statistics
+ data
Nature Methods: Points of Significance
Generated on 27-Nov-2024 (419 days ago).
Metrics are provided by Altmetric.
Access values larger than 10,000 are rounded off to nearest 1,000 by Altmetric.
| article |
accesses |
daily |
%nm |
%all |
cit (ws) |
cit (cross) |
altmetric |
| Significance, P values and t-tests |
227,000 |
56 |
90
|
98
|
112 |
93 |
89 |
| Error bars |
223,000 |
55 |
98
|
99
|
186 |
179 |
272 |
| Visualizing samples with box plots |
205,000 |
52 |
86
|
98
|
390 |
371 |
77 |
| Principal component analysis |
203,000 |
75 |
87
|
96
|
513 |
867 |
87 |
| Association, correlation and causation |
187,000 |
56 |
98
|
99
|
215 |
179 |
187 |
| Replication |
135,000 |
36 |
57
|
93
|
127 |
94 |
24 |
| P values and the search for significance |
134,000 |
46 |
93
|
98
|
64 |
71 |
151 |
| Statistics versus machine learning |
130,000 |
53 |
97
|
99
|
224 |
888 |
348 |
| Importance of being uncertain |
121,000 |
29 |
79
|
96
|
63 |
55 |
51 |
| Power and sample size |
110,000 |
27 |
74
|
97
|
138 |
126 |
54 |
| Nonparametric tests |
66,000 |
17 |
53
|
87
|
60 |
54 |
12 |
| Comparing samples—part I |
64,000 |
16 |
67
|
92
|
29 |
33 |
20 |
| Analysis of variance and blocking |
62,000 |
16 |
60
|
91
|
51 |
49 |
18 |
| Nested designs |
61,000 |
16 |
86
|
96
|
44 |
38 |
55 |
| Bayes' theorem |
59,000 |
17 |
72
|
94
|
67 |
53 |
36 |
| Two-factor designs |
59,000 |
16 |
34
|
51
|
28 |
27 |
3 |
| The SEIRS model for infectious disease dynamics |
58,000 |
35 |
98
|
99
|
117 |
127 |
356 |
| Comparing samples—part II |
55,000 |
14 |
48
|
87
|
54 |
48 |
12 |
| Simple linear regression |
54,000 |
16 |
74
|
93
|
78 |
83 |
28 |
| Split plot design |
54,000 |
15 |
40
|
78
|
52 |
46 |
7 |
| Sources of variation |
54,000 |
15 |
53
|
91
|
19 |
18 |
16 |
| Bayesian statistics |
49,000 |
14 |
55
|
89
|
21 |
17 |
16 |
| Designing comparative experiments |
49,000 |
13 |
51
|
82
|
13 |
14 |
8 |
| Sampling distributions and the bootstrap |
48,000 |
14 |
54
|
91
|
84 |
77 |
18 |
| Interpreting P values |
47,000 |
17 |
74
|
95
|
50 |
53 |
57 |
| Multiple linear regression |
47,000 |
14 |
80
|
95
|
88 |
80 |
42 |
| Classification and regression trees |
45,000 |
17 |
45
|
79
|
194 |
219 |
9 |
| Classification evaluation |
40,000 |
13 |
70
|
94
|
227 |
208 |
44 |
| Model selection and overfitting |
39,000 |
13 |
66
|
92
|
392 |
347 |
26 |
| Bayesian networks |
38,000 |
11 |
45
|
77
|
38 |
26 |
7 |
| Clustering |
34,000 |
12 |
50
|
89
|
86 |
99 |
21 |
| Optimal experimental design |
28,000 |
12 |
49
|
89
|
58 |
67 |
20 |
| Analyzing outliers: influential or nuisance? |
27,000 |
9 |
28
|
65
|
61 |
56 |
4 |
| Machine learning: supervised methods |
23,000 |
9 |
56
|
91
|
173 |
203 |
22 |
| Logistic regression |
22,000 |
7 |
67
|
92
|
77 |
67 |
25 |
| Regression diagnostics |
22,000 |
7 |
46
|
72
|
53 |
48 |
6 |
| The curse(s) of dimensionality |
21,000 |
9 |
58
|
88
|
207 |
228 |
20 |
| Ensemble methods: bagging and random forests |
19,000 |
7 |
35
|
78
|
147 |
162 |
9 |
| Modeling infectious epidemics |
18,000 |
11 |
85
|
97
|
54 |
67 |
115 |
| Machine learning: a primer |
17,000 |
7 |
89
|
97
|
103 |
112 |
74 |
| Tabular data |
14,000 |
5 |
28
|
64
|
3 |
2 |
4 |
| Regularization |
13,000 |
4 |
53
|
86
|
34 |
27 |
14 |
| Two-level factorial experiments |
11,000 |
5 |
12
|
24
|
11 |
11 |
1 |
| Predicting with confidence and tolerance |
8,183 |
4 |
24
|
59
|
6 |
6 |
4 |
| Markov models—Markov chains |
7,993 |
4 |
41
|
90
|
18 |
19 |
24 |
| Markov models — hidden Markov models |
6,183 |
3 |
26
|
79
|
19 |
24 |
10 |
| The standardization fallacy |
5,278 |
4 |
47
|
92
|
30 |
32 |
28 |
| Convolutional neural networks |
5,268 |
11 |
15
|
69
|
17 |
20 |
5 |
| Quantile regression |
4,398 |
2 |
36
|
78
|
39 |
73 |
9 |
| Markov models — training and evaluation of hidden Markov models |
4,285 |
2 |
40
|
84
|
5 |
5 |
12 |
| The class imbalance problem |
4,267 |
4 |
20
|
73
|
42 |
51 |
7 |
| Survival analysis—time-to-event data and censoring |
3,974 |
5 |
17
|
68
|
12 |
11 |
4 |
| Uncertainty and the management of epidemics |
3,671 |
2 |
21
|
70
|
6 |
9 |
7 |
| Analyzing outliers: robust methods to the rescue |
3,665 |
2 |
25
|
50
|
20 |
18 |
3 |
| Neural networks primer |
3,210 |
5 |
16
|
67
|
4 |
5 |
4 |
| Graphical assessment of tests and classifiers |
2,245 |
2 |
26
|
82
|
8 |
6 |
11 |
| Regression modeling of time-to-event data with censoring |
2,052 |
3 |
12
|
71
|
4 |
5 |
5 |
| Comparing classifier performance with baselines |
1,701 |
7 |
28
|
76
|
0 |
0 |
7 |
| Testing for rare conditions |
1,553 |
1 |
15
|
60
|
3 |
3 |
4 |
| Errors in predictor variables |
1,345 |
4 |
3
|
30
|
1 |
1 |
1 |
| Propensity score matching |
1,102 |
15 |
16
|
57
|
0 |
0 |
2 |
|
3,062,373 |
988 |
52 |
82 |
5,039 |
5,977 |
%NM percentile rank (avg 52) for the article of tracked articles of a similar age in Nature Methods.
%ALL percentile rank (avg 82) for the article of tracked articles of a similar age in all journals.
Total accesses 3,062,373.
Total citations 6,281 = sum(maxi(webscience,crossref)).
news
+ thoughts
Wed 23-07-2025
What immortal hand or eye, could frame thy fearful symmetry? — William Blake, "The Tyger"
This month, we look at symmetric regression, which, unlike simple linear regression, it is reversible â remaining unaltered when the variables are swapped.
Simple linear regression can summarize the linear relationship between two variables `X` and `Y` â for example, when `Y` is considered the response (dependent) and `X` the predictor (independent) variable.
However, there are times when we are not interested (or able) to distinguish between dependent and independent variables â either because they have the same importance or the same role. This is where symmetric regression can help.
▲ Nature Methods Points of Significance column: Symmetric alternatives to the ordinary least squares regression. Geometry of quantities minimized in OLS and symmetric regression. OLS minimizes `\Sigma e_y^2` in `Y` ~ `X` and `\Sigma e_x^2` `X` ~ `Y`. Pythagorean regression minimizes AB (magenta). Geometric means regression (GMR) minimizes area of ABP (orange). Orthogonal regression (OR) minimizes HP (blue).
(
read)
Luca Greco, George Luta, Martin Krzywinski & Naomi Altman (2025) Points of significance: Symmetric alternatives to the ordinary least squares regression. Nat. Methods 22:1610–1612.
Wed 11-06-2025
Fuelled by philanthropy, findings into the workings of BRCA1 and BRCA2 genes have led to groundbreaking research and lifesaving innovations to care for families facing cancer.
This set of 100 one-of-a-kind prints explore the structure of these genes. Each artwork is unique — if you put them all together, you get the full sequence of the BRCA1 and BRCA2 proteins.
Mon 17-03-2025
The needs of the many outweigh the needs of the few. —Mr. Spock (Star Trek II)
This month, we explore a related and powerful technique to address bias: propensity score weighting (PSW), which applies weights to each subject instead of matching (or discarding) them.
▲ Nature Methods Points of Significance column: Propensity score weighting.
(
read)
Kurz, C.F., Krzywinski, M. & Altman, N. (2025) Points of significance: Propensity score weighting. Nat. Methods 22:638–640.
Thu 13-03-2025
Celebrate Ï Day (March 14th) and sequence digits like its 1999. Let's call some peaks.
▲ 2025 Ï DAY | TTCAGT: a sequence of digits. The digits of Ï are encoded into DNA sequence and visualized with Sanger sequencing.
(
details)
