Skip to main content

Table 5 Summary of regression coefficients and standard errors produced by the 625 models which incorporated a range of imputed operating experience data for the two patients who had missing data (see ‘Methods’ section)

From: Exploring and adjusting for potential learning effects in ROLARR: a randomised controlled trial comparing robotic-assisted vs. standard laparoscopic surgery for rectal cancer resection

Parameter

Original learning effects model parameter estimate

Median and range of parameter estimates from the 625 models of imputed data

Treatment effect: estimate

− 0.916

− 0.946 (− 0.964, − 0.908)

Treatment effect: standard error

0.441

0.441 (0.438, 0.443)

Laparoscopic experience: estimate

− 0.309

− 0.317 (− 0.338, − 0.205)

Laparoscopic experience: standard error

0.404

0.408 (0.349, 0.409)

Robotic experience: estimate

0.074

0.073 (− 0.080, 0.168)

Robotic experience: standard error

0.397

0.392 (0.382, 0.397)

Treatment × laparoscopic experience interaction: estimate

− 0.160

− 0.144 (− 0.226, − 0.135)

Treatment × laparoscopic experience interaction: standard error

1.014

1.012 (0.989, 1.015)

Treatment × robotic experience interaction: estimate

− 1.076

− 1.077 (− 1.149, − 0.970)

Treatment × robotic experience interaction: standard error

0.526

0.524 (0.518, 0.527)