In an email, 4 features are extracted. Let n=10 data are observed from this email.
- What is your proposed model of data? (Hint: you are allowed to choose freely parameters of the model so that the conditions of the proposed model met.)
- What is the probability that we observe 2, 1, 4, 3 data respectively from feature one to five?
- What is the probability that we observe at least 4 data from the last feature?
- Compute the correlation between the first and second features?
- Generate 1000 samples from your proposed model in part (a).
- Find the sample correlation between the first and the second features.
- Compare the sample and model correlation between these two features.