Chain Reversion for Detecting Associations in Interacting Variables—St. Nicolas House Analysis

Hermanussen, Michael; Aßmann, Christian; Groth, Detlef

doi:10.3390/ijerph18041741

Cited by 23 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Series of coefficients of determinants that are characterized by the symmetry of ranks of R² both in forward and in backward direction are named "association chains". Thus, association chains formed are ranked according to magnitude of correlation coefficients (R 2 ), e.g., c Performance measures, the balanced classification rate and the F1score showed that SNHA was superior to methods using sophisticated correlation value thresholds and methods based on partial correlations for analyzing bands and hubs (Groth et al 2019;Hermanussen et al 2021). This technique is suitable for handling multiple correlations usually encountered in anthropometric and various socio-economic and socio-demographic variables (Groth et al 2019).…”

Section: Discussionmentioning

confidence: 99%

No association between body height and metabolic risk factors in historically short height Asian Indian tribes

Dorjee

Sen

Das

et al. 2022

HBPH

View full text Add to dashboard Cite

Background Asian Indians often get predisposed to non-communicable diseases for which the "thin-fat" or "hidden obese" Indian phenotype is usually regarded responsible. In Europe, America and in some low-middle-income countries (LMICs) short height is often associated with a high risk of metabolic syndrome (MetS). Indians and particularly tribal Indian people are relatively short. Aim To assess the associations of height with MetS risk factors among tribal people of India. Sample and methods This study was conducted among tribes of India under life-style transition. The height range was 163.2 cm to 156.5 cm (males) and 151.6 cm to 146.9 cm (females). The participants were 1066 men and 1090 women aged between 20 and 60 years. Anthropometric and metabolic markers included in the study were height, body mass index (BMI), waist circumference (WC), skinfolds (biceps, triceps, sub-scapular, and supra-iliacal), fasting blood glucose (FBG), blood pressure (systolic and diastolic) and pulse rate (PR). ResultsThe highest correlation existed between height and WC (male: 0.21; female: 0.15). Correlations of body composition variables (BMI, WC, skinfolds) with MetS risk factors (FBG, SBP, DBP, PR) were not reliable (r < 0.30) among both sexes. St. Nicolas House Analysis revealed WC among males and WC and sub-scapular skinfolds among females sharing more connections with other nodes variables. Conclusions Unlike the people of the wealthy and often obese social strata of low-middle-income countries, and in Europe and North America, height of tribal Indian populations is not associated with metabolic risk factors, such as hypertension, elevated fasting blood sugar, and central obesity. Rather than linked to the phenotype, obesity appears to be associated with an obesogenic environment. Public health policy should focus on problems associated with obesogenic environments.Take home message for students Short body height cannot predispose individuals to MetS risk factors in the absence of an obesogenic environment.

show abstract

Section: Discussionmentioning

confidence: 99%

No association between body height and metabolic risk factors in historically short height Asian Indian tribes

Dorjee

Sen

Das

et al. 2022

HBPH

View full text Add to dashboard Cite

show abstract

“…St. Nicolas House Analysis (SNHA) constructs networks based on association chains of variables based on their correlations. The method has advantages as it is non-parametric and there is no need to specify a selection threshold for including variables (Groth et al 2019;Hermanussen et al 2021).…”

Section: Network Construction Methodsmentioning

confidence: 99%

“…The set contains data of variables related to the health status of 189 children and their mothers, collected at Baystate Medical Center, Springfield, Mass during 1986: age -mother's age in years, lwt -mother's weight in pounds at last menstrual period, eth -mother's ethnicity (1 = white, 2 = black, 3 = other), smo -smoking status during pregnancy (0 = no, 1 = yes), ptl -number of previous premature labours, ht -history of hypertension (0 = no, 1 = yes), ui -presence of uterine irritability (0 = no, 1 = yes), ftv -number of physician visits during the first trimester, bwt birth weight of child in grams, rndsome random uncorrelated data. For graph construction the St. Nicolas House algorithm was used(Groth et al 2019;Hermanussen et al 2021).…”

mentioning

confidence: 99%

Network reconstruction based on synthetic data generated by a Monte Carlo approach

Novine

Mattsson

Groth

2022

HBPH

Self Cite

View full text Add to dashboard Cite

Background: Network models are useful tools for researchers to simplify and understand investigated systems. Yet, the assessment of methods for network construction is often uncertain. Random resampling simulations can aid to assess methods, provided synthetic data exists for reliable network construction. Objectives: We implemented a new Monte Carlo algorithm to create simulated data for network reconstruction, tested the influence of adjusted parameters and used simulations to select a method for network model estimation based on real-world data. We hypothesized, that reconstructs based on Monte Carlo data are scored at least as good compared to a benchmark. Methods: Simulated data was generated in R using the Monte Carlo algorithm of the mcgraph package. Benchmark data was created by the huge package. Networks were reconstructed using six estimator functions and scored by four classification metrics. For compatibility tests of mean score differences, Welch’s t-test was used. Network model estimation based on real-world data was done by stepwise selection. Samples: Simulated data was generated based on 640 input graphs of various types and sizes. The real-world dataset consisted of 67 medieval skeletons of females and males from the region of Refshale (Lolland) and Nordby (Jutland) in Denmark. Results: Results after t-tests and determining confidence intervals (CI95%) show, that evaluation scores for network reconstructs based on the mcgraph package were at least as good compared to the benchmark huge. The results even indicate slightly better scores on average for the mcgraph package. Conclusion: The results confirmed our objective and suggested that Monte Carlo data can keep up with the benchmark in the applied test framework. The algorithm offers the feature to use (weighted) un- and directed graphs and might be useful for assessing methods for network construction.

show abstract

“…After calculating all possible bivariate correlations, we performed a primary data exploration with St. Nicolas House Analysis (SNHA) (Groth et al 2019;Hermanussen et al 2021). This new statistical method is a robust non-parametric statistical tool for immediate visualization of essential associations between extensive interacting variables.…”

Section: Statisticsmentioning

confidence: 99%

Vietnamese migrants are as tall as they want to be

Hermanussen

Nguyen

Hermanussen³

2021

HBPH

Self Cite

View full text Add to dashboard Cite

Background Members of the same social group tent to have the same body height. Migrants tend to adjust in height to their host communities. Objectives Social-Economic-Political-Emotional (SEPE) factors influence growth. We hypothesized that Vietnamese young adult migrants in Germany (1) are taller than their parents, (2) are as tall as their German peers, and (3) are as tall as predicted by height expectation at age 13 years. Sample and Methods The study was conducted in 30 male and 54 female Vietnamese migrants (mean age 26.23 years. SD=4.96) in Germany in 2020. Information on age, sex, body height, school and education, job, height and ethnicity of best friend, migration history and cultural identification, parental height and education, and recalled information on their personal height expectations at age 13 years were obtained by questionnaire. The data were analyzed by St. Nicolas House Analysis (SNHA) and multiple regression. Results Vietnamese young adults are taller than their parents (females 3.85cm, males 7.44cm), but do not fully attain height of their German peers. The body height is positively associated with the height of best friend (p < 0.001), the height expectation at age 13 year (p < 0.001), and father height (p=0.001). Conclusion Body height of Vietnamese migrants in Germany reflects competitive growth and strategic growth adjustments. The magnitude of this intergenerational trend supports the concept that human growth depends on Social-Economic-Political-Emotional (SEPE) factors.

show abstract

Chain Reversion for Detecting Associations in Interacting Variables—St. Nicolas House Analysis

Cited by 23 publications

References 11 publications

No association between body height and metabolic risk factors in historically short height Asian Indian tribes

No association between body height and metabolic risk factors in historically short height Asian Indian tribes

Network reconstruction based on synthetic data generated by a Monte Carlo approach

Vietnamese migrants are as tall as they want to be

Contact Info

Product

Resources

About