Skip to main content

Table 2 Comparison of the mean absolute error and mean % absolute error using the Parmar method and nlopt method (exact and non-exact P value) described in this study

From: A non-linear optimisation method to extract summary statistics from Kaplan-Meier survival plots using the published P value

Method

Mean Absolute Error (95% CIs)

Mean % Absolute Error (95% CIs)

Ln (HR)

Var ln (HR)

Ln (HR)

Var ln (HR)

1. Nlopt method: exact P value

0.014 (0.007–0.022)

0.0039 (0.0022–0.0056)

6.63% (2.69–10.57%)

20.12% (5.51–34.73%)

2. Nlopt method: non-exact P value

0.087 (−0.036–0.210)

0.0033 (0.0010–0.0055)

27.37% (8.69–46.05%)

17.30% (3.68–30.91%)

3. Parmar

0.077 (0.039–0.115)

0.0038 (0.0016–0.0060)

43.47% (11.18–75.77%)

20.06% (6.50–33.62%)

  1. The nlopt method using a exact and non-exact P value were compared with the Parmar method using a validation dataset of 13 KM plots. The mean absolute error and mean % absolute error for ln (HR) and var. ln (HR) were calculated for each method