Type 1 Error in Hypothesis Testing

Type 1 error occurs when 'we declare an innocent as guilty'.

By default, null hypothesis supports a homogeneous distribution and a no effect property. To reject a null hypothesis, requires a fair amount of certainty.

If a null hypothesis is actually true, but our result shows otherwise i.e. we reject the null hypothesis, that leads to committing a Type 1 error.

The impact of this error depends on the cost associated with committing one. For example, suppose I am shopping from a store which has only good apples, I believe that a particular apple is bad and hence I replace it from my bag. Here I have committed a Type-1 error but it's not going to cost me since the replacement apple too, is good. Here, the type 1 error is not harmful at all.

On the other hand, this error would have been too costly, if the lot has many bad apples and we remove a good apple from our bag thinking it to be bad.

Comments

Post a Comment

Popular posts from this blog

Analysis of Variance (ANOVA)

ANOVA technique deals with ascertaining differences in groups within a population. The dependent variable is continuous and the independent variable is categorical. Assumptions - Data is normally distributed Population and groups variance is homogenenous and have similar variance Samples are random and independent It uses the F-value statistic. It is the ratio of 'variance among groups'/'variance within group'. Higher F-value leads to rejection of null hypothesis. The null hypothesis states that there is no difference between groups. The alternate hypothesis states that at least one group is different. One-way ANOVA: 1 continuous dependent; 1 categorical independent (> 2 levels) (* Special case - t-test: 1 continuous dependent; 1 categorical independent (2 levels)) Two-way ANOVA: 1 continuous dependent; 2 or more categorical independent Python Implementation: scipy.stats, statsmodels
Read more

SMOTE for oversampling minority class in an Imbalanced Dataset

SMOTE stands for Synthetic Minority Oversampling Technique. It uses k-nearest neighbors of the minority class to create a synthetic row for the class. We can specify how much data to synthesize by mentioning the ratio to the majority class. We can also specify which classes to resample - majority, minority, not majority, not minority, all classes. There are other variants of SMOTE in which minority class is synthesized using SVM algorithm or KMeans clustering. Python Implementation : pip install imbalanced-learn ; from imblearn.over_sampling import SMOTE ; <SMOTE object>.fit_resample(X,Y)
Read more

Precision, Recall and Accuracy for Classification models

Image
The accuracy of a classification model is judged by whether the predicted class is the same as the actual class. Let us assume the levels of a class as either positive or negative, then - For all predicted positives, they can be either true (right) or false (wrong). For all predicted negatives, they can be either true (right) or false (wrong). Precision is a ratio defined as (True Positives)/(Predicted Positives). Ideally 1. Recall is a ratio defined as (True Positives)/(Actual Positives). It is also called Sensitivity or True Positive Rate (TPR). Ideally 1. Specificity is a ratio defined as (True Negatives)/(Actual Negatives). It is also called Selectivity. Ideally 1. Accuracy is a ratio defined as (True Positives + True Negatives)/(Total Predictions). Ideally 1. Python Implementation: sklearn.metrics -> classification_report
Read more