This data set is synthetically generated from real GLSS (Ghana Living Standards Survey) data.
A data frame with 36970 observations on the following 14 variables.
integer; the household ID.
integer; the number of persons in the household.
factor; the region in which the household is located
(levels western, central, greater accra, volta,
eastern, ashanti, brong ahafo, northern,
upper east and upper west).
factor; the enumeration area.
integer; the person's age.
factor; the person's sex (levels male and
female).
factor; the relationship with the
household head (levels head, spouse, child,
grandchild, parent/parentlaw, son/daughterlaw,
other relative, adopted child, househelp and
non_relative).
factor; the person's
nationality (levels ghanaian birth, ghanaian naturalise,
burkinabe, malian, nigerian, ivorian,
togolese, liberian, other ecowas, other africa
and other).
factor; the person's ethnicity
(levels akan, all other tribes, ewe, ga-dangbe,
grusi, guan, gurma, mande and
mole-dagbani).
factor; the person's religion
(levels catholic, anglican, presbyterian,
methodist, pentecostal, spiritualist, other
christian, moslem, traditional, no religion and
other).
factor; the person's highest
degree of education (levels none, mlsc, bece,
voc/comm, teacher trng a, teacher trng b, gce 'o'
level, ssce, gce 'a' level, tech/prof cert,
tech/prof dip, hnd, bachelor, masters,
doctorate and other).
factor; the
person's occupation (levels armed forces and other security
personnel, clerks, craft and related trades workers,
elementary occupations, legislators, senior officials and
managers, none, plant and machine operators and assemblers,
professionals, service workers and shop and market sales
workers, skilled agricultural and fishery workers, and
technicians and associate professionals).
numeric; the person's annual income.
numeric; the sample weights.
The data set consists of 8700 households and is used as sample data in some
of the examples in package simPopulation. Note that it is included
for illustrative purposes only. The sample weights do not reflect the true
population sizes of Ghana and its regions. The resulting population data is
about 100 times smaller than the real population size to save computation
time.
Only some of the variables in the original survey are included in this example data set. Furthermore, categories are aggregated for certain variables due to the large number of possible outcomes in the original survey data.
Ghana Statistical Service (2008) Ghana Living Standards Survey: Report of the fifth round.