ordinal logistic regression

In the Conjoint Analysis (COA) model proposed here—a new approach to estimate more than one response function— an extension of the traditional COA, the polytomous response variable (i.e. evaluation of the overall desirability of al- ternative product profiles) is described by a sequence of binary variables. To link the categories of overall evaluation to the factor levels, we adopt—at the aggregate level—an ordinal logistic regression, based on a main effects experimen- tal design. The model provides several overall desirability functions (aggregated part-worths sets), as many as the overall ordered categories are, unlike the traditional metric and non metric COA, which gives only one response func- tion. We provide an application of the model and an interpretation of the main effects.

DOI: 10.4236/jfrm.2017.63020 274 Journal of Financial Risk Management between variables when the dependent variable is categorical. This method is al- so categorized among consecutive categories, from low to high values. Ordinal Logistic Regression Method cannot be used when the ranking of categories is close (Menard, 2001). This method can be constructed as a ordinal category lo- gistic regression model, a continuous rate model and a proportional odds model (Hosmer & Lemeshow, 2000: 288). After modeling, the model needs to be statis- tically evaluated and tested (Çokluk, 2010: 1404). Statistics related to the test of the significance of the model, Chi-square statistic, −2LogL statistic, Hosmer and Lemeshow G, Block Chi-square statistic are used.

There were 433 burn areas for which clinician's predic- tions of healing time using the LDI were available. Of these a subset of 310 wounds was appropriate for computing average laser-Doppler flux. The analysis here focuses on the use of flux as a predictor rather than using the clinician predictions, mainly because this shows the performance of the technology when quite divorced from clinical judgement. Also, the mean flux measure- ment data are probably better suited to answering questions about the role of covariates. Proportional- odds (PO) ordinal logistic regression is the most popular method of analyzing data such as these, where a dependent variable Y that takes ordered integer values is modeled as a function of a vector x of covariates. An introductory account is given in [19] and general descriptions in [20-22]. We seek to predict a dependent variable (healing time) that is ordered, and model the logits of the cumulative probabilities of healing in under 14 days or in 14 – 21 days as a linear function of the covariates. In the 'parallel lines' model usually fitted to the kth (of 2) cumulative probabilities P 1 and P 2 , the

Abstract: Although Ethiopia is a young country with 46 per cent of the population under the age of 14, over five per cent of the 81 million Ethiopians are aged 60 years or more. This proportion of older persons is anticipated to nearly double to nine per cent by 2050. There are several factors that could hinder old people access to food such as income, health status, household size, disability and others (HAIE, 2011). This objective of this study was to assess the old people access to food and its determinants in Dire Dawa city. Total samples of 947 old people were taken by using cluster sampling over proportional allocation to each kebele. Quantitative and qualitative data has been collected from aged persons in Dawit Aid for Aged persons Association, Asegedech Association and other appropriate enumeration areas. The descriptive analysis resulted that 72.76% were members of the associations. Most (74.3%) members of the organization have medium and above food access. Additionally their life have been improved in terms of obtaining medical, clothing and counseling service after they joined the organizations. The ordinal logistic regression identified income source, occupation, owning a house and type of membership organization as determinants of daily food access for the elderly.

moderately malnourished and severely malnourished. When the researchers are interested to find the determi- nants of malnutrition and severe malnutrition, two sepa- rate binary logistic regression (BLR) models are required to develop by grouping the response variable into two categories [7]. This task is tedious and cumbersome due to estimation and interpretation of more parameters. However, the researcher may consider the response vari- able as ordinal and may apply ordinal logistic regression model for the same purpose. A few studies have been done using ordinal logistic regression model (OLR) to identify the predictors of child undernutrition [11]. In many epidemiological and medical studies, OLR model is frequently used when the response variable is ordinal in nature [12-17]. The study has made an effort to iden- tify the predictors of child malnutrition as well as severe malnutrition for under five Bangladeshi children by developing an ordinal logistic regression model.

There were 433 burn areas for which clinician's predic- tions of healing time using the LDI were available. Of these a subset of 310 wounds was appropriate for computing average laser-Doppler flux. The analysis here focuses on the use of flux as a predictor rather than using the clinician predictions, mainly because this shows the performance of the technology when quite divorced from clinical judgement. Also, the mean flux measure- ment data are probably better suited to answering questions about the role of covariates. Proportional- odds (PO) ordinal logistic regression is the most popular method of analyzing data such as these, where a dependent variable Y that takes ordered integer values is modeled as a function of a vector x of covariates. An introductory account is given in [19] and general descriptions in [20-22]. We seek to predict a dependent variable (healing time) that is ordered, and model the logits of the cumulative probabilities of healing in under 14 days or in 14 – 21 days as a linear function of the covariates. In the 'parallel lines' model usually fitted to the kth (of 2) cumulative probabilities P 1 and P 2 , the

There are some alternative software toolboxes that implement certain features for ordinal regression. Those include: i) mord 1 in Python, ii) ordinal 2 in R, iii) vgam 3 in R, iv) bmrm 4 in R and v) ocapis 5 in Scala. mord and ordinal focus on well-established simple statistical methods (i.e. ordinal logistic regression, which is also included in our toolbox) rather than on novel machine learning approaches. vgam and bmrm focus on vector generalised linear and additive models and regularised empirical minimisation respectively, having a setting to deal with ordinal classification problems. Finally, ocapis implements 4 of the 15 methods that ORCA includes but lacks the experimental and parallelisation framework.

Ordinal logistic regression was used to test the associ- ation between QOL and physical and psychosocial health after controlling for age and socioeconomic status. All analyses were performed separately for each gender. In this study, we applied the Polytomous Universal Model (PLUM), which incorporates the ordinal nature of the dependent variable in the analysis; thus, a logistic regres- sion model with proportional-odds and Logit function [28] was performed. The odds between the categories of the dependent variable were compared by calculating the crude and adjusted odds ratio (OR), and tests evaluating the homogeneity of slopes and multicollinearity were con- ducted using Pearson's adjustment to analyze the validity of the model. To ascertain the possible interference of a small number of observations, we used residual analysis for ordinal data, as proposed by McCullagh [29]. All of these tests showed that the model satisfied all of the assumptions, and the effect of the complex sample design was considered in all of the analyses.

Piracy at sea is a great detriment to the transportation of goods through our seaways. Seaborne trade accounts for about 80% of global trade. To effectively monitor their territorial waters and Exclusive Economic Zones is problematic for many countries in West and Central Africa. To figure out the modus operandi of the pirates and be aware and proactive enough to create effective countermeasures remains a crucial endeavour to arrest this menace. The Gulf of Guinea (GoG) has been an active arena for piratical activities. This paper utilizes systematic analysis to determine and examine pirate incidents that occured from 2006 to 2015 with data from the International Maritime Bureau (IMB). Analysis of the data was done using RealStats resouce add-on for Excel and predictive modelling was used to test the forecasting ability of various models empirically. Three key models namely, Ordinal Logistic Regression, Bayesian Network Predictor, and Series Hazard Models are used to compute the probable increase in pirate attacks with a forecast into the next fifteen years. This is essential to the trend of the new wave of pirate attacks and its current and potential impact on Maritime Transportation and Maritime Security. While there is an international presence in the Gulf of Aden, there is no such dedicated force in the GoG. The findings from the statistical results are to assist policymakers in their decision making when using their scarce law enforcement apparatus to combat Maritime Piracy and their Maritime Transportation and Security challenges.

may exacerbate depressive symptoms. Our findings chal- lenge the theory that individuals with greater pain at night had disturbed sleep quality and subsequent exacer- bation of depressive symptoms. However, this result should be interpreted with caution. This exploratory study did not perform pre-study sample size calcula- tions, although we initially checked the maximum num- ber of independent variables included in the ordinal logistic regression model. Therefore, a lack of statistical power due to a small number of included patients may explain this absence. Indeed, post-hoc power calculation detected by the Power and Sample Size Program, PS (version 3.1.2) [52] revealed that we have only 69.0% power to detect a standardized mean difference of at least 0.51, at the 5% alpha level. The lower 95% CI of proportional OR for the presence of night pain is close to 1, suggesting that further studies with larger sample sizes would be warranted to confirm the relationship between depressive symptom and night pain.

Ordinal logistic regression ( fi gure 2A, B) predicts mem- bership of the minimal, mild, moderate and severe fatigue groups using all 24 cytokines, WCC, lymphocytes, neutrophils, ESR, CRP, ESSDAI scores and dryness scores, as well as patient-reported depression, anxiety and pain. The full model, with all parameters, correctly predicts fatigue in 67% of cases ( fi gure 2A). This model with all parameters was robust to the presence or absence of loose markers of disease activity (such as WCC, lymphocytes, neutrophils, ESR, CRP, ESSDAI and dryness scores), but sensitive to the presence or absence of cytokines, depression, anxiety and pain. The model predictions are reasonably accurate providing cytokines, depression and pain are retained. This suggests that measures of disease activity in pSS appear to be less Table 2 Clinical summary for pSS fatigue groups showing mean±SD for key demographics, haematological and clinical variables

Legal Aid Service (LAS) intervention is considered to have an influence on women empowerment through raising awareness of women towards their rights. Using Kongwa and Morogoro Rural districts as study areas, a study was conducted involving 240 women (120 beneficiaries and 120 non-beneficiaries of LAS). A cross-sectional research design was used, whereby random selection of respondents was done. Statistical Package for the Social Sciences (SPSS) was used to analyze the data. A Composite Empowerment Index (CEI) was used to measure the extent of women empowerment among beneficiaries and non-beneficiaries of LAS interventions. Women in the study areas were categorized at medium level of empowerment. Beneficiaries of LAS interventions were found to be more empowered relative to their counterparts. Ordinal logistic regression analysis results showed that involvement of women in LAS interventions, awareness of women legal rights, marital status and age at first marriage were the most determinant factors that influence women empowerment in Morogoro Rural and Kongwa district. Hence persistent sensitization of women about their rights is critical for reducing violence against them and ultimately achieving high levels of empowerment. Also, rigorous enforcement of existing laws and policies is required to discourage and ultimately eliminate the practice of early marriage.

Wood Turtles (Glyptemys insculpta) are difficult to survey because their use of aquatic and terrestrial environments varies spatio-temporally. existing survey methodology is highly variable and typically involves searching for Wood Turtles within water and on land 0 to >20 m from the shoreline from spring to autumn. The mobility of Wood Turtles suggests that detection is likely influenced by distance surveyed from water and the amount of vegetation, which varies by season. To determine an ideal survey methodology for the Wood Turtle, we recorded distances from a waterway of 31 radio-tagged turtles at canadian Forces base, gagetown, new brunswick, in 2003 and 2004. ordinal logistic regression was used to determine the probability of finding male or female Wood Turtles with increasing distance from water at different times of day or season. Sex and time of day were not significant factors in detecting Wood Turtles. Season was a significant factor, with highest probability (69%) of finding Wood Turtles at a distance of 0–10 m of a waterway up to July 1 (corresponding to pre-nesting and nesting periods), compared to probabilities of <10% for any 10-m distance between 10 m and 50 m from a waterway. after July 1, the highest detection probability (50%) was at distances greater than 50 m from a waterway. We recommend that Wood Turtle surveys for environmental impact assessments and population monitoring be conducted on warm days (i.e., 10–25°c) within 10 m of waterways up to July 1.

Education gives us knowledge of the world around us and knowledge is most important asset for the economic and social development of a country. The students’ academic performance plays a vital role in creating the finest quality alumnae who will become leader and manpower of a particular country, consequently responsible for the country’s social and economic development, but now a day students’ academic performance face many problems. This study assesses the effect of elementary and high schools academic performance of student on their University result in Debre Birhan University. Statistical method which used for this study is Ordinal logistic regression. 365 students from different fields were studied. The result reveal that ministry result, grade 10 total score, grade 10 English score, field, mission, monthly income, place of residence had significant effect on academic performance of student, but factor such as sex, age1, age2, grade 12 total score, Grade 12 English score, Grade 12 mathematics score, Grade10 mathematics score, Grade 8 English score, Grade 8 mathematics score were not significant. The study recommends enhancing quality of education at elementary level and high school level is very important, and empowers students and teacher to increase the skill of English language at each level.

Ordinal logistic regression was used to estimate the association between number of counselling sessions and AUDIT zones at follow-up (abstinence or low-risk, hazardous alcohol use, harmful alcohol use and alcohol dependence), controlling for AUDIT score, mental health problems and treatment goal (abstinence or controlled drinking) at baseline and help seeking for alcohol problems during the previous 12 months (yes/no). As estimate of as- sociation we calculated the Odds Ratios (OR) and corre- sponding 95% confidence intervals. The test of parallel lines was used to see whether the assumption of proportional odds was met. In case of a rejection of the proportional odds assumption, separate logistic regressions were used to examine how the ORs varied at the different thresholds.

Ordinal logistic regression ( fi gure 2A, B) predicts mem- bership of the minimal, mild, moderate and severe fatigue groups using all 24 cytokines, WCC, lymphocytes, neutrophils, ESR, CRP, ESSDAI scores and dryness scores, as well as patient-reported depression, anxiety and pain. The full model, with all parameters, correctly predicts fatigue in 67% of cases ( fi gure 2A). This model with all parameters was robust to the presence or absence of loose markers of disease activity (such as WCC, lymphocytes, neutrophils, ESR, CRP, ESSDAI and dryness scores), but sensitive to the presence or absence of cytokines, depression, anxiety and pain. The model predictions are reasonably accurate providing cytokines, depression and pain are retained. This suggests that measures of disease activity in pSS appear to be less Table 2 Clinical summary for pSS fatigue groups showing mean±SD for key demographics, haematological and clinical variables

Background: The concept of risk thresholds has been studied in medical decision making for over 30 years. During that time, physicians have been shown to be poor at estimating the probabilities required to use this method. To better assess physician risk thresholds and to more closely model medical decision making, we set out to design and test a method that derives thresholds from actual physician treatment recommendations. Such an approach would avoid the need to ask physicians for estimates of patient risk when trying to determine individual thresholds for treatment. Assessments of physician decision making are increasingly relevant as new data are generated from clinical research. For example, recommendations made in the setting of ocular hypertension are of interest as a large clinical trial has identified new risk factors that should be considered by physicians. Precisely how physicians use this new information when making treatment recommendations has not yet been determined. Results: We derived a new method for estimating treatment thresholds using ordinal logistic regression and tested it by asking ophthalmologists to review cases of ocular hypertension before expressing how likely they would be to recommend treatment. Fifty-eight physicians were recruited from the American Glaucoma Society. Demographic information was collected from the participating physicians and the treatment threshold for each physician was estimated. The method was validated by showing that while treatment thresholds varied over a wide range, the most common values were consistent with the 10-15% 5-year risk of glaucoma suggested by expert opinion and decision analysis.

Abstract: Our study is to investigate the relationships between the metabolic syndrome (MS) components and the risks of the prostate cancer (PCa) in Chinese Han male population. We studied 186 PCa patients with or without MS and 107 healthy controls. Clinical data including age, body mass index (BMI), systolic blood pressure (SBP), diastolic blood pressure (DBP), fasting blood glucose (FBG), triglyceride (TG), total cholesterol (TCHO), high density lipoprotein (HDL), low density lipoprotein (LDL) and other related indicators were collected. The relationships between cases of PCa and controls were analyzed by t-test. The relationships between high-risk cases, low-risk cases and controls were analyzed by the analysis of variance (ANOVA) and ordinal logistic regression with SPSS 18.0. The age, BMI, DBP, TCHO and HDL were statistically significant between PCa patients and controls (P<0.05), but the age, DBP, TG, TCHO and HDL were statistically significant between high-risk cases, low-risk cases of PCa and controls these three groups (P<0.05). Among them, the age and TCHO were statistically significant not only between high-risk cases and controls but also between low-risk cases and controls. The DBP and HDL were statistically significant between high-risk cases and controls only. As mentioned, BMI is statistically significant between PCa cases and controls, but it is not statistically significant between high-risk cases, low-risk cases and controls these three groups and TG is just the opposite. It means that BMI is associated with the risks of PCa occurrence, which is not associated with high or low risks of occurred PCa. TG is associated with the high-risk of occurred PCa, which is not with the risks of PCa occurrence. The age, DBP, TCHO and HDL were associated with the risks of PCa occurrence and the degree of occurred PCa risks. BMI is associated with the risks of PCa occurrence and TG is associated with the high-risk of occurred PCa only.

The empirical analysis in this paper consists of three parts and proceeds as follows. At the outset, we use latent class analysis (LCA) to explore potential forms of community environmental satisfaction in the study population. As a prominent branch of structural equation modelling, LCA addresses the complex pat- tern of association that appears among observations. The key logic of LCA is that the method is ‘respon- dent-centred’ , as it allows us to classify the study population based on the proximity or distance of their scores on the variables. LCA models seek to as- sign individual respondents to one of a number of subgroups, i.e. classes with similar patterns. Using the classes captured in LCA as the dependent variable, we then establish a multinomial logistic regression model to examine the sociodemographic characteris- tics of different forms of community environmental satisfaction. The last analysis consists of a series of ordinal logistic regression models, which aim to cap- ture the association between community environmen- tal satisfaction and happiness among migrant cohorts in urban China.

Another limitation is that the questionnaires are not first-hand. The present study investigated whether the guardian who answered the questionnaire felt that the child seemed distressed, which cannot rule out the possi- bility that the child was not actually distressed. Addition- ally, parents who were distressed may have overestimated their children’s distress. However, we considered that getting first-hand information from preschool children would not be easy because of immaturity, and alterna- tively asked the guardians. Furthermore, the presence of Tourette symptoms was assessed based on observa- tions by the guardians. This is a major limitation since the assessment of Tourette symptoms can be a challenge even for experienced clinicians, but it would have been impractical for clinicians to screen all children in such a large sample for the presence of individual Tourette symptoms. The same are true for the assessment of other items assessed in this study, such as compulsive-like behaviors and ASD, ADHD, internalizing behavior, and externalizing behavior traits. We determined that asking guardians, who look after the children on a daily basis, for Table 4 Stepwise ordinal logistic regression analysis