Conditions Affecting Integrity of A Factor Solution Under Varying Degress of Over - Extraction  

Oleh:

Hancock, Gregory R. ; Lawrence, Frank R.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: Educational and Psychological Measurement vol. 59 no. 4 (1999), page 549-579.
Topik: extraction; data integrity; sampling; mathematical analysis
Fulltext: 549.pdf (141.52KB)

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: EE30.4 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Simulated data were employed to test the integrity of orthogonal factor solutions when varying sample size, factor pattern . structure coefficient magnitude, method of extraction (principal component vs common factor), number of variables, number fo factors and degree of over extraction. Factor solutions' itnegrity was opeationalized by comparing sample factor / component patterns to know population factor patterns, from which measures of non zero coefficient bias and variability, and zero coefficient bias and variability, were determined. Slopes of each of these measure across degrees of over extraction were determined and related to the expeirmental condition variables. Results showed that non zero pattern / strucutre coefficients generally degrade with increased over extraction, with PCA coefficients exhibiting this property to a greater degree than CFA coefficients. With smaller sampel size and sample coefficient magnitude, the degradation was greater, with higher sample size and larger coefficients, coefficient degradation was usually not enough to yield incorrect factor / component structure interpretations.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali