Skip to main content
Matthew Drury's user avatar
Matthew Drury's user avatar
Matthew Drury's user avatar
Matthew Drury
  • Member for 9 years, 1 month
  • Last seen this week
74 votes

If 900 out of 1000 people say a car is blue, what is the probability that it is blue?

70 votes
Accepted

Why use regularisation in polynomial regression instead of lowering the degree?

68 votes
Accepted

Relative variable importance for Boosting

62 votes
Accepted

Least Squares Regression Step-By-Step Linear Algebra Computation

55 votes
Accepted

How to apply standardization/normalization to train- and testset if prediction is the goal?

53 votes
Accepted

What is the difference between decision_function, predict_proba, and predict function for logistic regression problem?

51 votes
Accepted

Gradient Boosting for Linear Regression - why does it not work?

50 votes
Accepted

One-hot vs dummy encoding in Scikit-learn

49 votes
Accepted

What to conclude from this lasso plot (glmnet)

43 votes
Accepted

Understanding complete separation for logistic regression

42 votes
Accepted

Is a model fitted to data or is data fitted to a model?

32 votes
Accepted

What does log-uniformly distribution mean?

31 votes
Accepted

Why does this regression NOT fail due to perfect multicollinearity, although one variable is a linear combination of others?

30 votes

Cost function in OLS linear regression

30 votes
Accepted

Does this discrete distribution have a name?

28 votes
Accepted

Classification with Gradient Boosting : How to keep the prediction in [0,1]

26 votes

Are two standard normal random variables always independent?

25 votes
Accepted

Question about bias-variance tradeoff

24 votes
Accepted

Why are symmetric positive definite (SPD) matrices so important?

23 votes

What areas of mathematical statistics are highly employable?

23 votes
Accepted

What is use of Tweedie or poisson loss/objective function in XGboost and Deep learning models

21 votes
Accepted

Why feature scaling only to training set?

21 votes
Accepted

Why does logistic regression produce well-calibrated models?

21 votes
Accepted

Why linear and logistic regression coefficients cannot be estimated using same method?

20 votes

Should parsimony really still be the gold standard?

20 votes
Accepted

Scikit Binomial Deviance Loss Function

20 votes

Expected prediction error - derivation

20 votes

Is this the solution to the p-value problem?

20 votes
Accepted

Why does Central Limit Theorem break down in my simulation?

19 votes

When should we discretize/bin continuous independent variables/features and when should not?

1
2 3 4 5
15