Skip to main content

Table 4 Estimates of 5-year RS and LLE for settings 1S, 2S and scenarios E, J. Point estimates (PE) of 5-year relative survival (RS) and loss in life expectancy (LLE), with lower (LCI) and upper (UCI) confidence intervals, standard errors (SE) and relative % precision (RP) from different methods, settings and scenarios for including uncertainty in the general population mortality when estimating SEs. Results are presented for men and women, aged 55, 65, 75 and 85 years at diagnosis, and in setting 2S, scenario J the LLE estimates are for the Stockholm region. For setting 1S general population mortality rates are stratified by age, sex and calendar year. For setting 2S general population mortality rates are stratified by age, sex, calendar year and region. RP illustrates comparison of the conventional method to a bootstrap-based method

From: Assessing the impact of including variation in general population mortality on standard errors of relative survival and loss in life expectancy

Method Setting / scenariob 5-year Relative Survival (RS) Loss in life expectancy (LLE)a,g
   PE SE LCI UCI RPc PE SE LCI UCI RP
men, 55 years at diagnosis
Conventionald 1Sf 0.639 0.102 0.406 0.801 0.00 11.28 3.08 5.24 17.31 0.00
Bootstrap-basede E 0.639 0.102 0.405 0.801 0.01 11.28 3.08 5.24 17.31 0.03
men, 65 years at diagnosis
Conventional 1S 0.670 0.072 0.507 0.790 0.00 7.47 1.50 4.53 10.41 0.00
Bootstrap-based E 0.670 0.072 0.507 0.790 0.00 7.47 1.50 4.53 10.41 0.06
men, 75 years at diagnosis
Conventional 1S 0.510 0.075 0.357 0.644 0.00 5.81 0.72 4.39 7.23 0.00
Bootstrap-based E 0.510 0.075 0.357 0.644 0.00 5.81 0.72 4.39 7.23 0.16
men, 85 years at diagnosis
Conventional 1S 0.619 0.100 0.394 0.781 0.00 1.74 0.44 0.88 2.60 0.00
Bootstrap-based E 0.619 0.101 0.394 0.781 0.03 1.74 0.44 0.88 2.60 0.18
women, 55 years at diagnosis
Conventional 1S 0.672 0.099 0.440 0.825 0.00 8.83 2.89 3.17 14.49 0.00
Bootstrap-based E 0.672 0.099 0.440 0.825 0.00 8.83 2.89 3.17 14.49 0.00
women, 65 years at diagnosis
Conventional 1S 0.701 0.060 0.566 0.801 0.00 6.49 1.47 3.61 9.37 0.00
Bootstrap-based E 0.701 0.060 0.566 0.801 0.00 6.49 1.47 3.61 9.37 0.04
women, 75 years at diagnosis
Conventional 1S 0.550 0.082 0.377 0.693 0.00 5.98 1.05 3.92 8.05 0.00
Bootstrap-based E 0.550 0.082 0.377 0.693 0.00 5.98 1.05 3.92 8.05 0.07
women, 85 years at diagnosis
Conventional 1S 0.653 0.082 0.470 0.787 0.00 1.89 0.46 0.98 2.80 0.00
Bootstrap-based E 0.653 0.082 0.470 0.787 0.03 1.89 0.46 0.98 2.80 0.11
men, 55 years at diagnosis
Conventionald 2Sf 0.637 0.103 0.404 0.800 0.00 11.49 3.12 5.38 17.60 0.00
Bootstrap-basede J 0.637 0.102 0.404 0.800 -0.01 11.49 3.12 5.38 17.61 0.05
men, 65 years at diagnosis
Conventional 2S 0.668 0.072 0.505 0.788 0.00 7.65 1.54 4.64 10.66 0.00
Bootstrap-based J 0.668 0.072 0.505 0.788 0.00 7.65 1.54 4.63 10.67 0.16
men, 75 years at diagnosis
Conventional 2S 0.509 0.074 0.356 0.643 0.00 6.03 0.75 4.56 7.51 0.00
Bootstrap-based J 0.509 0.074 0.356 0.643 0.00 6.03 0.76 4.55 7.51 0.62
men, 85 years at diagnosis
Conventional 2S 0.612 0.100 0.389 0.774 0.00 1.88 0.47 0.96 2.79 0.00
Bootstrap-based J 0.612 0.100 0.389 0.774 0.01 1.88 0.47 0.96 2.80 0.50
women, 55 years at diagnosis
Conventional 2S 0.673 0.098 0.443 0.825 0.00 8.93 2.94 3.17 14.69 0.00
Bootstrap-based J 0.673 0.098 0.443 0.825 -0.01 8.93 2.94 3.17 14.69 0.03
women, 65 years at diagnosis
Conventional 2S 0.702 0.060 0.567 0.802 0.00 6.59 1.50 3.64 9.54 0.00
Bootstrap-based J 0.702 0.060 0.567 0.802 0.00 6.59 1.50 3.65 9.54 0.06
women, 75 years at diagnosis
Conventional 2S 0.553 0.082 0.380 0.695 0.00 6.17 1.11 4.00 8.33 0.00
Bootstrap-based J 0.553 0.082 0.380 0.695 0.00 6.17 1.11 4.00 8.33 0.14
women, 85 years at diagnosis
Conventional 2S 0.649 0.081 0.467 0.783 0.00 2.03 0.50 1.05 3.01 0.00
Bootstrap-based J 0.649 0.081 0.467 0.783 0.00 2.03 0.50 1.05 3.01 0.20
  1. aLLE is presented in years
  2. bSee Table 1 for information on the different settings and scenarios
  3. cRP is presented in %
  4. dConventional refers to the standard method for estimating SEs, where the general population mortality is assumed to be measured without uncertainty
  5. eBootstrap-based refers to the parametric bootstrap approach used for including uncertainty in population mortality rates in the estimation of SEs
  6. fS stands for small and refers to the setting to investigate what would be observed for a smaller population
  7. gLLE estimates in setting 2S and scenario J are presented for the Stockholm region
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us