Is a Classification Procedure Good Enough?-A Goodness-of-Fit Assessment Tool for Classification Learning

Abstract Background: High burden of chronic cardio-metabolic disease (CCD) including type 2 diabetes mellitus (T2DM), chronic kidney disease (CKD), and cardiovascular disease (CVD) have been reported in the Middle East and North Africa region. We aimed to externally validate a Europoid risk assessment tool designed by Alssema et al, including non-laboratory measures, for the prediction of the CCD in the Iranian population. Methods: The predictors included age, body mass index, waist circumference, use of antihypertensive, current smoking, and family history of cardiovascular disease and or diabetes. For external validation of the model in the Tehran lipids and glucose study (TLGS), the Area under the curve (AUC) and the Hosmer-Lemeshow (HL) goodness of fit test were performed for discrimination and calibration, respectively. Results: Among 1310 men and 1960 women aged 28-85 years, 29.5% and 47.4% experienced CCD during the 6 and 9-year follow-up, respectively. The model showed acceptable discrimination, with an AUC of 0.72(95% CI: 0.69-0.75) for men and 0.73(95% CI: 0.71-0.76) for women. The calibration of the model was good for both genders (min HL P=0.5). Considering separate outcomes, AUC was highest for CKD (0.76(95% CI: 0.72-0.79)) and lowest for T2DM (0.65(95% CI: 0.61-0.69)), in men. As for women, AUC was highest for CVD (0.82(95% CI: 0.78-0.86)) and lowest for T2DM (0.69(95% CI: 0.66-0.73)). The 9-year follow-up demonstrated almost similar performances compared to the 6-year follow-up. Conclusion: This model showed acceptable discrimination and good calibration for risk prediction of CCD in short and long-term follow-up in the Iranian population.

Download Full-text

Applied AVSWAT 2000 for Assessment of Pollutant Load in Brantas River Basin, Indonesia

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.250-253.3945 ◽

2011 ◽

Vol 250-253 ◽

pp. 3945-3948

Author(s):

Mohammad Sholichin ◽

Faridah Othman ◽

S.M Shirazi ◽

Shatirah Akib ◽

Donny Harisuseno ◽

...

Keyword(s):

Water Quality ◽

River Basin ◽

Stream Flow ◽

Goodness Of Fit ◽

Assessment Tool ◽

Organic N ◽

Nutrient Load ◽

Organic P ◽

Dominant Type ◽

Pollutant Load

This paper presented the results of assessment pollutant load such as nutrient and phosphorus on Brantas River basin Indonesia. A Soil and Water Assessment Tool (SWAT) was choose to applied in this study due to successful for simulate the effect land used management from large watershed in many countries. Stream flow and sediment yield were calibrated for the 1991-2003 period and validated for the 2004-2006 period. The resulting statistical goodness-of-fit was evaluated with the Nash-Sutcliffe coefficient NS = 0.38 and R2 of the one-to-one line for monthly stream flow was 0.725. Results showed that annual average nutrient loads such as organic N, organic P, nitrate, sediment P increased in trend from 1991 to 2006.Simulated results showed that average annual nutrient load was 60.88 kg N/ha/yr for organic N, 11.64 kg N/ha/yr for Nitrate, 0.08 kg P/ha/yr for organic P and 0.25 kg P/ha/yr for soluble P, respectively. The most dominant type of land use contributing to increased nutrient load in rivers was the rice field. The water quality of Brantas River did not meet class II in term of nutrient parameters based on local water quality standard.

Download Full-text

Improvement of model evaluation by incorporating prediction and measurement uncertainty

10.5194/hess-2017-66 ◽

2017 ◽

Author(s):

Lei Chen ◽

Shuang Li ◽

Yucen Zhong ◽

Zhenyao Shen

Keyword(s):

Measurement Uncertainty ◽

Model Evaluation ◽

Goodness Of Fit ◽

Assessment Tool ◽

Model Performance ◽

Evaluation Process ◽

Distribution Functions ◽

Cumulative Distribution ◽

New Approaches ◽

Three Gorges Region

Abstract. Numerous research studies have been conducted to assess uncertainty in hydrological and nonpoint source pollution predictions, but few studies have considered both prediction and measurement uncertainty in the model evaluation process. In this study, the Cumulative Distribution Function Approach (CDFA) and the Monte Carlo Approach (MCA) were used to develop two new approaches for model evaluation within an uncertainty framework. For the CDFA, a new distance between the cumulative distribution functions of the predicted data and the measured data was established, whereas the MCA was proposed to address conditions with dispersed data points. These new approaches were then applied in combination with the Soil and Water Assessment Tool in the Three Gorges Region, China. Based on the results, these two new approaches provided more accurate goodness-of-fit indicators for model evaluation compared to traditional methods. The model performance worsened when the error range became larger, and the choice of probability density functions (PDFs) affected model performance, especially for non-point source (NPS) predictions. The case study showed that if the measured error is small and if the distribution can be specified, the CDFA and MCA could be extended to other model applications within an uncertain condition.

Download Full-text

Modeling the Hydrological Characteristics of Hangar Watershed, Ethiopia

10.22541/au.160775467.77784100/v1 ◽

2020 ◽

Author(s):

Abdata Galata

Keyword(s):

Goodness Of Fit ◽

Assessment Tool ◽

Swat Model ◽

Integrated Water Resources Management ◽

Water Balance Components ◽

Warm Up ◽

Hydrological Characteristics ◽

Digital Elevation ◽

Physically Based ◽

Elevation Model

Modelling the hydrological characteristics of watershed is a method of understanding behavior and simulating the water balance components of watershed for planning and development of integrated water resources management. The soil and water assessment tool (SWAT) physically based hydrological modelling was used for modelling hydrologic characteristics of the Hangar watershed. The data used for this study were digital elevation model (DEM), land use land cover data, soil map, climatological and hydrological data. The model calibrated and validated using measured streamflow data of 13 years (1990-2002) and 9 years (2003-2011) respectively including warm-up period. The SWAT model performs well for both calibration (R2 = 0.87, NSE = 0.82 and PBIAS = +1.4) and validation (R2 = 0.89, NSE = 0.88 and PBIAS = +1.2). The sensitivity analysis, which was carried out using 18 SWAT parameters, identified the 13 most sensitive parameters controlling the output variable and with which goodness-of-fit was reached. The analysis results indicated that the watershed receives around, 9.6%, 59.9%, and 30.5% precipitation during dry, wet and short rainy seasons respectively. The received precipitation was lost by 9.6 %, 40.5%, and 41.3% in the form of evapotranspiration for each seasons correspondingly. The surface runoff contribution to the Watershed were 3.8%, and 79.2% during dry and wet seasons respectively, whereas, it contributes by 17.0% during short rainy seasons.

Download Full-text

A novel high-resolution gridded precipitation dataset for Peruvian and Ecuadorian watersheds – development and hydrological evaluation

Journal of Hydrometeorology ◽

10.1175/jhm-d-20-0285.1 ◽

2021 ◽

Keyword(s):

Goodness Of Fit ◽

Hydrological Modeling ◽

Performance Metrics ◽

Assessment Tool ◽

Novel Approach ◽

The Pacific ◽

Precipitation Estimates ◽

Droughts And Floods ◽

Terrain Elevation ◽

Streamflow Simulation

Abstract A novel approach for estimating precipitation patterns is developed here and applied to generate a new hydrologically corrected daily precipitation dataset, called RAIN4PE (for ‘Rain for Peru and Ecuador’), at 0.1° spatial resolution for the period 1981-2015 covering Peru and Ecuador. It is based on the application of a) the random forest method to merge multi-source precipitation estimates (gauge, satellite, and reanalysis) with terrain elevation, and b) observed and modeled streamflow data to firstly detect biases and secondly further adjust gridded precipitation by inversely applying the simulated results of the eco-hydrological model SWAT (Soil and Water Assessment Tool). Hydrological results using RAIN4PE as input for the Peruvian and Ecuadorian catchments were compared against the ones when feeding other uncorrected (CHIRP and ERA5) and gauge-corrected (CHIRPS, MSWEP, and PISCO) precipitation datasets into the model. For that, SWAT was calibrated and validated at 72 river sections for each dataset using a range of performance metrics, including hydrograph goodness of fit and flow duration curve signatures. Results showed that gauge-corrected precipitation datasets outperformed uncorrected ones for streamflow simulation. However, CHIRPS, MSWEP, and PISCO showed limitations for streamflow simulation in several catchments draining into the Paċific Ocean and the Amazon River. RAIN4PE provided the best overall performance for streamflow simulation, including flow variability (low-, high- and peak-flows) and water budget closure. The overall good performance of RAIN4PE as input for hydrological modeling provides a valuable criterion of its applicability for robust countrywide hydrometeorological applications, including hydroclimatic extremes such as droughts and floods.

Download Full-text

Analysis of the Psychometric Properties of an Assessment Tool for Deviant Behavior in Adolescence

European Journal of Psychological Assessment ◽

10.1027/1015-5759/a000015 ◽

2010 ◽

Vol 26 (2) ◽

pp. 108-115 ◽

Cited By ~ 5

Author(s):

Giorgia Molinengo ◽

Silvia Testa

Keyword(s):

Psychometric Properties ◽

Goodness Of Fit ◽

Deviant Behavior ◽

Assessment Tool ◽

Factor Model ◽

Three Dimensions ◽

Deviant Behaviors ◽

Behavior Scale ◽

Interrelated Factor ◽

And Gender

The study explores the psychometric properties of a deviant behavior scale for adolescents based on Jessor’s problem behavior theory. The sample consisted of 2191 Italian adolescents aged between 13 and 24 years (M = 16.2, SD = 1.6) attending different types of secondary schools in Piemonte and Valle d’Aosta. The results demonstrate goodness of fit for a three interrelated factor model corresponding to the three most common deviant behaviors in adolescents – “physical aggression,” “theft and vandalism,” and “lying and disobedience.” Furthermore, the three dimensions prove to possess a satisfactory degree of reliability. Multigroup analyses show that the three-factor structure is substantially stable over age and gender subgroups.

Download Full-text

RETRACTED: Persian Version of VEINES-QOL/Sym Questionnaire in Iranian Patients With Deep Venous Thrombosis: Cross-Cultural Adaptation and Psychometric Properties

Journal of Nursing Measurement ◽

10.1891/1061-3749.26.2.e98 ◽

2018 ◽

Vol 26 (2) ◽

pp. E98-E113

Author(s):

Amir Hossein Goudarzian ◽

Hamed Jafarpour ◽

Pantea Tajik ◽

Mozhgan Taebi ◽

Misagh Shafizad ◽

...

Keyword(s):

Venous Thrombosis ◽

Deep Venous Thrombosis ◽

Psychometric Properties ◽

Goodness Of Fit ◽

Assessment Tool ◽

Cross Cultural ◽

Persian Version ◽

Cultural Adaption ◽

Retraction Notice ◽

Iranian Patients

RETRACTION NOTICERetraction notice for this article available at Background and Purpose:The present study was done to assess the cultural adaption and psychometric properties of Persian version of VEINES-QOL/Sym questionnaire in Iranian patients with deep venous thrombosis (DVT).Methods:This cross-cultural psychometrics study was conducted in 2016. About 270 DVT patients completed a Persian version of the VEINES-QOL/Sym questionnaire. The face, content, and construct validity were assessed. Internal consistency, test–retest, and construct reliability (CR) were used to assess reliability.Results:Three-factor solution was extracted that explaining 71.373% of the total variance. Goodness-of-fit indices (GFI; χ2(68) =332.037, p < .05, χ2/df = 4.882, GFI = .862, CFI = .928, NFI = .914, IFI = .928, RMSEA (90% confidence interval) =.091 [.081, .110]) in the final VEINES-QOL/Sym questionnaire structure demonstrated the adequacy of the three-domain structure. The reliability was greater than .70.Conclusions:The VEINES-QOL/Sym questionnaire was found to be a valid and reliable assessment tool for quality of life in Iranian patients with DVT.

Download Full-text

Predictive value of Score for Neonatal Acute Physiology and Perinatal Extension II for neonatal mortality in Sanglah Hospital, Denpasar, Indonesia

Paediatrica Indonesiana ◽

10.14238/pi56.5.2016.257-61 ◽

2017 ◽

Vol 56 (5) ◽

pp. 257

Author(s):

I Gede Ketut Aryana ◽

I Made Kardana ◽

I Nyoman Adipura

Keyword(s):

Intensive Care ◽

Neonatal Mortality ◽

Goodness Of Fit ◽

Assessment Tool ◽

Area Under The Curve ◽

Severe Infection ◽

Scoring Systems ◽

World Health ◽

Severe Illness ◽

Goodness Of Fit Test

Background Neonatal mortality, which is largely caused by severe illness, is the biggest contributor to overall infant mortality. The World Health Organization (WHO) estimated that 4 million neonates die yearly worldwide, often due to severe infection and organ system immaturity. Neonates with severe illness require treatment in the neonatal intensive care unit (NICU), in which a reliable assessment tool for illness severity is needed to guide intensive care requirements and prognosis. Neonatal disease severity scoring systems have been developed, including Score for Neonatal Acute Physiology and Perinatal Extension II (SNAPPE II), but it has never been validated in our setting.ObjectiveTo study the prognostic value of SNAPPE II as a predictor of neonatal mortality in Sanglah Hospital, Denpasar, Indonesia.Methods This prospective cohort study was conducted in the NICU of Sanglah Hospital, Denpasar from November 2014 to February 2015. All neonates, except those with congenital anomaly, were observed during the first 12 hours of admission and their outcomes upon discharge from the NICU was recorded. We assessed the SNAPPE II cut-off point to predict neonatal mortality. The calibration of SNAPPE II was done using the Hosmer-Lemeshow goodness-of-fit test, and discrimination of SNAPPE II was determined from the receiver-operator characteristic (ROC) curve and area under the curve (AUC) value calculation.ResultsDuring the period of study, 63 children were eligible, but 5 were excluded because of major congenital abnormalities. The SNAPPE II optimum cut-off point of 37 gave a high probability of mortality and the ROC showed an AUC of 0.92 (95%CI 0.85 to 0.99). The Hosmer-Lemeshow goodness-of-fit test showed a good calibration with P = 1.0Conclusion The SNAPPE II has a good predictive ability for neonatal mortality in Sanglah Hospital, Denpasar, Indonesia.

Download Full-text

Test for Mobile phone dependence: psychometric properties and confirmatory factor analysis

Current Psychology ◽

10.1007/s12144-021-01449-5 ◽

2021 ◽

Author(s):

Michela Vezzoli ◽

Aurora Colombo ◽

Alessandra Marano ◽

Giorgia Zoccatelli ◽

Cristina Zogmaister

Keyword(s):

Factor Analysis ◽

High School Students ◽

Confirmatory Factor Analysis ◽

Mobile Phone ◽

Psychometric Properties ◽

Goodness Of Fit ◽

Assessment Tool ◽

School Students ◽

Confirmatory Factor ◽

Lack Of Control

AbstractThe Test of Mobile Phone Dependence (TMD) is a questionnaire designed for appraising the main dimensions of problematic smartphone use in adolescence. This study evaluates the factor structure and psychometric properties of the TMD on a sample of 813 Italian middle and high school students. The original three-factor model (Abstinence, Lack of Control, and Tolerance) of the TMD was tested through a Confirmatory Factor Analysis. The results of the goodness of fit indices indicated a satisfactory solution. The overall TMD score showed a good level of internal consistency and good construct validity with the duration of use, age of possession of the first mobile phone, perceived self-efficacy, gender, and participants’ age. The relationship between TMD and Nomophobia was also explored. Overall, the results indicate that the TMD is a valid and reliable assessment tool in Italian culture. However, reliability issues emerged on the subfactor Lack of Control. This indicates that the scores on this subfactor should be treated with caution.

Download Full-text

Psychometric properties of the Bangla version of multidimensional scale of perceived social support

Psihologija ◽

10.2298/psi200319026i ◽

2020 ◽

pp. 26-26

Author(s):

Nurul Islam

Keyword(s):

Social Support ◽

Factor Analysis ◽

Psychometric Properties ◽

Factor Structure ◽

Goodness Of Fit ◽

Assessment Tool ◽

Perceived Social Support ◽

Cross Sectional ◽

Split Sample ◽

Three Factor

The Bangla version of the Multidimensional Scale of Perceived Social Support (MSPSS-B) is a popular psychological assessment tool in Bangladesh. It has largely been used to measure perceived social support of Bangladeshi people. In spite of its popularity, it had not gone through an extensive validation procedure yet. Even its psychometric properties were not tested before, except for the test-retest reliability. This cross-sectional study aimed to examine the psychometric properties of MSPSS-B through a questionnaire survey among 812adult Bangladeshi people. The MSPSS-B revealed a three-factor structure through exploratory factor analysis (EFA) on the first split sample (n = 403), explaining 71.64% of the total variance. Acceptable goodness of fit indices (?2/df = 4.293, p = .000, GFI = .920, CFI = .926, TLI = .904, SRMR = .063, and RMSEA = .078) in the MSPSS-B were obtained through confirmatory factor analysis (CFA) on the second split sample (n = 409). The three-factor structure of the MSPSS-B was the same as the original English MSPSS. Acceptable internal item consistencies, significant test-retest reliabilities, reliabilities between two scale versions, convergent and discriminant validities, and measurement invariance between two gender groups were also established in the MSPSS-B through different statistical analyses. Thus, the MSPSS-B with its three factors can be used as a valid and reliable measure to assess the perceived social support of Bangladeshi people.

Download Full-text