user avatar
user avatar
user avatar
user3303
  • Member for 10 years, 6 months
  • Last seen more than 1 year ago
481 votes
20 answers
170k views

The Two Cultures: statistics vs. machine learning?

  • 12k
391 votes
18 answers
156k views

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

274 votes
6 answers
42k views

Is $R^2$ useful or dangerous?

  • 9,330
223 votes
4 answers
418k views

How to interpret a QQ plot

  • 18.7k
198 votes
7 answers
178k views

PCA on correlation or covariance?

  • 2,160
132 votes
2 answers
74k views

Removal of statistically significant intercept term increases $R^2$ in linear model

  • 2,132
128 votes
10 answers
71k views

Bias and variance in leave-one-out vs K-fold cross validation

116 votes
10 answers
7k views

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

  • 117k
110 votes
12 answers
56k views

When should linear regression be called "machine learning"?

  • 1,429
98 votes
7 answers
19k views

The Book of Why by Judea Pearl: Why is he bashing statistics?

  • 7,129
94 votes
2 answers
43k views

When to use regularization methods for regression?

  • 5,391
90 votes
2 answers
47k views

Resampling / simulation methods: monte carlo, bootstrapping, jackknifing, cross-validation, randomization tests, and permutation tests

  • 2,266
77 votes
3 answers
140k views

How to use Pearson correlation correctly with time series

  • 1,077
75 votes
5 answers
175k views

Covariance and independence?

  • 5,869
69 votes
6 answers
7k views

Criticism of Pearl's theory of causality

  • 13.9k
65 votes
6 answers
9k views

Is ridge regression useless in high dimensions ($n \ll p$)? How can OLS fail to overfit?

  • 95.8k
62 votes
5 answers
221k views

Correlations between continuous and categorical (nominal) variables

60 votes
5 answers
67k views

Best practice when analysing pre-post treatment-control designs

59 votes
3 answers
6k views

Statistics and causal inference?

  • 12k
56 votes
5 answers
30k views

Statistical inference when the sample "is" the population

  • 1,181
56 votes
2 answers
36k views

Prediction interval for lmer() mixed effects model in R

  • 827
47 votes
3 answers
122k views

What is the relationship between the mean squared error and the residual sum of squares function?

  • 3,588
44 votes
3 answers
7k views

Variance of $K$-fold cross-validation estimates as $f(K)$: what is the role of "stability"?

43 votes
2 answers
8k views

If only prediction is of interest, why use lasso over ridge?

43 votes
10 answers
15k views

How to efficiently generate random positive-semidefinite correlation matrices?

  • 2,279
42 votes
3 answers
15k views

What is the rationale of the Matérn covariance function?

42 votes
5 answers
35k views

K-fold vs. Monte Carlo cross-validation

  • 563
42 votes
1 answer
56k views

What is the intuitive reason behind doing rotations in Factor Analysis/PCA & how to select appropriate rotation?

41 votes
4 answers
17k views

When is the bootstrap estimate of bias valid?

40 votes
3 answers
6k views

Does statistical independence mean lack of causation?

1
2 3 4 5
7