mys_panel: mean years of schooling of people with disabilities, 2016-2026

A synthetic panel dataset with direct estimates of the mean years of schooling of people with disabilities in the 42 areas of mys over 11 years (2016-2026). Areas 21 and 25 are never sampled (y = NA in every year). The rows are in time-major order (all areas of 2016, then 2017, ...); eblup_stfh sorts them internally, but sae::eblupSTFH() needs domain-major order.

Usage

mys_panel

Format

A data frame (tibble) with 462 rows and 10 variables:

area

area identifier, 1 to 42.

year

year of observation (2016 to 2026).

y

direct estimate of the mean years of schooling (NA for areas 21 and 25).

vardir

sampling variance of the direct estimate (NA where y is NA).

rse

relative standard error of the direct estimate (%).

x1

number of elementary schools.

x2

number of junior high schools.

x3

number of senior high schools.

n

number of people with disabilities in the Susenas sample of the area in that year (eligible sample size; synthetic, hence not an integer, and positive also for areas 21 and 25). vardir was not derived from it.

weight

sample share, n / sum(n) over all rows of the panel (the weights sum to 1 over the panel, not within a year).

Source

Simulated panel data based on empirical characteristics of the National Socio-Economic Survey (Susenas), BPS-Statistics Indonesia.

Examples

data(mys_panel)
head(mys_panel)
#> # A tibble: 6 × 10
#>    area  year     y vardir   rse    x1    x2    x3      n   weight
#>   <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>    <dbl>
#> 1     1  2016  8.26  0.662  9.85 123.   24.8 12.9   7229. 0.00287 
#> 2     2  2016  7.48  0.837 12.2   93.2  17.8  9.14  2767. 0.00110 
#> 3     3  2016  5.55  0.882 16.9   54.0  18.0  5.10  1693. 0.000671
#> 4     4  2016  3.43  0.658 23.7   87.4  35.8 17.8   3140. 0.00125 
#> 5     5  2016  6.46  1.28  17.5  138.   45.7 27.1  13421. 0.00532 
#> 6     6  2016  3.61  0.388 17.3   95.7  29.2 10.6   1984. 0.000787
table(sampled = !is.na(mys_panel$y), mys_panel$year)[, 1:3]
#>        
#> sampled 2016 2017 2018
#>   FALSE    2    2    2
#>   TRUE    40   40   40