BCA_SEM 4_QUIZ 3

1) What is the primary purpose of Principal Component Analysis (PCA)?

• To detect outliers

• To increase the dimensionality of data

• To detect outliers

• To reduce the dimensionality of data

2) What does PCA aim to achieve in terms of variance?

• To make variance uniform across components

• To minimize variance along the first few principal components

• To maximize variance along the first few principal components

• To reduce variance to zero

3) How can we determine how many principal components to retain?

• By calculating the mean of the eigenvectors

• By using the elbow method on a scree plot

• By selecting all principal components

• By looking at the eigenvalues and selecting components with eigenvalues greater than 1

4) In PCA, what does a scree plot help identify?

• The accuracy of the PCA model

• The correlation between components

• The eigenvalues of each feature

• The optimal number of principal components

5) Which of the following is true about the principal components in PCA?

• They are always the same as the original features

• They are uncorrelated with each other

• They are correlated with each other

• They are a subset of the original features

6) What does a high eigenvalue in PCA signify?

• The variable contributes little to the variance

• The variable is correlated with all others

• The variable contributes significantly to the variance

• The data is non-linear

7) What happens when you standardize the data before applying PCA?

• The data is centered around zero with unit variance

• The data is scaled to a fixed range

• The data is normalized

• The data becomes non-linear

8) What is the role of the covariance matrix in PCA?

• It helps in feature selection

• It scales the data

• It determines the correlation between the variables

• It calculates the eigenvectors

9) In PCA, the first principal component (PC1) captures:

• The minimum variance in the data

• The median value of the data

• The correlation between all variables

• The maximum variance in the data

10) After performing PCA, what does the transformation of data produce?

• New features that are linear combinations of the original features

• Discrete variables

• Features that are exactly the same as the original ones

• A correlation matrix of the original data