Tim's user avatar
Tim's user avatar
Tim's user avatar
Tim
Moderator
  • Member for 8 years, 10 months
  • Last seen this week
  • Warsaw, Poland
266 votes
3 answers
26k views

How to know that your machine learning problem is hopeless?

208 votes
10 answers
108k views

Why is accuracy not the best measure for assessing classification models?

116 votes
10 answers
7k views

ASA discusses limitations of $p$-values - what are the alternatives?

95 votes
8 answers
32k views

When is unbalanced data really a problem in Machine Learning?

58 votes
10 answers
9k views

Who are frequentists?

50 votes
6 answers
57k views

Best method for short time-series

33 votes
5 answers
8k views

What do confidence intervals say about precision (if anything)?

22 votes
3 answers
1k views

Why is there -1 in beta distribution density function?

21 votes
1 answer
3k views

How to sample from Cantor distribution?

20 votes
3 answers
1k views

Algorithm for sampling fixed number of samples from a finite population

15 votes
1 answer
1k views

Why don't we use non-constant learning rates for gradient decent for things other then neural networks?

15 votes
1 answer
9k views

Is there a multivariate two-sample Kolmogorov–Smirnov test?

13 votes
3 answers
2k views

Is is true that Bayesians don't need test sets?

12 votes
2 answers
702 views

Why does entropy as error measure leads to overfitting?

12 votes
0 answers
607 views

Help me understand the Bayesian kernel density estimation (Sibisi and Skilling, 1996)

12 votes
6 answers
2k views

Does there exist any univariate distribution that we can't sample from?

12 votes
1 answer
1k views

Calculating confidence intervals for mode?

9 votes
2 answers
3k views

Beta as distribution of proportions (or as continuous Binomial)

9 votes
1 answer
1k views

When do improper linear models get robustly beautiful?

9 votes
2 answers
2k views

What happens when merging random variables in Dirichlet distribution?

8 votes
1 answer
1k views

Does there exist zero-inflated linear regression?

8 votes
1 answer
269 views

Detecting changes in large number of time-series that share seasonality

8 votes
1 answer
615 views

Can cosine kernel be understood as a case of Beta distribution?

7 votes
1 answer
167 views

Approximate Metropolis algorithm - does it make sense?

7 votes
2 answers
9k views

Number of samples needed in Monte Carlo simulation: how good is this approximation?

7 votes
2 answers
2k views

Analysing the residuals themselves

7 votes
3 answers
1k views

What makes constant function an estimator?

7 votes
2 answers
1k views

Judging flatness of time-series

6 votes
2 answers
637 views

Efficient random generation from truncated Laplace distribution

6 votes
2 answers
140 views

Test if function "raises faster then linear"