soil texture (≥16.5%), color (≥14.6%), compactness (≥10.9%) and depth (≥6.7%). Farmers soil fertility indicators were found to relate to the attributes that they can measure, see or feel. The key indicators and their relative importance were as crop yield >> soil texture > color > compactness > depth. Crop yield was considered most important because it is easily measureable to the farmers and it reflects the farmers concern for household food security.

Lymphoma images analysis using morphological and non-morphological descriptors for classification

Mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue.

An Age Distribution of D-Dimer Values in Normal Healthy Donor Population: An Indirect Verification of the Age-Adjusted D-Dimer Cutoffs for VTE Exclusion

Introduction: The prevalence of venous thrombosis and pulmonary embolism (VTE) increases with age. Definitive VTE diagnosis or exclusion relies on imaging modalities, which are found to be negative in a high proportion of tested patients. Algorithms based on pretest clinical probability (low and intermediate) in conjunction with negative d-dimer test results have reliably excluded VTE sparing the need for additional imaging studies. Currently, the cutoff for a negative d-dimer is based on reference ranges regardless of age of the donor population. Since baseline d-dimer increases with aging, an age-adjusted d-dimer (AADD) cutoff for patients older than 50 years (age*10 ng/mL FEU) has been shown to improve specificity of diagnosis while still maintaining a high sensitivity (>97%) of detecting VTE/PE (Righini, et al. JAMA, 2014). Due to FDA restrictions, clinical laboratories cannot implement and report such AADD cutoffs. Major hurdles include: AADD cutoffs are assay-dependent, and there is a lack of feasible strategy for laboratories to verify the AADD cutoffs. We hypothesize that an adequate study of age-distribution of baseline d-dimer levels of healthy donors can assist the verification of AADD cutoffs and ultimately ensure patient safety in the VTE patient population.Objective: Establish an age dependent reference range for patients 50 years or older with the HemosIL HS 500 D-dimer reagent on the ACL TOP 700 (Instrumentation Laboratory, Bedford MA, USA); and compare this range with the manufacturer provided and literature recommended AADD cutoffs.Methods: D-dimer assay was performed on plasma samples from normal adult donors per the manufacturers' instructions. D-Dimer age, gender distribution and association were analyzed using non-parametric Wilcoxon rank sum, Kolmogorov-Smirnov tests, and quantile regression methods to estimate the 95th percentile to establish a reference range.Results: We studied 241 healthy donors, ranging from 21-91 years of age. Statistically significant differences between males and females (100 [42%] male) were detected (p-value <0.001; p-value =0.0009). Using CLSI guidelines, these statistical differences (median d-dimer for men = 200, while median d-dimer for women = 300) are not considered clinically significant, since only 6% of women would be outside an overall reference range (CLSI guideline states to partition if over 8% for either group would be outside the overall reference range). Using the quantile regression method, a significant association between d-dimer and age was found at the median (P<0.0001). We then established a reference range (95th percentile) for donors younger than age 50 at 635 ng/mL FEU for both men and women and AADD reference range for patients 50 and older (635 + (age - 50)*10 ng/mL) (Figure 1). This reference range was verified with our sample set, with only 6.2% of donors higher than the established reference limit. If we used the non-AADD cutoff provided by the manufacturer for donors younger than 50 (500 ng/mL FEU) and the literature recommended AADD cutoffs for older donors (age*10 ng/mL FEU), 13.3% of our normal donors were above the limits, resulting in not validating this literature reference range per CLSI guidelines in EP28-A3c. These data imply that if both manufacturer and literature recommended AADD cutoffs were adopted, HemosIL HS 500 D-dimer assay should have sufficient sensitivity and negative predictive value, although with slightly lower specificity than those reported by Righini, et al. for detecting VTE/PE.Conclusion: Our study verifies the association between d-dimer level and age and for the first time, to our knowledge, determined AADD normal range for the HemosIL HS 500 D-dimer assay. The manufacturer and literature recommended AADD cutoffs should provide sufficient sensitivity and negative predictive value for VTE/PE exclusion. [Display omitted] DisclosuresNo relevant conflicts of interest to declare.

Testing a Mixture of Rank Preference Models on Judges' Scores in Paris and Princeton

AbstractRank preference and mixture models have been employed to evaluate the ranks assigned by consumers in taste tests of beans, cheese, crackers, salad dressings, soft drinks, sushi, animal feed, and wine. In many wine tastings, including the famous 1976 Judgment of Paris and the 2012 Judgment of Princeton, judges assign scores rather than ranks, and those scores often include ties. This article advances the application of ranking and mixture models to wine-tasting results by modifying the established use of a Plackett-Luce rank preference model to accommodate scores and ties. The modified model is tested and then employed to evaluate the Paris and Princeton wine-tasting results. Test results show that the mixture model is an accurate predictor of observed rank densities. Results for Paris and Princeton show that the group preference orders implied by the mixture model are highly correlated with the orders implied by widely employed rank-sum methods. However, the mixture model satisfies choice axioms that rank-sum methods do not, it yields an estimate of the proportion of scores that appear to be assigned randomly, and it also yields a preference order based on nonrandom preferences that tasters appear to hold in common. (JEL Classifications: A10, C00, C10, C12, D12)

Antimicrobial Use in Horses Undergoing Colic Surgery

Recommendations for antimicrobial prophylaxis for surgery are well-described in human medicine, but information is limited for veterinary practice. To characterize antimicrobial use in horses undergoing emergency colic surgery. A total of 761 horses undergoing emergency colic surgery (2001-2007). Retrospective case review. Antimicrobial dose and timing, surgical description, and duration of treatment were collected from medical records. Associations between antimicrobial use and the occurrence of fever, incisional inflammation or infection, catheter-associated complications, or Salmonella shedding during hospitalization were analyzed using rank-sum methods and logistic regression. A total of 511 (67.2%) horses received an inappropriate amount of drug preoperatively. Median time from preoperative dose to incision was 70 (IQR 55-90) minutes; median total surgery time was 110 (IQR 80-160) minutes. Seventy-three horses were euthanized under anesthesia because of poor prognosis. Of 688 horses, 438 should have been redosed intraoperatively based on the duration of surgery. Only 8 (1.8%) horses were redosed correctly. Horses remained on perioperative antimicrobials a median of 3 (IQR 2-4.5) days. Antimicrobial therapy was reinstituted in 193 (28.9%) horses, and median days of total treatment were 3.8 (IQR 2-6). Signs that led to reinstituting therapy were fever (OR 3.13, P = .001) and incisional inflammation/infection (OR 2.95, P = .001). Horses in which treatment was reinstituted had 2.3 greater odds of shedding Salmonella (P = .003). Increased surgical time was associated with longer duration of antimicrobial therapy (OR 1.02, P = .001). Despite published recommendations regarding antimicrobial prophylaxis, compliance is poor; improvement might reduce postoperative complications.

Vandetanib, a Dual Inhibitor of Vascular Endothelial Growth Factor Receptor (VEGFR) and Epidermal Growth Factor Receptor (HER1), Potentiates Anti-Tumor Effects of Combined Endocrine and Trastuzumab Treatment in Estrogen Receptor-Positive (ER+)/HER2-Overexpressing Xenografts.

Abstract Background: Compelling evidence suggests that cross-talk between the pathways of ER and HER1/HER2 contributes to endocrine resistance. Using a xenograft model of human ER+ breast cancer cells engineered to overexpress HER2 (MCF-7/HER2-18), we have shown that tamoxifen (Tam) stimulates tumor growth resulting in de novo resistance. Anti HER1/HER2 targeted treatment overcomes this Tam resistant phenotype, though these effects are transient using single agents like the anti-HER2 antibody trastuzumab (T), thus suggesting that a more potent anti-HER therapy or simultaneous inhibition of alternative pathways is required to reverse resistance. Both ER and HER2 are known to promote angiogenesis. Vandetanib (V) (ZD6474, ZACTIMA) is an orally active, VEGFR/HER1 tyrosine kinase inhibitor that has shown both anti-angiogenic and anti tumor cell activities in different models. We thus hypothesize that in ER+/HER2+ tumors, the addition of V to the combination regimen of Tam+T would increase antitumor effect and delay onset of resistance due to inhibition of tumor angiogenesis and delivery of a more complete blockade of the HER network.Methods: Mice bearing MCF-7/HER2-18 tumors were randomized and treated with Tam given alone or in combination with T (10 mg/Kg, bi-weekly), V (50 mg/Kg, 5 d/week), or T+V. Tumor volumes were followed weekly. Mean tumor regression (M-TR) ± SD and median time to tumor progression (M-TTP, defined by tumor doubling from its size at randomization) and 95% CIs were analyzed by Wilcoxon Rank Sum and survival analysis methods (Kaplan-Meier estimates and generalized Wilcoxon test), respectively. All statistical tests were two-sided and adjusted (Holm) for multiple comparisons.Results: Tam monotherapy had minimal effect on tumor growth (M-TR 22%±15 SD) after which all tumors progressed rapidly [M-TTP 42 (35-56) days, 95% CI]. The addition of either T or V to Tam significantly improved tumor regression compared to Tam monotherapy (M-TR 66%±27, P=0.0012, and 67%±25, P=0.001, respectively) and significantly delayed time to tumor progression [M-TTP 91 (70-119) days, P=0.012, and 77 (63-98) days, P=0.02, respectively]. However, the combined regimen of T+V with Tam was significantly more effective than either T or V added separately to Tam, resulting in further significant tumor regression (M-TR 81%±29, P=0.0086 vs. T and 0.0012 vs. V) and a prolonged M-TTP (&amp;gt;154 d, P=0.02 vs. T and 0.01 vs. V).Conclusions: This study supports the concept that the dual VEGFR/HER1 inhibitor vandetanib can improve efficacy of combined endocrine and anti-HER trastuzumab therapy in ER+/HER2+ tumors, probably due to angiogenesis inhibition and to a more potent blockade of HER family signaling and its cross-talk with ER. Clinical studies to examine this approach are warranted. Citation Information: Cancer Res 2009;69(24 Suppl):Abstract nr 5128.

Interpreting genotype × environment interactions for durum wheat grain yields using nonparametric methods

The objective of this study was to compare nonparametric stability procedures and apply different nonparametric tests for genotype × environment (G × E) interactions on grain yields of 15 durum wheat genotypes selected from Iran/ICARDA joint project grown in 12 environments during 2004–2006 in Iran. Results of nonparametric tests of G × E interaction and a combined ANOVA across environments indicated the presence of both crossover and noncrossover interactions, and genotypes varied significantly for grain yield. In this study, high values of TOP (proportion of environments in which a genotype ranked in the top third) and low values of sum of ranks of mean grain yield and Shukla’s stability variance (rank-sum) were associated with high mean yield. The other nonparametric stability methods were not positively correlated with mean yield but they characterized a static concept of stability. The results of correlation analysis indicated that only TOP and rank-sum methods would be useful for simultaneous selection for high yield and stability. These two methods identified lines Mrb3/Mna-1, Syrian-4 and Mna-1/Rfm-7 as genotypes with dynamic stability and wide adaptation. According to static stability parameters, the genotypes 12A-Mar8081 and 19A-Mar8081 with lowest grain yield were selected as genotypes with the highest stability.

The distribution of health care costs and their statistical analysis for economic evaluation.

Where patient level data are available on health care costs, it is natural to use statistical analysis to describe the differences in cost between alternative treatments. Health care costs are, however, commonly considered to be skewed, which could present problems for standard statistical tests. This review examines how authors report the distributional form of health care cost data and how they have analysed their results. A review of cost-effectiveness studies that collected patient-level data on health care costs. To supplement the review, five datasets on health care costs are examined. Consideration is given to the use of parametric methods on the transformed scale and to non-parametric methods of analysing skewed cost data. Since economic analysis requires estimation in monetary units, the usefulness of transformation-based methods is limited by the inability to retransform cost differences to the original scale. Non-parametric rank sum methods were also found to be of limited use for economic analysis, partly due to the focus on hypothesis testing rather than estimation. Overall, the non-parametric approach of bootstrapping was found to offer a useful test of the appropriateness of parametric assumptions and an alternative method of estimation where those assumptions were found not to hold. Guidelines for the analysis of skewed health care cost data are offered.

A Composite Index for Statistical Inference for Ranking Metropolitan Areas

ABSTRACT The construction of a composite index is described to rank U.S. metropolitan areas for educational attainment. The suggested methodology departs from traditional rank sum methods in that this approach utilizes data resulting in a continuous scale, whereas in the rank sum method, no use is made of the actual values of the data, but merely their rankings. The proposed index circumvents several practical problems because the numbers generated are metric measures allowing the use of arithmetic and statistical operations. Data used are pupil/teacher ratio, an effort index, and academic options in higher education. Comparisons are made across areas by population size and by geographic region.

Urban Variation in Personal Economic Locational Outlook

: The paper provides a simple method based on Euclidean distance to rank U.S. metropolitan areas for personal economic locational outlook. The suggested technique has advantages over the commonly used rank sum methods because the resulting measure is an absolute scale. This aspect allows the use of parametric probability distributions for statistical analysis of the results.

Statistical Analysis of Screening Studies in Toxicology with Special Emphasis on Neurotoxicology

Screens have a common set of operating characteristics that are not widely appreciated and that make traditional approaches to statistical analysis both insensitive and inefficient in comparison to other available methods. Traditional methods also do not incorporate additional data as it is generated. Such incorporation would serve to strengthen both the design and analysis processes and is essential in the case of screens. Traditional methods of analysis (contingency tables, rank sum, and ANOVA methods) are overviewed briefly, and their weaknesses are discussed. The concept of power and the factors influencing it are discussed. Alternative approaches to analysis of univariate (control charts and central tendency plots) and multivariate (analog contrast plots and multidimensional cluster plots) data from screens are presented, and their performance is evaluated. The resulting general principles of design and analysis of screens for neurotoxicology are presented. The alternative approaches are shown to be superior to traditional approaches in performance toward meeting the objectives of screens.

An Approach to the Design and Analysis of Screening Studies in Toxicology

An increasingly important aspect of toxicology is the use of screening tests for detecting the presence or absence of a single end point of effect, such as mutagenicity or neurobehavioral effects. Such screens have a common set of operating characteristics that are not widely apreciated and that make traditional approaches to statistical analysis insensitive and inefficient in comparison to other available methods. All too often, control and historical data are not used to strengthen the analysis process. The characteristics of screens are presented and reviewed, along with overviews of 26 sets of data from functional observational battery screen (neurobehavioral) studies. Two alternative approaches to statistical analysis of screening tests (a control chart approach and a graphic-exploratory data analysis approach) are presented, along with a review of traditionally used contingency table, rank sum, and ANOVA methods. The performances of these methods in analyzing the test case screen datasets are compared in terms of power, sensitivity, and efficiency. Both alternative approaches are shown to be superior to traditional approaches in performance toward meeting the objectives of screens.