Predictive Models Using Regression

McCarthy, Richard V.; McCarthy, Mary M.; Ceccucci, Wendy; Halawi, Leila

doi:10.1007/978-3-030-14038-0_4

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, here we present the results of Pearson's analysis related to outdoor temperature and relative humidity. In fact, only for these meteorological parameters, results showed significant statistical correlations, and in most cases related probability values were much lower than 5% [36]. Here, we present Pearson's analyses performed over eight couples of experimental data series.…”

Section: Resultsmentioning

confidence: 93%

“…In simple terms, the null hypothesis implies that no linear relationship exists between variables, and the p-value can be seen as the probability that the current results would be found if the correlation were, in fact, null (which is exactly within the null hypothesis). Conventionally, if the probability value is lower than 5% (p-value < 0.05) the correlation coefficient may be called statistically significant [36].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Preliminary Investigation on the Statistical Correlations between SARS-CoV-2 Spread and Local Meteorology

Passerini

Mancinelli

Morichetti

et al. 2020

IJERPH

View full text Add to dashboard Cite

The statistical correlation between meteorological parameters and the spread of Coronavirus Disease-2019 (COVID-19) was investigated in five provinces of Italy selected according to the number of infected individuals and the different trends of infection in the early stages of the epidemic: Bergamo and Brescia showed some of the highest trends of infections while nearby Cremona and Mantova, showed lower trends. Pesaro–Urbino province was included for further investigation as it was comparably affected by the epidemic despite being the area far from the Po valley. Moving means of the variables were considered to take into account the variability of incubation periods and uncertainties in the epidemiological data. The same analyzes were performed normalizing the number of new daily cases based on the number of checks performed. For each province, the moving mean of adjusted and unadjusted new daily cases were independently plotted versus each meteorological parameter, and linear regressions were determined in the period from 29th of February 2020 to 29th of March 2020. Strong positive correlations were observed between new cases and temperatures within three provinces representing 86.5% of the contagions. Strong negative correlations were observed between the moving means of new cases and relative humidity values for four provinces and more than 90% of the contagions.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Methodsmentioning

confidence: 99%

A Preliminary Investigation on the Statistical Correlations between SARS-CoV-2 Spread and Local Meteorology

Passerini

Mancinelli

Morichetti

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…Regression is a statistical analysis method used to determine the relationship between one dependent variable and multiple independent variables [26]. ere are different types of Regression models or algorithms by which one can easily estimate the criticality of the problem accordingly [27]; that is, (i) Linear Regression identified the relationship existing between predicted values and targeted values [19]. (ii) Ridge Regression examines the labels based on a statistical-based fundamental relationship.…”

Section: Regressionmentioning

confidence: 99%

Systematic Framework to Predict Early‐Stage Liver Carcinoma Using Hybrid of Feature Selection Techniques and Regression Techniques

et al. 2022

View full text Add to dashboard Cite

The liver is the human body’s mandatory organ, but detecting liver disease at an early stage is very difficult due to the hiddenness of symptoms. Liver diseases may cause loss of energy or weakness when some irregularities in the working of the liver get visible. Cancer is one of the most common diseases of the liver and also the most fatal of all. Uncontrolled growth of harmful cells is developed inside the liver. If diagnosed late, it may cause death. Treatment of liver diseases at an early stage is, therefore, an important issue as is designing a model to diagnose early disease. Firstly, an appropriate feature should be identified which plays a more significant part in the detection of liver cancer at an early stage. Therefore, it is essential to extract some essential features from thousands of unwanted features. So, these features will be mined using data mining and soft computing techniques. These techniques give optimized results that will be helpful in disease diagnosis at an early stage. In these techniques, we use feature selection methods to reduce the dataset’s feature, which include Filter, Wrapper, and Embedded methods. Different Regression algorithms are then applied to these methods individually to evaluate the result. Regression algorithms include Linear Regression, Ridge Regression, LASSO Regression, Support Vector Regression, Decision Tree Regression, Multilayer Perceptron Regression, and Random Forest Regression. Based on the accuracy and error rates generated by these Regression algorithms, we have evaluated our results. The result shows that Random Forest Regression with the Wrapper Method from all the deployed Regression techniques is the best and gives the highest R2-Score of 0.8923 and lowest MSE of 0.0618.

show abstract

“…The conditioning model for predicting propensity scores Logistic regression: The process of obtaining propensity scores with logistic regression is very simple and easy to understand and perform, but the model must be transformed into a linear model via an appropriate connection function such as the logit function [31]. However, when the relationship between covariates and transformation variables does not satisfy the linear hypothesis, the values of the propensity scores are often unreliable.…”

Section: Sci Forschenmentioning

confidence: 99%

Logistic Regression and Generalized Boosted Modelling in Inverse Probability of Treatment Weighting: A Simulation and Case Study of Outpatients with Coronary Heart Disease

Wang¹,

Xie²,

Liu³

et al. 2019

J Epidemiol Public Health Rev

View full text Add to dashboard Cite

Objectives: To compare the ability of logistic regression and generalized boosted modelling (GBM) to estimate treatment effects and balance covariates in inverse probability of treatment weighting (IPTW) and to explore the independent impact of different types of medical insurance on drug costs of outpatients with coronary heart disease based on this method.Methods: This study was used to evaluate the performance of logistic regression and GBM in IPTW under a Monte Carlo study with the simulated design of linear and nonlinear correlations between treatment variable and covariates of different sample sizes (n=500, 2000). The assessment indicators included average standardized absolute mean difference (ASAM), point estimation, bias, relative bias, standard error, mean square error, 95% confidence interval coverage rate, distribution of weights and an empirical study of outpatients with coronary heart disease was carried out after simulation. Results:The simulations show that GBM in propensity score weighting is superior to logistic regression in the lower bias and mean square error and it achieves better covariate balance, especially in nonlinear conditioning models. And in this case study. It's found that GBM in IPTW has better ability to balance the confounding factors compared with logistic regression. The weighted results show that the drug costs of outpatients with coronary heart disease of Urban Employee Basic Medical Insurance increase by 256.35 Yuan on average compared with those of Urban-Rural Resident Basic Medical Insurance. Conclusion:It may be better to control confounding factors in case of the unknown relationship between the treatment variable and covariates by IPTW with GBM. There is still a certain gap in drug costs among different types of medical insurance for patients with coronary heart disease according to this study, which provides a reasonable scientific basis for the optimal allocation of medical insurance system and health resources in coronary heart disease.

show abstract

Predictive Models Using Regression

Cited by 4 publications

References 0 publications

A Preliminary Investigation on the Statistical Correlations between SARS-CoV-2 Spread and Local Meteorology

A Preliminary Investigation on the Statistical Correlations between SARS-CoV-2 Spread and Local Meteorology

Systematic Framework to Predict Early‐Stage Liver Carcinoma Using Hybrid of Feature Selection Techniques and Regression Techniques

Logistic Regression and Generalized Boosted Modelling in Inverse Probability of Treatment Weighting: A Simulation and Case Study of Outpatients with Coronary Heart Disease

Contact Info

Product

Resources

About