High-Performance Open-Source Archive
For notation details, see (Bowers et al. 1997).
Using the well-known relation \({}_{s+u}p_y={}_up_{y+s} \times {}_sp_y\), we compute \({}_tp_{x}\) as for all \(x,t\in\mathbb R_+\) \[ {}_tp_{x} = \frac{{}_{t+\epsilon_x}p_{\lfloor x\rfloor} }{{}_{\epsilon_x}p_{\lfloor x\rfloor}} = \frac{{}_{\lfloor u\rfloor}p_{\lfloor x\rfloor} \times {}_{\epsilon_u}p_{\lfloor x\rfloor+\lfloor u\rfloor} }{{}_{\epsilon_x}p_{\lfloor x\rfloor}} \] with \(\epsilon_x=x - \lfloor x\rfloor\), \(u=t+\epsilon_x\) and \(\epsilon_u=u-\lfloor u\rfloor\).
Then we estimate \({}_np_{m}\) as for all \(n,m\in\mathbb N\) \[ {}_np_{m} = \frac{l_{n+m}}{l_m}. \]
We interpolate fractional age probabilities by three classical assumptions for all \(y \in [0,1), m\in\mathbb N\) \[ {}_{y}p_{m} = \left\{ \begin{array}{ll} 1 - y (1-p_{m}) & \text{if uniform distribution} \\ (p_{m})^y & \text{if constant force} \\ \frac{p_{m}}{1-(1-y)(1-p_{m})} & \text{if hyperbolic distribution} \\ \end{array} \right. \]
library(lifecontingencies)
data("soa08Act")
pXt <- Vectorize(lifecontingencies:::pxtold, "x")
pxT <- Vectorize(lifecontingencies:::pxtold, "t")
pxtvect <- pxt
z <- 1:6/3
#non integer time
cbind(t=z, pxtvect(soa08Act, x=100, t=z, fractional = "lin"), pxT(object=soa08Act, x=100, t=z, fractional = "lin"))
#> t
#> [1,] 0.3333333 0.8639604 0.8639604
#> [2,] 0.6666667 0.7279208 0.7279208
#> [3,] 1.0000000 0.5918812 0.5918812
#> [4,] 1.3333333 0.5056079 0.5056079
#> [5,] 1.6666667 0.4193345 0.4193345
#> [6,] 2.0000000 0.3330612 0.3330612
cbind(t=z, pxtvect(soa08Act, x=100, t=z, fractional = "hyp"), pxT(object=soa08Act, x=100, t=z, fractional = "hyp"))
#> t
#> [1,] 0.3333333 0.8131121 0.8131121
#> [2,] 0.6666667 0.6850791 0.6850791
#> [3,] 1.0000000 0.5918812 0.5918812
#> [4,] 1.3333333 0.4701083 0.4701083
#> [5,] 1.6666667 0.3898924 0.3898924
#> [6,] 2.0000000 0.3330612 0.3330612
cbind(t=z, pxtvect(soa08Act, x=100, t=z, fractional = "exp"), pxT(object=soa08Act, x=100, t=z, fractional = "exp"))
#> t
#> [1,] 0.3333333 0.8396111 0.8396111
#> [2,] 0.6666667 0.7049468 0.7049468
#> [3,] 1.0000000 0.5918812 0.5918812
#> [4,] 1.3333333 0.4886498 0.4886498
#> [5,] 1.6666667 0.4034232 0.4034232
#> [6,] 2.0000000 0.3330612 0.3330612x <- 50+0:6/6
#non-integer age
cbind(x=x, pxtvect(soa08Act, x=x, t=1, fractional = "lin"), pXt(object=soa08Act, x=x, t=1, fractional = "lin"))
#> x
#> [1,] 50.00000 0.9940801 0.9940801
#> [2,] 50.16667 0.9939968 0.9939968
#> [3,] 50.33333 0.9939134 0.9939134
#> [4,] 50.50000 0.9938298 0.9938298
#> [5,] 50.66667 0.9937460 0.9937460
#> [6,] 50.83333 0.9936620 0.9936620
#> [7,] 51.00000 0.9935779 0.9935779
cbind(x=x, pxtvect(soa08Act, x=x, t=1, fractional = "hyp"), pXt(object=soa08Act, x=x, t=1, fractional = "hyp"))
#> x
#> [1,] 50.00000 0.9940801 0.9940801
#> [2,] 50.16667 0.9939960 0.9939960
#> [3,] 50.33333 0.9939120 0.9939120
#> [4,] 50.50000 0.9938282 0.9938282
#> [5,] 50.66667 0.9937446 0.9937446
#> [6,] 50.83333 0.9936612 0.9936612
#> [7,] 51.00000 0.9935779 0.9935779
cbind(x=x, pxtvect(soa08Act, x=x, t=1, fractional = "exp"), pXt(object=soa08Act, x=x, t=1, fractional = "exp"))
#> x
#> [1,] 50.00000 0.9940801 0.9940801
#> [2,] 50.16667 0.9939964 0.9939964
#> [3,] 50.33333 0.9939127 0.9939127
#> [4,] 50.50000 0.9938290 0.9938290
#> [5,] 50.66667 0.9937453 0.9937453
#> [6,] 50.83333 0.9936616 0.9936616
#> [7,] 51.00000 0.9935779 0.9935779x <- 135:145
#high-age
cbind(x=x, pxtvect(soa08Act, x=x, t=1), pXt(object=soa08Act, x=x, t=1))
#> x
#> [1,] 135 1.932519e-06 1.932519e-06
#> [2,] 136 5.431077e-07 5.431077e-07
#> [3,] 137 1.350422e-07 1.350422e-07
#> [4,] 138 2.935883e-08 2.935883e-08
#> [5,] 139 5.508989e-09 5.508989e-09
#> [6,] 140 0.000000e+00 0.000000e+00
#> [7,] 141 0.000000e+00 0.000000e+00
#> [8,] 142 0.000000e+00 0.000000e+00
#> [9,] 143 0.000000e+00 0.000000e+00
#> [10,] 144 0.000000e+00 0.000000e+00
#> [11,] 145 0.000000e+00 0.000000e+00
Need mirroring services?
Contact our team at info@vpspulse.com.
Mirror powered by VPSpulse
Infrastructure sponsored by VPSPulse & Secure Payments by ArionPay.