Explore chapters and articles related to this topic
Machine Learning Classifiers
Published in Rashmi Agrawal, Marcin Paprzycki, Neha Gupta, Big Data, IoT, and Machine Learning, 2020
Logistic regression, or logistic model or logit model, examines the relationship between a set of predictor variables and a categorical response variable, and determines the probability of occurrence of an event by modeling the response in terms of predictors using a logistic or sigmoid curve (DeGregory, Kuiper et al. 2018). Logistic regression models are binary logistic regression and multinomial logistic regression depending on whether the dependent variable is binary or not. If the dependent variable is binary, having two values, true or false, and independent variables are either continuous or categorical, binary logistic regression is applied. Multinomial logistic regression is applied when the response variable has more than two categorical values. The relationship between independent and dependent variables is represented as: Y=b0+b1X1+b2X2+………bnXn
Supervised Learning
Published in Peter Wlodarczak, Machine Learning and its Applications, 2019
Logistic regression (LR), or logit regression, is used to estimate the binary dependent variable based on one or on a set of discrete explanatory values. It is a widely-used model in machine learning and is used in many different areas. Logistic regression does not need a linear relationship between the dependent and the independent variable. It is used for classification when the dependent variable is binary (dichotomous), e.g., 0/1 or true/false. This is why it is also called binary logistic regression. Logistic regression calculates the probability of an event, such as success/failure. If the dependent variable has more than two categories, it is called multinomial logistic regression.
Classification of crimes based on socioeconomics using multinomial regression
Published in Yuli Rahmawati, Peter Charles Taylor, Empowering Science and Mathematics for Global Competitiveness, 2019
V.M. Santi, W. Rahayu, M. Japar
Multinomial logistic regression is a continuation of binary logistic regression in which the response variable category is more than two categories (Myers et al., 2010; Santi et al., 2017; Apsari et al., 2013). Multinomial logistic regression is very interesting because multinomial logistic regression does not test standard assumptions.
Electric vehicle car-sharing optimization relocation model combining user relocation and staff relocation
Published in Transportation Letters, 2021
Ning Wang, Jiahui Guo, Xiang Liu, Yiyu Liang
In order to define the target group for electric vehicle car-sharing service, multinomial logistic regression analysis was used in this section. Multinomial Logistic Regression mainly studies the regression relationship between independent variables and dependent variables, in which the dependent variable is a multi-category variable and the independent variable can be discrete or continuous. In this paper, the dependent variable is the willingness to choose electric vehicle car-sharing service (will certainly choose and may choose to be 1, neutral to be 2, may not choose and will certainly not choose to be 3). Independent variables include three major aspects: Travel behaviors (transportation mode, monthly transportation expenses); Consumer expectation (minimum acceptable driving range, minimum acceptable time to car-sharing station, and minimum acceptable waiting time plus processing time, minimum acceptable price); Consumer social-demographics characteristics (gender, age, whether there is a driving license, whether there is a private car, education, occupation, average monthly income, etc.).
Investigating influence factors of traffic violation using multinomial logit method
Published in International Journal of Injury Control and Safety Promotion, 2020
Tefera Bahiru Ambo, Jian Ma, Chuanyun Fu
In multinomial logistic regression the effect of any predictor/independent variable on the outcome variable can be tested using the likelihood ratio (LR) statistic test. Independent variables do not affect the dependent variable is the null hypothesis of the test, where the null model is calculated by taking the log likelihood of the observations with the response variable in the model with intercept alone (iteration zero). The final fitted model is calculated by taking the log likelihood of observations with all the independent variables. The difference of these two yields a chi-squared LR statistic which is a measure of how well the independent variables affect the dependent variable categories (Hosmer et al., 2013). When the LR statistic for the overall model is significant, then there is evidence that the predictors are effective and they have contributed to the prediction of the dependent variable.
Modeling expressway lane utilization and lane choice behaviour: a case study on Delhi–Gurgaon Expressway
Published in Transportation Letters, 2019
Chaitrali Shirke, Nikhil Sumanth, Shriniwas Arkatkar, Ashish Bhaskar, Gaurang Joshi
In the multinomial logistic regression model, the Wald test (and associated p-value) is used to evaluate whether or not the logistic coefficient is different than zero. In Table 6a, B i.e. logistic coefficient of lane utilization factor is positive and significant which indicate that as lane utilization factor for lane j (j = 1, 2, 3) increases, vehicles will choose lane j over lane 4 which is taken as reference lane. The odd ratio increased by 7.339 times for lane1 compare to lane 4, suggesting that vehicles are more willing to choose lane 1 compare to lane 4. Similarly, the odd ratio increased by 6.34 and 3.67 times for lane 2 and lane 3, respectively, as compared to lane 4.This conclusion can be justified from the fact that the lane which is preferred by more and more vehicles, will have higher utilization factor as compared to the lane which is least preferred by vehicles.