Top-down disaggregation of a hierarchical forecast

$$\tilde{y}_j = p_j\hat{y}$$ Hyndman & Athanasopoulos, FPP 3rd ed., Sec. 11.3. The proportions are closed to sum 1 so the parts add back to the total; the raw sum is reported so a caller who supplied unnormalised proportions sees it.

Usage

Topdown(top, props)

Arguments

top

Forecast of the Total series.

props

Non-negative disaggregation proportions.

Value

Named list with estimate, props, prop_sum, total, n, method.

References

Hyndman & Athanasopoulos, FPP3, Sec. 11.3.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
Topdown(V, V)
#> $estimate
#> [1] 0.02777778 0.11111111 0.25000000 0.44444444 0.69444444 1.00000000 1.36111111
#> [8] 1.77777778
#> 
#> $props
#> [1] 0.02777778 0.05555556 0.08333333 0.11111111 0.13888889 0.16666667 0.19444444
#> [8] 0.22222222
#> 
#> $prop_sum
#> [1] 36
#> 
#> $total
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $n
#> [1] 8
#> 
#> $method
#> [1] "Top-down disaggregation p_j yhat -- Hyndman & Athanasopoulos, FPP3 Sec. 11.3"
#>