Goodness of Fit for Categorical Variables

2005 ◽  
Author(s):  
Alexander von Eye ◽  
G. Anne Bogat ◽  
Stefan von Weber
Keyword(s):  
Goodness Of Fit ◽  
Categorical Variables

scholarly journals Factors Associated with Cognitive and Functional Performance in Indigenous Older Adults of Nariño, Colombia

2019 ◽  
Vol 2019 ◽  
pp. 1-9
Author(s):  
Yenny Vicky Paredes-Arturo ◽  
Eunice Yarce-Pinzon ◽  
Diego Mauricio Diaz-Velasquez ◽  
Daniel Camilo Aguirre-Acevedo
Keyword(s):  
Psychosocial Factors ◽  
Goodness Of Fit ◽  
Elderly Population ◽  
Functional Performance ◽  
Medical Condition ◽  
Developed Countries ◽  
Screening Tests ◽  
Categorical Variables ◽  
Functional Factors ◽  
Global Cognition

Introduction. Ethnicity in Latin America is a factor of poverty and social exclusion. Like in developed countries, demographic, medical, psychosocial, global cognitive, and functional variables interact in a complex relationship on the elderly population. Such interaction should be considered to determine cognitive and functional performance using screening tests. The aim of this study was to evaluate the demographic, medical, and psychosocial factors affecting global cognitive performance as well as functional activities. Methods. The study was conducted in a Colombian elderly indigenous population which included a sample of 518 adults. This research employed a structural model of latent factors to assess the effects of demographic, medical, and psychosocial factors on cognitive and functional performance. The model was estimated by least squares and used a maximum-likelihood procedure, and it was determined RMSEA, TLI, and CFI to assess the model’s goodness of fit. The categorical variables used in the model were as follows: (1) demographics, (2) psychosocial factors, (3) medical condition, (4) global cognition, and (5) functional factors. Results. Demographics, in addition to medical and psychosocial factors, were related to global cognition and functional factors (RMSEA = 0.051, CI 90% 0.045–0.057, CFI = 0.901, and TLI = 0.881). Conclusion. These results provide strong evidence about the complex relationships among demographics, medical conditions, and psychosocial factors and their influence on global cognition and functional performance in Colombian indigenous elderly population.

scholarly journals P90 Streamlining primary care referrals to an early inflammatory arthritis (EIA) clinic: distinguishing between patients with osteoarthritis and inflammatory arthritis

Rheumatology ◽  
2020 ◽  
Vol 59 (Supplement_2) ◽  
Author(s):  
Ben M Jacobs ◽  
Nichola Sarathchandra ◽  
Mayuri Karela ◽  
Louise E Daniels ◽  
Nirupam Purkayastha
Keyword(s):  
Clinical Diagnosis ◽  
Inflammatory Arthritis ◽  
Goodness Of Fit ◽  
Statistical Tests ◽  
Small Sample ◽  
Likelihood Method ◽  
Categorical Variables ◽  
Retrospective Audit ◽  
Common Diagnosis ◽  
Early Inflammatory Arthritis

Abstract Background To use biochemical markers and ultrasound to differentiate between inflammatory and noninflammatory diagnoses in the early inflammatory arthritis (EIA) referral setting. Careful patient selection is crucial to ensure timely and efficient use of secondary care resources. Methods A retrospective audit of the EIA pathway was conducted over six months at two partnered district general hospitals in London in 2018. For each of the 75 patients studied, data collected included demographics, biomarkers of disease and inflammation, appointments dates, details of scans requested, and the clinical diagnosis made at the EIA appointment. Statistical tests included pairwise comparisons using Welch’s 2-sample t-test for continuous variables and two-sample chi squared tests for equality of proportions with continuity correction for categorical variables. Logistic regression models were used, incorporating age, inflammatory markers and serostatus. Goodness of fit was evaluated using the log likelihood method and McFadden’s pseudo-R2. Predictive modelling was carried out using the Caret package. Analysis was conducted in R (R v3.5). Results Over half of participants (59%) were diagnosed with non-inflammatory disorders; the most common diagnosis was osteoarthritis (31%). Rheumatoid Arthritis (15%) was most common amongst the 41% of Inflammatory arthritides (IA). Ultrasound confirmed the clinical diagnosis of IA vs non-IA with 70% accuracy. There were no significant differences between those with and without ultrasound evidence of synovitis in terms of age (p 0.25), CRP (p 0.22), ESR (p 0.59), RF (p 0.43) or CCP (p 1) positivity. This null is likely due to a small sample size and lack of statistical power. Comparison of patients with a clinical diagnosis of IA vs non-IA revealed significantly increased CRP (9.5 vs 4.2 p 0.01) and CCP positivity rates (22.5% vs 0%, p 0.003) in the inflammatory group, with no significant differences in age (p 0.45), ESR (p 0.24), or RF positivity rate (p 0.18). In those with a clinical diagnosis of osteoarthritis, there were a significantly higher age (55.0 vs 43.5, p 0.0009), lower CRP (3.2 vs 7.8, p 0.005), and lower ESR (9.2 vs 19.7, p 0.006). Neither RF (p 0.73) nor CCP (p 0.16) positivity rates differed significantly between osteoarthritis or other diagnoses. Conclusion It was demonstrated that even in small cohorts, simple predictive variables can be used to risk-stratify and assess the likelihood that a patient will have osteoarthritis rather than IA. It is shown that older age, lower ESR and lower CRP are indicators at differentiating IA from non-IA. Given the national high prevalence of osteoarthritis and the clinical uncertainty in distinguishing osteoarthritis from IA, ultrasound has significant value in the diagnostic work-up. Further research should attempt to predict eventual diagnosis from clinical characteristics alone to help general practitioners distinguish patients with IA from those with non-IA. Disclosures B.M. Jacobs None. N. Sarathchandra None. M. Karela None. L.E. Daniels None. N. Purkayastha None.

scholarly journals COVID-19 and Obesity: An Epidemiologic Analysis of the Brazilian Data

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Diego Assis Gonçalves ◽  
Victória Ribeiro ◽  
Ana Gualberto ◽  
Fernanda Peres ◽  
Michaela Luconi ◽  
...  
Keyword(s):  
Goodness Of Fit ◽  
Ventilatory Support ◽  
Significant Risk ◽  
Epidemiological Data ◽  
Significant Risk Factor ◽  
Nonparametric Tests ◽  
Categorical Variables ◽  
Chi Square ◽  
Effective Prevention ◽  
Prevention Campaign

Brazil has the second highest number of deaths due to COVID-19. Obesity has been associated with an important role in disease development and a worse prognosis. We aimed to explore epidemiological data from Brazil, discussing the potential relationships between obesity and COVID-19 severity in this country. We used a public database made available by the Ministry of Health of Brazil (182700 patients diagnosed with COVID-19). Descriptive statistics were used to characterize our database. Continuous data were expressed as median and analyzed by the nonparametric tests Mann–Whitney or one-sample Wilcoxon. The frequencies of categorical variables have been analyzed by chi-square tests of independence or goodness-of-fit. Among the number of deaths, 74% of patients were 60 years of age or older. Patients with obesity who died of COVID-19 were younger (59 years (IQR = 23)) than those without obesity (71 years (IQR = 20), P < 0.001 , and η2 = 0.0424). Women with obesity who died of COVID-19 were older than men (55 years (IQR = 25) vs. 50 (IQR = 22), P < 0.001 , and η2 = 0.0263). Furthermore, obesity increases the chances of needing intensive care unit (OR: 1.783, CI: 95%, and P < 0.001 ), needing ventilatory support (OR: 1.537, CI: 95%, and P < 0.001 and OR: 2.302, CI: 95%, and P < 0.001 , for noninvasive and invasive, respectively), and death (OR: 1.411, CI: 95%, and P < 0.001 ) of patients hospitalized with COVID-19. Our analysis supports obesity as a significant risk factor for the development of more severe forms of COVID-19. The present study can direct a more effective prevention campaign and appropriate management of subjects with obesity.

Application of Cluster Analysis in Building Retirement Wealth Adequacy Profile: A Case Study in Malaysia

2020 ◽  
Vol 17 (2) ◽  
pp. 689-699
Author(s):  
Zarul Khaliff Kamal ◽  
Noriszura Ismail ◽  
Ros Idayuwati Alaudin
Keyword(s):  
Cluster Analysis ◽  
Private Sector ◽  
Goodness Of Fit ◽  
Likelihood Function ◽  
Multinomial Distribution ◽  
Hierarchical Cluster ◽  
Categorical Variables ◽  
Underlying Structure ◽  
Retirement Wealth ◽  
Monthly Salary

This study aims to examine retirement wealth adequacy based on the underlying structure of households’ attributes from Household Expenses and Income Survey 2014 (HEIS14) data. In specific, the two-step cluster analysis is carried out to build the profiles that will be used to compute retirement wealth adequacy. In general, the data that contains both numerical and categorical variables do not suit well for pure hierarchical and non-hierarchical cluster analysis. To counter this issue, the twostep cluster analysis employs log-likelihood function to measure the distance between two clusters, where the numerical variables are assumed to follow a normal distribution, meanwhile categorical variables are assumed to follow the multinomial distribution. We have used Schwarz’s Bayesian Criterion (BIC) and Akaike’s Information Criterion (AIC) to determine the number of clusters to be formed. In addition, we employed a Silhouette measure of cohesion and separation to examine the overall goodness-of-fit. The analysis successfully generated a solution of three clusters. The first cluster represents households with the majority of SPM holders, receiving an average gross monthly salary of RM 5058.73 and working in the private sector. The second cluster represents households with the majority of diploma holder/professional certificate, receiving an average gross monthly salary of RM 10154.06 and most of them (92%) working in the private sector. The third cluster represents households who work in the public sector with an average gross monthly salary of RM 7185.74. From the microsimulation process, the results show that 51% of households in Cluster 1 have adequate retirement wealth, while only 13% of households in Cluster 3 have adequate retirement wealth.

scholarly journals FREQUENCY OF ACUTE RISE OF INTRAOCULAR PRESSURE FOLLOWING YAG LASER POSTERIOR CAPSULOTOMY

2018 ◽  
Vol 16 (4) ◽  
pp. 109-112
Author(s):  
Muhammad Adnan Khan ◽  
Muhammad Tariq Khan ◽  
Ashfaq Ur Rehman ◽  
Mohammad Idris ◽  
Muhammad Ayub Khan
Keyword(s):  
Intraocular Pressure ◽  
Cataract Surgery ◽  
Goodness Of Fit ◽  
Yttrium Aluminum Garnet ◽  
Categorical Variables ◽  
Posterior Capsular Opacification ◽  
Cross Sectional ◽  
Yag Laser ◽  
Posterior Capsulotomy ◽  
Department Of Ophthalmology

Background: Posterior capsular opacification (PCO) is the most frequent complication of cataract surgery. The objective of this study was to determine the frequency of acute rise of intraocular pressure (IOP) following Neodymium-Yttrium Aluminum Garnet (Nd:Yag) laser posterior capsulotomy. Materials & Methods: This cross-sectional study was conducted in the Department of Ophthalmology, HMC, Peshawar, Pakistan, from July-December 2016. Sample size was 325 selected by consecutive sampling technique. Inclusion criteria were all patients having significant PCO after uneventful cataract surgery with intra ocular lens implant. Demographic variables were sex, age groups and age in years. Research variable was presence of acute rise of IOP following Yag laser capsulotomy. Pre-laser assessment included slit lamp examination and recording of IOP with Goldmann applanation tonometer by a single ophthalmologist. IOP was measured 3 hours after Nd: Yag laser capsulotomy. Rise in IOP was labeled when IOP was ≥5 mmhg from baseline. Mean ±SD was used to express quantitative variables like age. Categorical variables were analyzed as frequency and percentage. Goodness-of-fit was applied to compare the frequency of acute rise in IOP between sample and population. SPSS-20 was used for data entry and its analysis. Results: Out of 325 patients, 170(52.3%) were men and 155(47.7%) were women. The mean age of the sample was 44.92 ±23.843 years. A total of 107(32.9%) patients were 20-39 years old whereas 218(67.1%) were 40-70 years. IOP was raised in 61 (18.8%) patients while in 264(81.2%) patients it was not raised. The frequency of acute rise in IOP after Yag laser capsulotomy was significantly different in sample compared to population. Conclusion: Men were more than women, especially of old age. The frequency of acute rise in IOP after Yag laser capsulotomy was significantly different in sample compared to population.

scholarly journals Validating the Transformation of PROMIS-GH to EQ-5D in Adult Spine Patients

2019 ◽  
Vol 8 (10) ◽  
pp. 1506 ◽  
Author(s):  
Panchagnula ◽  
Sun ◽  
Montejo ◽  
Nouri ◽  
Kolb ◽  
...  
Keyword(s):  
Goodness Of Fit ◽  
Mean Squared Error ◽  
The United States ◽  
Coefficient Of Determination ◽  
Categorical Variables ◽  
Measurement Information ◽  
Sample Population ◽  
Health Index ◽  
Patient Reported ◽  
Adult Spine

Spinal disorders and associated interventions are costly in the United States, putting them in the limelight of economic analyses. The Patient-Reported Outcomes Measurement Information System Global Health Survey (PROMIS-GHS) requires mapping to other surveys for economic investigation. Previous studies have proposed transformations of PROMIS-GHS to EuroQol 5-Dimension (EQ-5D) health index scores. These models require validation in adult spine patients. In our study, PROMIS-GHS and EQ-5D were randomly administered to 121 adult spine patients. The actual health index scores were calculated from the EQ-5D instrument and estimated scores were calculated from the PROMIS-GHS responses with six models. Goodness-of-fit for each model was determined using the coefficient of determination (R2), mean squared error (MSE), and mean absolute error (MAE). Among the models, the model treating the eight PROMIS-GHS items as categorical variables (CATReg) was the optimal model with the highest R2 (0.59) and lowest MSE (0.02) and MAE (0.11) in our spine sample population. Subgroup analysis showed good predictions of the mean EQ-5D by gender, age groups, education levels, etc. The transformation from PROMIS-GHS to EQ-5D had a high accuracy of mean estimate on a group level, but not at the individual level.

Sign in / Sign up

Export Citation Format

Share Document