Skip to main content

Logistic Regression using R

 

1. What is Logistic Regression?

Logistic Regression is one of the machine learning algorithms used for solving classification problems. It is used to estimate probability whether an instance belongs to a class or not. If the estimated probability is greater than threshold, then the model predicts that the instance belongs to that class, or else it predicts that it does not belong to the class as shown in fig 1. This makes it a binary classifier. Logistic regression is used where the value of the dependent variable is 0/1, true/false or yes/no.


Example 1

Suppose we are interested to know whether a candidate will pass the entrance exam. The result of the candidate depends upon his attendance in the class, teacher-student ratio, knowledge of the teacher and interest of the student in the subject are all independent variables and result is dependent variable. The value of the result will be yes or no. So, it is a binary classification problem.


Why Logistic Regression, Not Linear Regression

Linear Regression models the relationship between dependent variable and independent variables by fitting a straight line.

In Linear Regression, the value of predicted Y exceeds from 0 and 1 range. As discussed earlier, Logistic Regression gives us the probability and the value of probability always lies between 0 and 1. Therefore, Logistic Regression uses sigmoid function or logistic function to convert the output between [0,1]. The logistic function is defined as:

1 / (1 + e^-value)

Where e is the base of the natural logarithms and value is the actual numerical value that you want to transform. The output of this function is always 0 to 1.

The equation of linear regression is

Y=B0+B1X1+...+BpXp

Logistic function is applied to convert the output to 0 to 1 range

P(Y=1)=1/(1+exp(?(B0+B1X1+…+BpXp)))

We need to reformulate the equation so that the linear term is on the right side of the formula.

log(P(Y=1)/1?P(Y=1))= B0+B1X1+…+BpXp

where log(P(Y=1)/1?P(Y=1)) is called odds ratio.

Comments

  1. Amazing Article! I would like to thank you for the efforts you had made for writing this awesome article. I will suggest you to check articles related to best data science course, at Learnbay.co website.

    ReplyDelete

Post a Comment

Popular posts from this blog

Data science: A Blend of These Data Components

Data Science Course ExcelR offers Data Science course, the most comprehensive Data Science course in the market, covering the complete Data Science lifecycle concepts from Data Collection, Data Extraction, Data Cleansing, Data Exploration, Data Transformation, Feature Engineering, Data Integration, Data Mining, building Prediction models, Data Visualization and deploying the solution to the customer. Skills and tools ranging from  Statistical Analysis , Text Mining, Regression Modelling, Hypothesis Testing, Predictive Analytics,  Machine Learning ,   Deep Learning, Neural Networks, Natural Language Processing, Predictive Modelling, R Studio, XLMiner,  Tableau , Spark, Hadoop, Minitab, programming languages like R programming ,  Python are covered extensively as part of this Data Science training. ExcelR is considered as the best Data Science training institute which offers services from training to placement as part of the Data Science training program wi...

Machine Learning Crash Course

Information science requires mastering in various fields like machine learning, R programming, Python, deep studying and plenty of extra. Machine Learning Engineer is categorized as one of the refined profiles due to the work profile in addition to the wage packages that the candidates draw from the companies. Many reinforcement studying algorithms use dynamic programming methods. This implies, through the use of a selected kind of algorithm, machines are given the facility of understanding the command and studying from there with out giving any further instructions or without programming again and again. It has been an important studying expertise for me. Online classroom training for Machine Learning Certification is carried out through online reside streaming of each class. The classification of information and labeling the information are trained in case of the supervised learning. The programme is designed for technology professionals who wish to advance their career as a spe...

Machine Studying Course Bangalore

Be taught the fundamentals of Machine Learning on this introductory course. A central application of unsupervised studying is within the field of density estimation in statistics , 26 though unsupervised learning encompasses other domains involving summarizing and explaining data features. According to Gartner, 2.three million Machine Learning Jobs shall be generated by 2020. If you have already got some experience in expertise and are serious about building a profession in the futuristic areas of Machine Studying, Deep Studying and AI, the PGPDM can equip you with all the abilities and instruments you need. The implementation particulars of these deep studying fashions along with tuning of the parameters will be illustrated in this course. I'd spent too much time building deep studying networks for ready datasets moderately than entering into the trenches and exploring data from scratch. I have completed my Machine studying training from Cetpa,Here i have discovered indepth in...