Logistic Regression

Logistic Regression not to be confused with Linear Regression. The former takes categorical / binary/ discrete values, whereas the latter takes continuous value for the dependent or target variable.

Logistic Regression solves classification problem whereas Linear Regression solves regression problems.

Logistic regression is similar to a linear regression, but the curve is constructed using the natural logarithm of the “odds” of the target variable, rather than the probability. Moreover, the predictors do not have to be normally distributed or have equal variance in each group.

To put it simply; In Python Logistic Regression algorithm is known as Logistic Regression Classifier.

Logistic Regression is nearly of ‘s’ shape. It uses Sigmoid/Logistic function.

Advantages of Logistic Regression

• It is easy to implement and train the data.
• Can be used with Categorical data.
• Variance is low.
• Used for feature extraction
• Logistic models can be updated easily with new data using stochastic gradient descent
• provides great efficiency, widely used alogorithm.

Disadvantages of Logistic Regression

• Logistic Regression can only predict a categorical outcome.
• Vulnerable to overfitting
• Suitable for linear data

Applications

• Image Segmentation and Categorization
• Geographic Image Processing
• Handwriting recognition
• Spam detection
• Weather Prediction
• Illness detection

When to use:

• When we want adjusted odds ratio where we know more than one risk factors.
• When chi-square test is not significant.

For further explanation and clarity refer to the video.