Skip to main content

Table 2 Multivariate regression analysis of risk factors for abstract reporting quality

From: Assessment of the abstract reporting of systematic reviews of dose-response meta-analysis: a literature survey

Influence factors Estimated β (95% CI)
WLSLR P-value GEE P-value
No. of authors
  ≤ 4 Reference   Reference  
 5 ~  6 −0.28 (−0.57, 0.00) 0.054 −0.36 (− 0.65, − 0.06) 0.017
 7~ 8 − 0.11 (− 0.40, 0.18) 0.450 − 0.13 (− 0.40, 0.14) 0.350
  > 8 − 0.03 (− 0.39, 0.33) 0.890 −0.12 (− 0.49, 0.25) 0.516
Year of publication
 2011 Reference   Reference  
 2012 −0.30 (−0.76, 0.17) 0.211 −0.38 (− 0.84, 0.08) 0.105
 2013 −0.55 (−1.10, 0.00) 0.048 − 0.58 (−1.10, − 0.06) 0.028
 2014 −0.12 (−.061, 0.36) 0.616 − 0.14 (− 0.59, 0.31) 0.546
 2015 − 0.37 (− 0.89, 0.15) 0.166 −0.39 (− 0.85, 0.07) 0.100
 2016 −0.45 (− 0.97, 0.06) 0.084 −0.49 (− 0.96, − 0.02) 0.041
 2017 −0.93 (− 1.40, − 0.47) <  0.001 −0.97 (− 1.43, − 0.51) < 0.001
Region
 European Reference   Reference  
 Asia Pacific −0.08 (− 0.37, 0.22) 0.612 − 0.11 (− 0.38, 0.16) 0.412
 America − 0.07 (− 0.61, 0.46) 0.785 −0.03 (− 0.59, 0.53) 0.917
Funding
 No Reference   Reference  
 Yes −0.20 (−0.43, 0.02) 0.077 −0.30 (− 0.47, − 0.05) 0.015
Word count
  ≤ 250 Reference   Reference  
  > 250 0.31 (0.02, 0.61) 0.039 0.28 (0.03, 0.54) 0.027
  1. WLSLR weighted least square linear regression;
  2. GEE generalized estimating equation
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us

\