Build an ensemble from a reporting triangle with no nowcast

Returns the counts reported so far as an ensemble with one draw. Use it for an indicator that SHOULD NOT be nowcast.

Usage

nowcast_passthrough_v4(x, max_delay_days, denominator_col = NULL)

Arguments

x

The csfmt_reporting_triangle_v4 to pass through.

max_delay_days

The delay horizon in days. The totals do not depend on it.

denominator_col

A denominator column to pass through in the same way. Its total also goes to $data as <denominator_col>_observed.

Value

A csfmt_ensemble_v4 with one draw per measure. $data holds original, the observed total.

Details

The method is that of nowcast_passthrough_to_ensemble_v1(), and the draws are identical. The draw matrix has the name of value_col, with no suffix. It holds the observed total, which includes the reports at delay max_delay_days or later. The function draws no random numbers.

See also

Other v4 functions: as_ensemble_v4(), csfmt_ensemble_v4(), csfmt_reporting_triangle_v4(), ens_add_rate_v4(), ens_compress_v4(), mem_thresholds_v4(), nowcast_ecdf_v4(), print.csfmt_ensemble_v4(), short_term_trend_v4(), signal_detection_hlm_v4()

Examples

monday <- as.Date("2023-01-02") + 7 * rep(0:39, each = 3)
set.seed(1)
d <- data.table::data.table(
  isoyearweek_reference = format(monday, "%G-%V"),
  reporting_date = monday + rep(c(3, 10, 17), 40),
  numerator = rpois(120, c(30, 15, 5)),
  indicator_tag = "x", location_code = "nation", age = "total", sex = "total"
)
d <- d[reporting_date <= as.Date("2023-01-02") + 7 * 39 + 6]
tri <- csfmt_reporting_triangle_v4(
  d,
  id_cols = c("indicator_tag", "location_code", "age", "sex")
)
nowcast_passthrough_v4(tri, max_delay_days = 21)