One row per household: first and last survey month with asset data, derived from
tstm_asset_loan in
vignettes/ffv_gen_asset_loan.qmd.
Format
Household start and end month file.
- id
Anonymized household ID (
tmid_hh). Matchesidintstm_asset_loanfor households present in both files.- month_start
First survey month with asset data for this household
- month_end
Last survey month with asset data for this household
- month_n
Number of household-month rows in
tstm_asset_loanfor thisid
Source
Regenerated by
vignettes/ffv_gen_asset_loan.qmd
(household span step; formerly
data-raw/ffs_hfid_gen_b_data.R;
PrjThaiHFID-#5).
Same bl_replace_data_output workflow as tstm_asset_loan. Shipped as
data/tstm_hh_mthspan.rda; the vignette also writes local-only CSV/DTA
copies to inst/extdata/tstm_hh_mthspan.{csv,dta}, but that folder is
git-ignored and excluded from the build (.Rbuildignore), so it is not
shipped — installed users load via data(tstm_hh_mthspan).
Anonymized in data-raw/id_anonymize/;
true IDs in data-raw/id_anonymize/tstm_hh_mthspan_true_id.rda.
Downstream vignettes: household-span denominator for the investment
frequency tables in ffv_invest_freq_sizes (issue
#9).
Details
The packaged object stores anonymized household IDs: id holds tmid_hh
from data-raw/tm_key_id.rda via data-raw/id_anonymize/ (same crosswalk as
id in tstm_asset_loan). True IDs are backed up in
data-raw/id_anonymize/tstm_hh_mthspan_true_id.rda.
Examples
data(tstm_hh_mthspan)
ffp_preview_dataset(tstm_hh_mthspan)
#>
#> ── tstm_hh_mthspan ─────────────────────────────────────────────────────────────
#> Dimensions: 791 rows × 4 columns(19.8 Kb)
#>
#> ── Column names (4) ──
#>
#> • 1. id
#> • 2. month_start
#> • 3. month_end
#> • 4. month_n
#>
#> ── Summary statistics (all variables) ──
#>
#> id month_start month_end month_n
#> Min. :1003 Min. : 0.000 Min. : 2.0 Min. : 3.0
#> 1st Qu.:3166 1st Qu.: 0.000 1st Qu.:160.0 1st Qu.:161.0
#> Median :5412 Median : 0.000 Median :160.0 Median :161.0
#> Mean :5467 Mean : 5.345 Mean :146.8 Mean :142.5
#> 3rd Qu.:7706 3rd Qu.: 0.000 3rd Qu.:160.0 3rd Qu.:161.0
#> Max. :9996 Max. :94.000 Max. :160.0 Max. :161.0
#> ── Sample rows (first 6) ──
#>
#> # A tibble: 6 × 4
#> id month_start month_end month_n
#> <int> <dbl> <dbl> <int>
#> 1 1003 0 35 36
#> 2 1015 0 2 3
#> 3 1031 0 160 161
#> 4 1046 0 160 161
#> 5 1059 0 160 161
#> 6 1078 0 160 161