Exam AWS Certified Machine Learning - Specialty topic 1 question 106 discussion

I would say B. Logarithmic transformation converts skewed distributions towards normal

I would go with B. For right skewed distributions -> Logrithmic transformation For left skewed distributions -> exponential transformations=

The linear regression model assumes that the errors are normally distributed. The plot of the feature shows that the errors are not normally distributed. The logarithmic transformation can be used to transform the errors to be normally distributed. The exponential transformation, polynomial transformation, and sinusoidal transformation cannot be used to transform the errors to be normally distributed.

B when the feature data is not normally distributed, applying a logarithmic transformation can help to normalize the data and satisfy the assumptions of the linear regression model.

'A' would make it considerably worse.

Log Normal Distribution => Log() => Normal Distribution

B is correct answer

This is B, as this feature seems skewed while others have a regular distribution according to the question. The log transformation will reduce this features skewness.

I think it's B. reference: https://corporatefinanceinstitute.com/resources/knowledge/other/positively-skewed-distribution/#:~:text=For%20positively%20skewed%20distributions%2C%20the,each%20value%20in%20the%20dataset. "For positively skewed distributions, the most popular transformation is the log transformation. The log transformation implies the calculations of the natural logarithm for each value in the dataset. The method reduces the skew of a distribution. Statistical tests are usually run only when the transformation of the data is complete."

I would also go for B, as Log transformation is often mentioned, when we are talking about right (positive) skewness.