IBM Data Science Practice Test

To predict salary based on education level, which model is best suited?

1. Logistical regression

2. Linear regression

3. Sigmoid operation

4. Classification

The correct answer is: Linear regression

The best model for predicting salary based on education level is linear regression because the goal is to establish a relationship between a continuous dependent variable (salary) and an independent variable (education level). Linear regression is specifically designed for regression tasks, where the outcome is a continuous variable. It captures the linear relationship between the variables by fitting a line that best describes how the salary changes with variations in education level. In this context, education level can often be treated as a numerical value or ordinal variable (for example, levels such as high school, bachelor's, master's, etc.), allowing for a direct mapping to a specific salary. Linear regression provides an interpretable model where coefficients represent the expected change in salary for a one-unit change in education level. Other options, such as logistical regression and classification, are more suited for scenarios where the outcome is categorical rather than continuous. A sigmoid operation is a mathematical function that is often utilized within logistic regression but does not serve as a standalone model for prediction. Therefore, linear regression is the most appropriate choice for this context.