Two-way Contingency Table Analysis Research Articles

Geometric Mean Type of Proportional Reduction in Variation Measure for Two-Way Contingency Tables

Traditional analysis of two-way contingency tables with explanatory and response variables focuses on the independence of two variables. However, if the variables do not show independence or a clear relationship, the analysis shifts to the degree of association. Various measures have been proposed to calculate the degree of association. One is the proportional reduction in variation (PRV) measure. This measure describes the PRV from the marginal distribution to the conditional distribution of the response variable. Although conventional PRV measures can assess the association of the entire contingency table, they cannot accurately assess the association for each explanatory variable. In this paper, we propose a geometric mean type of PRV (geoPRV) measure, which aims to sensitively capture the association of each explanatory variable to the response variable. Our approach uses a geometric mean, and enabling analysis without underestimating the values when the cells in the contingency table are partially biased. The geoPRV measure can be constructed using any function that satisfies specific conditions. This approach has practical advantages, and in special cases, conventional PRV measures can be expressed as geometric mean types.

Generalized Cramér’s coefficient via f-divergence for contingency tables

AbstractVarious measures in two-way contingency table analysis have been proposed to express the strength of association between row and column variables in contingency tables. Tomizawa et al. (2004) proposed more general measures, including Cramér’s coefficient, using the power-divergence. In this paper, we propose measures using the f-divergence that has a wider class than the power-divergence. Unlike statistical hypothesis tests, these measures provide quantification of the association structure in contingency tables. The contribution of our study is proving that a measure applying a function that satisfies the condition of the f-divergence has desirable properties for measuring the strength of association in contingency tables. With this contribution, we can easily construct a new measure using a divergence that has essential properties for the analyst. For example, we conducted numerical experiments with a measure applying the $$\theta$$ θ -divergence. Furthermore, we can give further interpretation of the association between the row and column variables in the contingency table, which could not be obtained with the conventional one. We also show a relationship between our proposed measures and the correlation coefficient in a bivariate normal distribution of latent variables in the contingency tables.

DEPARTURE FROM QUASI-UNIFORM ASSOCIATION MODEL IN ORDERED SQUARE CONTINGENCY TABLES

The Uniform Association (UA) and Quasi-Uniform Association (QUA) models are used for analysis of two-way square contingency tables with ordered categories. When the QUA model does not fit the data, one wants to measure the degree of departure from the quasi-uniform association model. The degree of the departure from the model is calculated by usingthe power divergence statistics. In this study, as an alternative to measures in the literature, a measure to estimate the degree of departure from the QUA model is suggested. This suggested measure allows us to compare the several R×R tables in terms of the departure from the model. The measures are compared by the simulation study and discussed by three unaided distance vision data.

Two-Dimensional Index of Departure from the Symmetry Model for Square Contingency Tables with Nominal Categories

In the analysis of two-way contingency tables, the degree of departure from independence is measured using measures of association between row and column variables (e.g., Yule’s coefficients of association and of colligation, Cramér’s coefficient, and Goodman and Kruskal’s coefficient). On the other hand, in the analysis of square contingency tables with the same row and column classifications, we are interested in measuring the degree of departure from symmetry rather than independence. Over past years, many studies have proposed various types of indexes based on their power divergence (or diversity index) to represent the degree of departure from symmetry. This study proposes a two-dimensional index to measure the degree of departure from symmetry in terms of the log odds of each symmetric cell with respect to the main diagonal of the table. By measuring the degree of departure from symmetry in terms of the log odds of each symmetric cell, the analysis results are easier to interpret than existing indexes. Numerical experiments show the utility of the proposed two-dimensional index. We show the usefulness of the proposed two-dimensional index by using real data.

Quantitative Evaluation of Intraspinal Lumbar Disc Herniation-related Lumbosacral Radiculopathy Before and After Percutaneous Transforaminal Endoscopic Discectomy Using Diffusion Tensor Imaging.

A prospective study. The aim of this study was to investigate the relationship between diffusion tensor imaging (DTI) derived parameters of compressed nerve roots at subregions and the corresponding clinical symptoms to evaluate the patients with intraspinal lumbar disc herniation (LDH)-related lumbosacral radiculopathy pre- and postoperatively. It is crucial to explore whether magnetic resonanve imaging (MRI) can quantitatively evaluate intraspinal LDH-related lumbosacral radiculopathy before and after surgery. In all, 66 patients underwent MRI scans and Clinical assessment before and after percutaneous transforaminal endoscopic discectomy (PTED). Pre- and postoperative findings of the related lumbar disk and nerve tractography were compared with two-way contingency table analysis. The embedded paired t test toolbox was applied to respectively compare the fractional anisotropy (FA) and apparent diffusion coefficient (ADC) values of nerves at the symptomatic and asymptomatic sides in three subregions pre- and postoperatively. The correlation of clinical Japanese Orthopedic Association (JOA) scores and FA/ADC values of nerves at three sub-regions was analyzed by stepwise multiple linear regression analysis. The postoperative FA values were significantly higher than the corresponding preoperative values (P < 0.001), while comparable ADC values were found. Using tractography, a notable improvement of compressed nerve was revealed after surgery (61 cases, 92.4%). Additionally, multiple linear regression analysis identified significant associations between JOA scores and FA values of the compressed nerves with the greatest effect at the proximal region. The FA values at subarticular zone can reflect the microstructural changes of the corresponding compressed nerves and well associate with clinical symptoms. Therefore, the DTI parameter FA can be considered an effective tool in clinic to quantitatively evaluate intraspinal LDH-related lumbosacral radiculopathy before and after PTED surgery.Level of Evidence: 3.

In vivo detection of vertical root fractures in endodontically treated teeth: Accuracy of cone-beam computed tomography and assessment of potential predictor variables.

BackgroundThis study aimed: (a) to determine the diagnostic performance of cone-beam computed tomography (CBCT) for detection of vertical root fractures (VRFs); (b) to evaluate the predictive value of diagnostic criteria regarding the definition of VRFs; and (c) to examine the robustness of the association of patient-, tooth-, and treatment-related variables with VRFs. Material and Methods130 root-filled teeth with signs/symptoms of VRFs underwent clinical and CBCT assessments. Definite diagnosis of VRF was confirmed by endodontic microsurgical (EMS) exploration. Determination of diagnostic performance of CBCT was based on standard algorithms derived from two-way contingency table analysis. Predictive value of diagnostic criteria and the association between predictor variables with VRFs were analyzed using logistic regression models. ResultsVRFs were detected during EMS in 50% of the teeth. Based on the finding of fracture lines on CBCT scans, sensitivity, specificity, and accuracy were 86.2%, 13.8%, and 50%, respectively. Teeth having more than three diagnostic criteria present had significant higher odds for VRF diagnosis. After logistic regression analysis, parafunctional habits, one-canal roots, excessive root canal enlargement, and absence of intra-radicular posts remained as robust predictor variables of VRFs. ConclusionsAlthough the sensitivity of CBCT for VRFs detection is high, the risk of false-positive results related to its low specificity makes that all suspected cases must be confirmed by surgical exploration. VRFs cannot be reliably diagnosed by isolated clinical signs/symptoms; instead those teeth possessing more than three diagnostic criteria might be considered practically pathognomonic. The parafunctional habits, one-canal roots, excessive root canal enlargement, and the absence of intra-radicular posts may act strongly/independently for the occurrence of VRFs in endodontically treated teeth. Key words:Cone-beam computed tomography, diagnostic accuracy, diagnostic surgery, predictor variables, root canal treatment, vertical root fracture.

Application of Numerical Weather Prediction Data to Estimate Infection Risk of Bacterial Grain Rot of Rice in Korea.

This study was conducted to evaluate usefulness of numerical weather prediction data generated by the Unified Model (UM) for plant disease forecast. Using the UM06- and UM18-predicted weather data, which were released at 0600 and 1800 Universal Time Coordinated (UTC), respectively, by the Korea Meteorological Administration (KMA), disease forecast on bacterial grain rot (BGR) of rice was examined as compared with the model output based on the automated weather stations (AWS)-observed weather data. We analyzed performance of BGRcast based on the UM-predicted and the AWS-observed daily minimum temperature and average relative humidity in 2014 and 2015 from 29 locations representing major rice growing areas in Korea using regression analysis and two-way contingency table analysis. Temporal changes in weather conduciveness at two locations in 2014 were also analyzed with regard to daily weather conduciveness (Ci) and the 20-day and 7-day moving averages of Ci for the inoculum build-up phase (Cinc) prior to the panicle emergence of rice plants and the infection phase (Cinf) during the heading stage of rice plants, respectively. Based on Cinc and Cinf, we were able to obtain the same disease warnings at all locations regardless of the sources of weather data. In conclusion, the numerical weather prediction data from KMA could be reliable to apply as input data for plant disease forecast models. Weather prediction data would facilitate applications of weather-driven disease models for better disease management. Crop growers would have better options for disease control including both protective and curative measures when weather prediction data are used for disease warning.

Analysis of salivary detection of P16INK4A and RASSF1A promoter gene methylation and its association with oral squamous cell carcinoma in a Colombian population.

BackgroundEpigenetic factors play a fundamental role in the etiopathogenesis of oral squamous cell carcinoma (OSCC). This study evaluated if salivary detection of P16INK4A/RASSF1A gene promoter methylation might be linked to the clinical/histological features of OSCC in a Colombian population. Material and MethodsMethylation-specific polymerase chain reaction (MSP-PCR) was used to detect the methylation frequency of P16INK4A/RASSF1A genes in DNA obtained from whole saliva collected of 40 healthy controls (HC) and 43 OSCC patients. Determination of the clinical performance of MSP-PCR assay was based on standard algorithms derived from two-way contingency table analysis. The association of methylation status of targeted genes with OSCC was analyzed in a multivariate binary logistic regression model. ResultsThere were significantly higher proportions of promoter methylation of these target genes in OSCC patients when compared with HC. The analysis of single methylated genes showed high specificity, good positive and negative predictive values, but was accompanied by a low sensitivity. OSCC cases with clinical stage III/IV, poorly differentiated, and severe cellular atypia showed a significantly greater proportion of methylated than that of unmethylated targeted genes in saliva samples. Logistic regression analysis indicated an independent association of P16INK4A and RASSF1A promoter methylation with OSCC diagnosis. A significant interaction effect between ageing and P16INK4A promoter methylation was also detected. ConclusionsSalivary detection of P16INK4A and RASSF1A promoter methylation appears to be independently associated with OSCC and may be linked to the tumor activity in the present population. Consequently, the targeting of these genes in saliva samples might constitute an important tool for diagnosis and prognosis purposes. Key words:Gene methylation, oral squamous cell carcinoma, P16INK4A, RASSF1A, saliva.

Assessment of the Quality of Malaria Rapid Diagnostic Test, Adama District, East Shewa Zone, Ethiopia

Background: In Ethiopia, smear microscopy is the gold standard for malaria diagnosis however; it is not available in health post. Smear microscopy is time consuming, requires trained personnel and needs careful preparation and application of reagents to ensure quality results. Objective: This study was aimed at testing the diagnostic performance of SD BIOLINE malaria rapid diagnostic test (RDT) with reference to smear microscopy for the diagnosis of falciparum and vivax malaria in Ethiopia. Methods: Blood samples were collected from 402 patients suspected to have malaria in four health facilities in the late minor malaria transmission season from June18-30, 2014. The samples were examined immediately by smear microscopy and the RDT (SD BIOLINE Malaria HRP2/pLDH POCT Test kit). Statistical analysis was performed using Epi-info version 7 and the two-way contingency table analysis. Results: The overall parasite positivity using smear microscopy was 163 (45.6%): 136 (33.8%) for P. falciparum, 25 (6.2%) for P. vivax and two (0.5%) for mixed infections. Using the SD BIOLINE RDT, the overall parasite positivity was 176 (43.7%): 149 (37%) for P. falciparum, 26 (6.5%) for P. vivax and 1 (0.2%) for mixed infections. The overall sensitivity and specificity of SD BIOLINE RDT was found to be 98.2% (97.5–99.9%, 95% CI) and 95.2% (93.9–97.7%, 95% CI), respectively. The sensitivity and specificity of SD BIOLINE RDT was found to be 98.2% (94–99.1%, 95% CI) and 95.4% (93.9–97.1%, 95% CI), respectively. The positive predictive value (PPV) and the negative predictive value (NPV) were found to be 93.6% (88.5–96.1%, 95% CI) and 98.7% (95.3–99.8%, 95% CI), respectively. There was an excellent agreement between the smear microscopy and SD BIOLINE RDT with a Kappa value of 0.965 (0.896–0.988, 95% CI). Conclusion: The SD BIOLINE RDT test showed good sensitivity and specificity with an excellent agreement to the reference smear microscopy. The RDT could therefore be used in place of smear microscopy, at health post where the microscope not applicable.

Demographics, Learner Characteristics, and Use of Wearable Devices

This case study was intended to explore whether wearable device use is associated with their demographic factors (e.g., device ownership and gender), using undergraduate students in a Hispanic Serving Institution. Preliminary findings of this two-way contingency table analysis suggested that students who own the device(s) are more likely to use it for school. Males are more likely to use the wearables for learning in spite of a marginal effect size. Implications and recommendations are discussed.

Measure of Departure from Marginal Average Point-Symmetry for Two-Way Contingency Tables

For the analysis of two-way contingency tables with ordered categories, Yamamoto, Tahata, Suzuki, and Tomizawa (2011) considered a measure to represent the degree of departure from marginal point-symmetry. The maximum value of the measure cannot distinguish two kinds of marginal complete asymmetry with respect to the midpoint. A measure is proposed which can distinguish two kinds of marginal asymmetry with respect to the midpoint. It also gives large-sample confidence interval for the proposed measure.

Comparing Two Approaches to Engineering Design in the 7th Grade Science Classroom

In schools, design projects can be implemented at a variety of ways and with varying degrees of resources from teachers and schools. However, little work has been done on the differences between student learning outcomes and the type of design projects. This study compares two design projects implemented in 7th grade classrooms (n=677) at two different schools to explain affordances of each approach based on differences in project authenticity, scale, and depth of context in supporting student learning outcomes. The main data sources were an engineering science test and a design reasoning elicitation problem, administered at each school before and after the design project. To understand the relationship between students’ science learning gains and school implementation, we conducted a sign test to compare between-group differences and a Mann Whitney Test to compare within-group differences. Then, we performed a content analysis to examine students’ design reasoning and a two-way contingency table analysis to understand if a student’s school implementation was related to the changes in design trade-off reasoning. Students at both schools exhibited statistically significant but small gains on their engineering science test scores. While students at the school with a more interdisciplinary, more authentic design project had higher scores on the engineering science test, students at the school with a smaller scale implementation discussed more trade-off factors in their design reasoning elicitation problem. These findings suggest that differences in project implementation appear to be associated with different learning outcomes, and there are potential benefits to both authenticity and simplicity in design projects.

Factors Associated with Type 1 and Type 2 Diabetes in Infants in Kuwait

Purpose: The purpose of the study is to investigate the factors associated with diabetes and its influence on the prevalence of diabetes in Kuwait. Methods: A questionnaire was designed to explore the relationships between various factors and diabetes in children. The survey included 300 mothers of children up to five years of age in Kuwait and the results were subjected to a two-way contingency table analysis. Results: Variables showing at least a medium effect and a linear relationship are herein reported. Increasing maternal age was found to be related to the increasing prevalence of type 1 diabetes. An association between a higher prevalence of both type 1 and type 2 diabetes in the mother and the child was found. Risk of having a child with diabetes increases with the maternal age. The consumption of fried food or fast food by a child was associated with a higher prevalence of both type 1 and type 2 diabetes. Sugar consumption, both by the mother during pregnancy and by the child, was associated with a higher prevalence of type 2 diabetes. Heavy consumption of nuts by the child was associated with a higher prevalence of type 2. Conclusion: Genetics and environmental factors including diet may play important roles in the causation of both type 1 and type 2 diabetes in Kuwait.

Corridor safety evaluation in a developing country using a survey based approach

ABSTRACTRoad traffic crashes are a major cause of concern in Saudi Arabia. Although the general view of the design and quality of Saudi Arabia's road network meets global standards, there is not enough in-depth analysis of crash locations and contributing factors and their relationship with user characteristics or behaviors. This study aims to investigate, analyze, and examine the safety problems on a main corridor in the Eastern Province and then suggest treatments to enhance the safety and explore the crash-risk factors associated with crashes on that corridor. A multiple survey approach was used to collect data from road users and experts. The survey addresses traffic safety issues and user behaviors on the corridor. To achieve the study aims, one-way analysis, two-way contingency table analysis, and structural equation modeling were applied. The results showed a need for adequate shoulders along the corridor, and the markings, signs, and signal timing should be reevaluated. In addition, greater restrictions on the use of mobile phones while driving are needed. Also television and radio programs are recommended for traffic awareness as reported by participants. Lastly, it showed that the multiple survey approach can be very useful when crash and geometric data are not available or incomplete.

A Bayesian model for two-way contingency tables with nonignorable nonresponse from small areas

Many surveys provide categorical data and there may be one or more missing categories. We describe a nonignorable nonresponse model for the analysis of two-way contingency tables from small areas. There are both item and unit nonresponse. One approach to analyze these data is to construct several tables corresponding to missing categories. We describe a hierarchical Bayesian model to analyze two-way categorical data from different areas. This allows a borrowing of strength of the data from larger areas to improve the reliability in the estimates of the model parameters corresponding to the small areas. Also we use a nonignorable nonresponse model with Bayesian uncertainty analysis by placing priors in nonidentifiable parameters instead of a sensitivity analysis for nonidentifiable parameters. We use the griddy Gibbs sampler to fit our models and compute DIC and BPP for model diagnostics. We illustrate our method using data from NHANES III data on thirteen states to obtain the finite population proportions.

Online Complaining Behavior in Mainland China Hotels: The Perception of Chinese and Non-Chinese Customers

Examining hotel customer feedback is vital for effective service recovery and improvement. The main objective of this study is to analyze online complaints about hotels in Mainland China and to examine the relationship between culture and other factors that affect the intention to complain online. Content analysis was performed for 822 complaints about hotels in major Chinese cities drawn from TripAdvisor and Ctrip. Complaints made by Chinese and non-Chinese customers were compared and 11 major complaint categories were identified. A two-way contingency table analysis demonstrated that traveler age, hotel price, and travel partner significantly influenced the online complaints made.

Cumulative Correspondence Analysis of Two-Way Ordinal Contingency Tables

A suitable measure of association for two ordered variables is the doubly cumulative chi-squared statistic (Hirotsu, 1994). This statistic is obtained by considering the cumulative sum of cell frequencies across the variables. In this article, we explore the development of correspondence analysis which takes into account the presence of two ordered variables by partitioning the doubly cumulative chi-squared statistic.

Tests of marginal homogeneity and special cases

The analysis of two-way contingency tables is common in clinical studies. In addition to summary counts and percentages, statistical tests or summary measures are often desired. If the data can be viewed as two categorical measurements on the same experimental unit (matched pair data) then a test of marginal homogeneity may be appropriate. The most common clinical example is the so called 'shift table' whereby a quantity is tested for change between two time points. The two principal marginal homogeneity tests are the Stuart Maxwell and Bhapkar tests. At present, SAS software does not compute either test directly (for tables with more than two categories) and a programmatic solution is required. Two examples of programmatic SAS code are found in the current literature. Although accurate in most instances, they fail to produce output for certain tables ('special cases'). After summarizing the mathematics behind the two tests, a SAS macro is presented, which produces correct output for all tables. Finally, several examples are coded and presented with resultant output.

Comparative distribution of Lysyl Oxidase (G473A) and NQO1 (C609T) polymorphism among tea-garden workers (habitual chewers of betel quid) of Darjeeling district and Kolkata city of West Bengal

Context:Chewing of processed arecanut products with tobacco and betel quid has been attributed to many oral pathological conditions. These products are very popular among the youngsters of lower economic groups. Genetic predisposition has been now identified as a major risk factor for increasing the susceptibility toward the disease among these chewers.Aims:Our study mainly aims to find out the predisposition of LOX (G473A) and NQO1 (C609T) polymorphisms and present a comparison between the population (habitually exposed to processed arecanut and smokeless tobacco products) of a metro-city Kolkata and the tea-garden workers of Darjeeling district of West Bengal.Settings and Design:Subjects for the study was recruited from various oral health check-up camps organized in the tea-gardens of Darjeeling district and Kolkata city.Materials and Methods:Genotyping analysis was done through a Polymerase Chain Reaction–Restriction Fragment Length Polymorphism (PCR-RFLP)-based approach.Statistical Analysis Used:A two-way contingency table analysis software (JAVASTAT: http://statpages.org/ctab2 × 2.html) using 95% confidence interval was used to study the distribution of genotypes among the populations. A P < 0.05 was considered to be significant.Results:The results indicates both the heterozygous and homozygous carriers of NQO1 C > T (609) was found to be significantly higher among the north Bengal tea-garden workers [OR 0.480 (0.280-0.82) P = 0.01; 0.218 (0.091–0.524) P = 0.0001], respectively. Interestingly CT (21% in both) and TT (8% and 7%, respectively) were found to be equally distributed in the two populations. For LOX G > A (473) a significantly higher number of Kolkata individuals were found to carry the heterozygous GA allele in individuals aged <30 years [OR 3.779 (1.684-6.547) P = 0.001]. However, none were carrier of heterozygous GA allele of Kolkata population as compared with 29% north Bengal tea-garden workers aged above 31 years.Conclusions:A close observation of occurrence of oral diseases over time among such a population will be helpful to identify risk genotypes responsible for betel quid-induced oral diseases.

A Framework for Integrated Analysis of Quality Defects in Supply Chain

Studies reported in supply chain literature have focused on demonstrating the benefits of information sharing, knowledge transfer, and collaborative efforts. The present study carries forward these fundamentals into the quality domain. A methodology is developed for quality defects information sharing among supply chain partners, and analysis of the shared data is structured using correspondence analysis of two-way contingency tables. The model presents a unique opportunity in identifying the underlying phenomenon causing defects by exploiting the associations and differences among the supply chain partners based on defect occurrences and then analyzing the process similarities/differences among them. This saves time and effort spent on finding root causes and designing solutions, as one will have an opportunity to adopt a proven process from a better supplier. This distinguishes the proposed methodology from other conventional quality tools and root cause analysis techniques. The proposed methodology is empirically validated through a case study on a multinational medical equipment manufacturer's supply chain. The application helped identify technical and nontechnical root causes driving defects. The methodology developed in this study is generic and can be applied to analyze quality defects in any supply chain.