Page 215 - Contributed Paper Session (CPS) - Volume 2

CPS1825 Suryo A.R.
higher the value of the indicator, the higher the score, while the negative
indicator applies otherwise. After that, the value of each indicator is
normalized. Normalization used in this research is standardization (z-score).

Calculation of scores for each dimension
Scores in each dimension are calculated with reference to the Indonesian
Youth Development Index 2017. The index of each dimension is calculated by
the equal weighting.

Calculation of Youth Development Index
Youth Development Index is obtained by averaging each dimension score.
The equal weight of each dimension means that the five dimensions have the
same role to the development of youth. The use of equal weight because it
can answer all arguments ethically or morally in the future about determining
the more important aspects for youth development in South Kalimantan, even
though in each dimension there are indicators that have the biggest role in
shaping the dimension score (Bappenas, 2017).
Measurement of disability in this research using Washington Group on
Disability Statistics (WG) which is included in Socio-Economic National Survey
in Indonesia. WG short set questions are not designed to measure all aspects
of difficulty in functioning that people may experience, but rather those
domains of functioning that are likely to identify the majority of people at risk
of participation restrictions, such as difficulty seeing, hearing, walking,
remembering or concentrating, self-care, and communicating.

Factor Analysis
Factor analysis is a statistical method used to describe variability among
observed, correlated variables in terms of a potentially lower number of
unobserved variables called factors (Johnson & Wichern, 2007). In factor
analysis there is random vector X with p component which has mean µ and
covariance matrix ∑ factor model states X linearly dependent with some
unobserved variables which are called common factors (F1, F2, …, Fm), and other
source of variation which is summed up as p (e1, e2, …, ep) or called error or
specific factor.
In this research, X is a variance-covariance matrix and p(max) for indicators
in dimension education, health and well-being, employment and opportunity,
participation and leadership, gender and discrimination are 4, 4, 3, 3, and 3
with condition that m ≤ p. λ is the eigen value of variance-covariance matrix ∑
2
or correlation matrix R. hi is communalities which shows the variance
proportion of indicator/variable i which can be explained in general factor.
While a variance which cannot be explained by general factor will be explained
by a specific factor with specific variance. lij is loading which shows a

204 | I S I W S C 2 0 1 9