Logistic regression is the most widely used machine learning algorithm for classification problems. In its original form it is used for binary classification problem which has only two classes to predict. However with little extension and some human brain, logistic regression can easily be used for multi class classification problem. In this post I will be explaining about binary classification. I will also explain about the reason behind maximizing log likelihood function.
Multicollinearity occurs in a multi linear model where we have more than one predictor variables. So Multicollinearity exist when we can linearly predict one predictor variable (note not the target variable) from other predictor variables with significant degree of accuracy. It means two or more predictor variables are highly correlated. But not the vice versa means if there is low correlation among predictors then also multicollinearity may exist.
In R, stepAIC is one of the most commonly used search method for feature selection. We try to keep on minimizing the stepAIC value to come up with the final set of features. “stepAIC” does not necessarily means to improve the model performance, however it is used to simplify the model without impacting much on the performance. So AIC quantifies the amount of information loss due to this simplification. AIC stands for Akaike Information Criteria.
Feature selection is a way to reduce the number of features and hence reduce the computational complexity of the model. Many times feature selection becomes very useful to overcome with overfitting problem. It helps us in determining the smallest set of features that are needed to predict the response variable with high accuracy. if we ask the model, does adding new features, necessarily increase the model performance significantly? if not then why to add those new features which are only going to increase model complexity.
The coefficient of Determination is the direct indicator of how good our model is in terms of performance whether it is accuracy, Precision or Recall. In more technical terms we can define it as The Coefficient of Determination is the measure of the variance in response variable ‘y’ that can be predicted using predictor variable ‘x’. It is the most common way to measure the strength of the model.
Storytelling or presenting insights is the most important part of data analytics. This is the selling point of all your hard work. Doesn’t matter how much hard work you have put in developing analytic model until you are able to get the attention of the target audience. Here in this particular article, my focus is on how we can use beautiful graphs to show the insights regarding employee attrition rate from IBM HR Attrition data. After all, a picture is worth to thousands of words.
Linear Regression is a field of study which emphasizes on the statistical relationship between two continuous variables known as Predictor and Response variables. (Note: when there are more than one predictor variables then it becomes multiple linear regression.)
Predictor variable is most often denoted as x and also known as Independent variable.
Response variable is most often denoted as y and also known as Dependent variable.
Covariance and Correlation are very helpful in understanding the relationship between two continuous variables. Covariance tells whether both variables vary in same direction (positive covariance) or in opposite direction (negative covariance). There is no significance of covariance numerical value only sign is useful. Whereas Correlation explains about the change in one variable leads how much proportion change in second variable. Correlation varies between -1 to +1. If correlation value is 0 then it means there is no Linear Relationship between variables however other functional relationship may exist.
In any business there are some easy to measure variables like : Age, Gender, Income, Education Level etc. and there are some difficult to measure variables like amount of loan to give, no of days a patient will stay in the hospital, price of the house after 10 years etc. So Regression is the technique which enables you to determine difficult to measure variables with the help of easy to measure variables.
A database link is a pointer in the local database that lets you access objects on a remote database. To create a private database link, you must have been granted the proper privileges. The following table illustrates which privileges are required on which database for which type of link:
CREATE DATABASE LINK
Creation of a private database link.
CREATE PUBLIC DATABASE LINK
Creation of a public database link.
Creation of any type of database link.
To see which privileges you currently have available, query ROLE_SYS_PRIVS. For example, you could create and execute the following privs.sql script (sample output included):
SELECT DISTINCT PRIVILEGE AS "Database Link Privileges"
WHERE PRIVILEGE IN ( 'CREATE SESSION','CREATE DATABASE LINK',
'CREATE PUBLIC DATABASE LINK')
or just execute following query to see all the permissions for current user:
SELECT DISTINCT PRIVILEGE AS "Database Link Privileges" FROM ROLE_SYS_PRIVS
In a schedule, if update performed by transaction T1 on data item ‘X’ gets overwritten by the update performed by transaction T2 on same data item ‘X’, then we say that update of T1 is lost to the update of T2.
This problem is known as Lost-Update-Problem in concurrent schedules.
Transaction-processing systems usually allow multiple transactions to run concurrently. Allowing multiple transactions to update data concurrently causes several complications with consistency of the data.
Ensuring consistency in spite of concurrent execution of transactions requires extra work; it is far easier to insist that transactions run serially—that is, one at a time, each starting only after the previous one has completed.