Data Mining-Statistical Measures

What does Maximum Likelihood Estimation (MLE) aim to do?

• Minimize variance
  

• Maximize the likelihood of the observed data

• Reduce redundancy

• Eliminate missing values

In linear regression, the goal is to:

• Cluster data

• Find hidden patterns

• Predict a continuous output

• Classify text

What does a node in a decision tree represent?

• A database table

• An outcome

• An attribute test

• A regression line

MSE is used to measure:

• The correlation between variables

• The average squared difference between predicted and actual values

• The percentage accuracy of classification

• The entropy of a dataset

What does a leaf node in a decision tree represent?

• A test

• An attribute

• A final class label or prediction

• The root

What is the main goal of the Expectation-Maximization (EM) algorithm?

• To minimize classification error

• To find maximum likelihood estimates

• To reduce the number of features

• To perform dimensionality reduction

What happens during the Expectation (E-step) of the EM algorithm?

• Parameters are updated

• The likelihood function is minimized

• Missing data is predicted using current parameter estimates

• Features are selected

What happens during the Maximization (M-step) of the EM algorithm?

• Missing values are filled

• Posterior probabilities are computed

• Parameters are re-estimated to maximize the likelihood

• Distance between clusters is minimized

What does a negative regression coefficient mean?

• The dependent variable decreases as the independent variable increases

• The variables are not related

• There is no change

• It’s a mistake

Metric used to measure the strength and direction of the linear relationship between two variables

• Mean Square Error

• Correlation

• Residual Sum of Squares

• T-test