user avatar
user avatar
user avatar
einar
  • Member for 8 years, 2 months
  • Last seen this week
1248 votes
27 answers
832k views

Making sense of principal component analysis, eigenvectors & eigenvalues

  • 12.8k
532 votes
15 answers
222k views

What is the intuition behind beta distribution?

  • 9,460
529 votes
23 answers
284k views

Why square the difference instead of taking the absolute value in standard deviation?

  • 5,535
481 votes
20 answers
169k views

The Two Cultures: statistics vs. machine learning?

  • 12k
397 votes
11 answers
172k views

Explaining to laypeople why bootstrapping works

  • 4,939
390 votes
18 answers
155k views

What happens if the explanatory and response variables are sorted independently before regression?

385 votes
9 answers
756k views

What is the difference between fixed effect, random effect and mixed effect models?

  • 5,618
362 votes
12 answers
351k views

Difference between logit and probit models

  • 5,914
361 votes
16 answers
130k views

Is normality testing 'essentially useless'?

  • 10.4k
334 votes
8 answers
130k views

Why is Euclidean distance not a good metric in high dimensions?

  • 3,557
321 votes
13 answers
185k views

How to understand degrees of freedom?

  • 18k
311 votes
8 answers
265k views

What should I do when my neural network doesn't learn?

  • 79.6k
268 votes
10 answers
153k views

How would you explain covariance to someone who understands only the mean?

  • 13.7k
256 votes
3 answers
26k views

How to know that your machine learning problem is hopeless?

  • 115k
248 votes
46 answers
26k views

What are common statistical sins?

230 votes
8 answers
112k views

Algorithms for automatic model selection

  • 2,450
221 votes
13 answers
201k views

What is the difference between data mining, statistics, machine learning and AI?

217 votes
5 answers
86k views

Which "mean" to use and when?

  • 13.7k
201 votes
10 answers
103k views

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

  • 115k
197 votes
10 answers
210k views

How to deal with perfect separation in logistic regression?

  • 6,731
194 votes
5 answers
246k views

How exactly does one “control for other variables”?

  • 2,637
187 votes
9 answers
44k views

What intuitive explanation is there for the central limit theorem?

183 votes
4 answers
45k views

Why do we need sigma-algebras to define probability spaces?

171 votes
4 answers
152k views

Cohen's kappa in plain English

  • 7,861
164 votes
9 answers
188k views

When is it ok to remove the intercept in a linear regression model?

161 votes
9 answers
105k views

Bottom to top explanation of the Mahalanobis distance?

  • 5,257
160 votes
34 answers
31k views

The Sleeping Beauty Paradox

  • 291k
143 votes
8 answers
87k views

Why L1 norm for sparse models

  • 1,613
140 votes
5 answers
156k views

Batch gradient descent versus stochastic gradient descent

  • 1,441
137 votes
9 answers
156k views

Why does a time series have to be stationary?

  • 1,371
1
2 3 4 5
14