Statistical Concepts and Theorems

The video, hosted by Krishna, covers common statistics interview questions relevant to data science, machine learning, and deep learning. It discusses key topics such as probability mass and density functions, covariance vs. correlation, various distributions, central limit theorem, and hypothesis testing. The video also provides resources for further learning, including playlists and recommended YouTube channels.

Why is statistics important in data science interviews?

• It helps in understanding data better.

• It is not relevant at all.

• It is only important for software engineering roles.

• It is only used in marketing.

What is the main difference between a probability mass function and a probability density function?

• Both are used for discrete data.

• Both are used for continuous data.

• One is used for continuous data, the other for discrete data.

• There is no difference.

How can histograms be related to probability density functions?

• They are unrelated.

• Probability density functions are a type of histogram.

• Histograms can approximate probability density functions.

• Histograms are only used for categorical data.

What is the key difference between covariance and correlation?

• Neither is normalized.

• Covariance is normalized, correlation is not.

• Correlation is normalized, covariance is not.

• Both are normalized.

Which of the following is not a type of distribution discussed?

• Normal distribution

• Standard distribution

• Log-normal distribution

• Exponential distribution

What does the central limit theorem state?

• The mode of a large number of independent random variables will be normally distributed.

• The median of a large number of independent random variables will be normally distributed.

• The sum of a small number of independent random variables will be normally distributed.

• The mean of a large number of independent random variables will be normally distributed.

How does a power law distribution differ from a normal distribution?

• It has a bell curve shape.

• It has a different shape and does not follow a bell curve.

• It is always skewed to the right.

• It is always symmetrical.

What is an example of a non-Gaussian distribution?

• Standard normal distribution

• Log-normal distribution

• Normal distribution

• Uniform distribution

Why are correlation coefficients important?

• They are only used in data visualization.

• They are only used in hypothesis testing.

• They help in feature selection.

• They are not important.

What is a null hypothesis?

• A hypothesis that there is no effect or difference.

• A hypothesis that is always false.

• A hypothesis that there is a significant effect or difference.

• A hypothesis that is always true.