A.
Wahab
Selasa, 29 Agustus 2017
Prodi S2 Kebidanan Universitas Aisyiyah Yogyakarta
A special case of existing statistics: it is
reanalysis of previously collected survey or other
data that were originally gathered by others
(Neuman, 2006)
Analysis of data by researchers who will probably
not have been involved in the collection of those
data for purposes that in all likelihood were not
envisaged by those responsible for the data
collection (Bryman, 2004).
It prevents you from duplicating work that has
been done before.
It helps you to find out what others have learned
and reported on the problem you want to study.
This may assist you in refining your statement of
the problem.
It helps you to become more familiar with the
various research approaches that might be used in
your study.
It should provide you with convincing arguments
for why your particular research project is needed.
Analisis data sekunder yang bersumber dari
data yang dikumpulkan oleh peneliti lain.
Analisis data sekunder yang bersumber dari
data yang dikumpulkan oleh institusi lain
(misalnya universitas, BPS)
Individuals, groups, and organisations;
Published information (books, articles,
indexes, abstract journals); and
Unpublished information (other research
proposals in related fields, reports, records,
computer data bases)
Administrative Levels:
oCommunity and district or provincial levels
oNational levels
oInternational levels
Community and district or provincial levels:
Opinions, beliefs of key informants (through
interviews), in addition to written sources
Clinic- and hospital- based data from routine
statistics, registers
Clinical observations, reports of critical incidents
Local surveys, annual service reports
Statistics issued at provincial and district levels
Newspapers, books, articles, mimeographed
reports, etc.
National Levels:
Articles from national journals, books identified
during literature searches at university and other
national libraries, WHO, UNICEF libraries, etc.
Special collections, e.g., newspaper clippings,
archival records, library or congress collections
Documentation, reports and raw data from:
◦ The Ministry of Health (e.g., 5-year plans)
◦ central statistical offices
◦ Non-governmental organisations
International levels:
Information from:
◦ Bilateral and multilateral organisations (e.g., IDRC, USAID,
UNICEF, WHO);
◦ Computerised searches for international literature (from
national library or international institutions).
Yuni (2013)
This dissertation discusses the association of
asphyxia in premature infants to the quality
of life of children aged 2-4 years with
retrospective cohort design. Asphyxia data
were obtained from the medical records of
Dr. Sardjito hospital, while the quality of life
of children data were assessed using PedsQL.
Data were analyzed using Cox regression.
Waktu dan Biaya
Kualitas Data: sampling, cakupan geografis,
pengalaman tim peneliti
Dapat melakukan analisis antar waktu:
melihat tren perubahan yang terjadi
Dapat melakukan analisis sub kelompok:
berdasarkan usia, etnis, agama, tingkat
pendidikan, dsb
Dapat melakukan analisis antar kelompok
budaya: perbandingan antar negara
melalui DHS (SDKI) survei memperbandingkan
dengan sesama negara berkembang, sesama
negara muslim, dsb
Lebih banyak waktu untuk analisis data
Menawarkan interpretasi yang berbeda
dengan sebelumnya
Penggunaan yang maksimal dari riset yang
telah dilakukan kewajiban peneliti
Perlu waktu untuk memahami data
◦ Peneliti dapat menggunakan data sekunder yang
tidak sesuai dengan tujuan penelitian.
◦ Peneliti dapat tidak dapat memahami data dengan
benar dan membuat asumsi yang salah terhadap
data.
Kompleksitas data: jumlah variabel yang
banyak dan sampel yang besar sensus
Tidak memiliki kontrol terhadap kualitas data
Peluang melakukan ecological fallacy
Validitas:
◦ Definisi teoritis peneliti tidak sesuai dengan definisi
dalam penelitian yang dipakai.
◦ Data yang dipakai tidak akurat menggambarkan hal
yang ingin diteliti.
◦ Kualitas data yang digunakan: kesalahan dalam
pengumpulan data, pengolahan, dan pelaporan
data.
Reliabilitas:
◦ Definisi yang dipakai dalam data sekunder berubah
dari waktu ke waktu
◦ Mengkomparasikan data set antar negara yang
berbeda definisi dan metodenya
Dilema penggunaan data statistik resmi:
◦ baik karena rendahnya reactivity tetapi kepentingan
pemerintah dapat bermain
Isu:
◦ Problem sama dengan yang dihadapi oleh data
kuantitatif
◦ Konteks berbeda: setting, latar belakang informan
◦ Etika penelitian: consent, confidentiality
Bersambung ......
