Acurácia
- Created by
- Renato Passos, Eng. de Software
- Reviewed by
- Renato Passos, Eng. de Software
Last updated: Apr 18, 2026
About this calculator
Accuracy is an important measure in statistics to evaluate the accuracy of a classification model. It is calculated by dividing the number of correctly classified cases (TP - True Positive and TN - True Negative) by the total number of cases.
The formula to calculate accuracy is simple: (TP+TN)/total. This means you need to count the number of true positive cases, the number of true negative cases and sum them to get the numerator.
To get the accuracy, you should consider the cases where the model classified correctly, not the cases where the model made a mistake. Additionally, you should be careful with the presence of imbalanced cases in the sample data.
Accuracy is an important measure to evaluate the accuracy of the classification model, but it is only one of the measures used. Other measures, such as precision, sensitivity and specificity, should also be considered for a complete evaluation of the model.
Frequently asked questions
What is accuracy in statistics?
Accuracy is a precision measure of a classification model. It is calculated by dividing the number of correctly classified cases by the total number of cases.
How do I calculate accuracy?
The formula to calculate accuracy is simple: (TP+TN)/total. To get the accuracy, you need to count the number of true positive cases, the number of true negative cases and sum them to get the numerator.
Why is accuracy important in statistics?
Accuracy is important to evaluate the precision of a classification model. This is especially useful when you're working with classification models in areas like medicine, finance and marketing.
What is an imbalanced case?
An imbalanced case is a case where the model classified incorrectly. This can occur when the sample data is imbalanced, or when the model is not able to capture the complexity of the problem.
Why is accuracy not the only important measure?
Accuracy is not the only measure important in statistics. Other measures, like precision, sensitivity and specificity, should also be considered for a complete evaluation of the model.