Table 7 |
||||
|
Estimation and statistical testing by analysis typea. |
||||
|
Analysis type |
||||
|
|
||||
|
Continuous (n = 8) |
Categorical (n = 29) |
Both (n = 21) |
Overall (n = 58) |
|
|
Type of estimate - n |
||||
|
Continuous |
7 |
0 |
16 |
23 (40%) |
|
By group for all groups |
0 |
4 |
6 |
10 (17%) |
|
By group relative to ref group |
0 |
26 |
12 |
38 (66%) |
|
Other |
1b |
1c |
3d |
5 (9%) |
|
Type of statistical test - n |
||||
|
Continuous |
8 |
0 |
19 |
27 (47%) |
|
Score trend test |
0 |
11 |
1 |
12 (21%) |
|
Median/mean trend |
0 |
7 |
1 |
8 (14%) |
|
Pairwise |
0 |
17 |
9 |
26 (45%) |
|
Global |
0 |
3 |
6 |
9 (16%) |
|
Other |
0 |
0 |
1e |
1 (2%) |
|
|
||||
|
For the 58 articles with a continuous risk factor. a More than one estimate type and more than one statistical test is possible: 40 (69%) articles had one type of estimate (8 from 'continuous', 27 from 'categorical' and 5 from 'both') whilst 18 (31%) articles had two types of estimate (2 from 'categorical' and 16 from 'both'); 35 (60%) articles had one type of statistical test (8 from 'continuous', 20 from 'categorical' and 7 from 'both'); 21 (36%) articles had two types of statistical test (9 from 'categorical' and 12 from 'both') and 2 (3%) articles (from 'both') had three types of statistical test. b A continuous analysis estimate given as difference between 90th and 10th percentile. c Reference group is the background population overall i.e. standardised incidence. d One article gave hazard ratios per one category increase, another article compared 1st and 4th quartiles only, the final article reported the mean by categories. e A t-test comparing means in two outcome groups. |
||||
|
Turner et al. Epidemiologic Perspectives & Innovations 2010 7:9 doi:10.1186/1742-5573-7-9 |
||||
