Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 5 The median and IQR for the differences in between-study variance estimates for the meta-analytic immediate level-change (top triangle, difference calculated as column method – row method) and slope-change per month (bottom triangle, difference calculated as row method – column method) (n = 17)

From: Comparison of statistical methods used to meta-analyse results from interrupted time series studies: an empirical study

 

Level-change

Slope-change per month

OLS ITS

DL MA

0.00 (0.00,0.38)

0.00 (-0.28,0.00)

0.08 (0.00,0.83)

0.00 (0.00,0.00)

OLS ITS

REML MA

0.00 (-0.29,0.00)

0.00 (-0.29,0.08)

0.00 (0.00,0.01)

0.00 (-0.01,0.00)

REML ITS

DL MA

0.00 (0.00,0.08)

0.00 (0.00,0.03)

0.00 (0.00,0.02)

0.00 (0.00,0.00)

REML ITS

REML MA

  1. The top row of the label indicates the ITS analysis methods, bottom row indicates the meta-analysis method, e.g., OLS Fixed is OLS ITS analysis and fixed effect meta-analysis. For example, the median between-study variance for immediate level-change yielded by REML ITS analysis with REML estimator 0.08 higher than that yielded by OLS ITS analysis with DL estimator (column 4, row 1)
  2. DL DerSimonian and Laird, HKSJ Hartung-Knapp/Sidik-Jonkman, ITS interrupted time series, IQR interquartile range, MA meta-analysis, OLS ordinary least squares, REML restricted maximum likelihood, WT Wald-type
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us