Linear Regression & Naïve Bayes
6 important questions on Linear Regression & Naïve Bayes
What are the objectives for single/multiple regression?
1. Predictive: Detect the outcome value for new records, given their input values
a. Given a new value for X, estimate the value for Y
2. Explanatory or descriptive: Quantifying / explaining the average effect of inputs on an outcome. Data are treated as a random sample from a larger population of interest.
a. Generate statements useful for decision making
What are possible issues with regression?
the model learns the existing data too well.
2. Underfitting: Model can’t accurately capture the data dependencies, Fails to identify effects
supported by the data, Usually this happens due to the model’s simplicity.
What is the consequence of overfitting?
predictions.
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
What is the consequence of underfitting?
data
What are the negative aspects of Naïve Bayes?
- Requires a very large number of records to obtain good results
- Independence assumption may not hold for some attributes
What are the advantages of Naïve Bayes?
- It has a probabilistic interpretation
- It is able to deal with a small training set
- It is able to deal with missing values
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding