Hypothesis Testing

Question 1

• Label purpose

Answer 1

• Signpost to tell us which data is distinct

Question 2

• Binary vs categorical vs continuous labels, give examples

Answer 2

• Binary – 0s and 1s (Yea/Nah)
• Categorical – distinct labels of types (colours)
• Continuous – range of values (temperature)

Question 3

• Consequence of bad or incorrect labelling

Answer 3

Misleading, biased outputs, ethical issues

Question 4

• If a particular label occurs rarely, how does that affect what can be learned or inferred?

Answer 4

Rare labels can lead to class imbalance, reduced model performance, overfitting, limited insights, and training challenges.

Question 5

• Purpose of hypothesis test

Answer 5

• Helps us make decisions about how we should work with data

Question 6

• How hypothesis testing be useful in a brute force approach assessing patterns in data?

Answer 6

• Hypothesis testing helps us determine which pattern or feature is best.

Question 7

• Risks of running many hypothesis tests?

Answer 7

• P-hacking

Question 8

• Two types of errors and how they inhibit data analysis?

Answer 8

-Type 1 - mistaken significance
-Type 2 - Missed significance