Skip to contents

Calculate survey confidence intervals by zone group and region

calc_survey_ci.Rd

Calculates confidence intervals for survey data by zone group and region, joining weights and crosswalks, and summarizing by group. Use for reporting survey fit and uncertainty.

Usage

calc_survey_ci(
  seed,
  weights,
  zone_group_crosswalk,
  puma_client_zone_xwalk,
  ci_level = 0.9,
  run_label,
  settings
)

Arguments

seed

data.table with required columns:

  • hh_id_dow — household-day ID

  • segment_name Rows: one per household-day. Keys: (hh_id_dow). Modified by reference: no (returns copy).

weights

data.table with required columns:

  • hh_id_dow

  • zone_group_balanced_weight Rows: one per household-day. Keys: (hh_id_dow). Modified by reference: no (returns copy).

zone_group_crosswalk

data.table. Zone group crosswalk.

puma_client_zone_xwalk

data.table. PUMA to client zone crosswalk.

ci_level

numeric(1). Confidence interval level (e.g., 0.9).

run_label

character(1). Run label for output files.

settings

list. Must include:

  • outputs_dir — output directory

  • seed_wtd_path — seed weighted path

Value

list with two data.tables:

  • zone_group: survey confidence intervals by zone group. Columns:

    • variable — variable name

    • day_group — day group label

    • mean — mean value

    • lower — lower confidence bound

    • upper — upper confidence bound

    • Additional columns as needed for reporting

  • region: survey confidence intervals by region. Columns:

    • variable — variable name

    • day_group — day group label

    • mean — mean value

    • lower — lower confidence bound

    • upper — upper confidence bound

    • Additional columns as needed for reporting

Details

  • Checks if outputs are up-to-date; re-runs if needed.

  • Joins weights to seed and adds zone group via crosswalks.

  • Summarizes survey data by zone group and region using helper functions.

  • Drops transit boardings for region summary.

  • Returns a list of data.tables for zone group and region.

Settings

  • outputs_dir (direct): Output directory. Default from settings.

  • seed_wtd_path (direct): Seed weighted path. Default from settings.

See also

  • summarize_survey

  • scripts/weighting/survey_fit.R

Other survey analysis: calc_max_error(), calc_weight_fit()

Examples

## Not run:
seed <- data.table(hh_id_dow = "H1", segment_name = "A")
weights <- data.table(hh_id_dow = "H1", zone_group_balanced_weight = 1.2)
zone_group_crosswalk <- data.table()
puma_client_zone_xwalk <- data.table()
ci_level <- 0.9
run_label <- "test"
settings <- list(outputs_dir = "out", seed_wtd_path = "seed.rds")
calc_survey_ci(seed, weights, zone_group_crosswalk, puma_client_zone_xwalk, ci_level, run_label, settings)
#> Error in get("working_dir", settings): object 'working_dir' not found
## End(Not run)