The Effects of Sampling Model on Inference With Coefficient Alpha  

Oleh:

Hakstian, A. Ralph ; Barchard, Kimberly A.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: Educational and Psychological Measurement vol. 57 no. 6 (1997), page 893-905.
Topik: sampling; psychology; test methods; cognition & reasoning
Fulltext: 893.pdf (1.14MB)

Ketersediaan

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

Lihat Detail Induk

Isi artikel

The distinction between type I and type 12 sampling in connection with measurement data is discussed, and a method is presented for simulating data arising from type 12 sampling. Next, an empirical study is described in which the performance of inferential procedures for coefficient alpha was examined when the procedures were applied with data rising from both kinds of sampling. The results indicate that as long as the data are drawn from a population exhibiting strict parallelism among the conditions (an assumption underlying the procedures), the methods maintain prices confidence level control under type 12 sampling. For data departing from essential parallelism, however, these procedures are not robust under type 12 sampling. In contrast, actual confidence coefficient values were close to nominal levels under type I sampling. Implications are noted for practice and for future research on inference with coefficient alpha.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali