再測信度概念的前提應為個案特質不變的狀況下，可以得到相同結果
因此，找出的文章中對在概念陳述上仍不完整
自己在閱讀文章時，應具批判能力，才不會被混淆!!!!!
由於對心理計量特性的概念尚未釐清，容易造成寫作陳述上無法正確描述
例如會將概念的陳述與研究設計方法混淆
以下是我原先對Test-retest reliability的概念與應用寫法：
[概念] Test-retest reliability refers to the extent to which results are
consistent across multiple time points, and the results of the same
construct administered on the same individuals can be reliably replicate
multiple times.
[應用] If the measure is reliable that means it is suitable for longitudinal
research.
老師表示：
再測信度就概念而言，應為在同個時間點測量相同個案多次都能得到相同的結果(例如量血壓)
但是真實情境下，評估工具無法在同個時間點評估相同個案多次
才會在研究方法學設計上以間隔兩個(以上)時間點去進行評估
因此當一個評估工具是穩定一致的狀況下，單一時間點評估即可得到可信賴之結果。
為了釐清自己是對概念或文章閱讀上的問題
謝老師建議找出3-5篇有敘述Test-retest
reliability研究意義的相關文獻
Reference 1:
[定義] Test-retest reliability evaluates the consistency of the measuring instrument; that is the probability of producing the same results with repeated administration of the test.
[研究方法] In this case, evaluating test-retest reliability involves a sample of patients completing the questionnaire on two occasions, under the same conditions.
[應用] If the test is reliable, each patient’s score will be identical across the two occasions.
Reference 2
[定義] Test-retest reliability is the stability of a measuring instrument over time.
[執行方法] It is assessed by giving the measure to the same subjects on two different occasions and examining the correlation between the two scores.
[應用] It is pertinent for self-report instruments.
Reference 3
[研究方法] Test-retest reliability is estimated by administering the same test to the same group of respondents at different times. The correlation between the two scores, and often between individual questions, indicates the stability of the instrument.
Reference 1:
[定義] Test-retest reliability evaluates the consistency of the measuring instrument; that is the probability of producing the same results with repeated administration of the test.
[研究方法] In this case, evaluating test-retest reliability involves a sample of patients completing the questionnaire on two occasions, under the same conditions.
[應用] If the test is reliable, each patient’s score will be identical across the two occasions.
Reference 2
[定義] Test-retest reliability is the stability of a measuring instrument over time.
[執行方法] It is assessed by giving the measure to the same subjects on two different occasions and examining the correlation between the two scores.
[應用] It is pertinent for self-report instruments.
Reference 3
[研究方法] Test-retest reliability is estimated by administering the same test to the same group of respondents at different times. The correlation between the two scores, and often between individual questions, indicates the stability of the instrument.
Reference:
1.
Bialocerkowski,
A., & Bragge, P. (2008). Measurement error and reliability testing:
Application to rehabilitation. International Journal of Therapy and
Rehabilitation, 15(10), 422–427.
2.
Hobart,
J. C., Lamping, D. L., & Thompson, A. J. (1996). Evaluating neurological
outcome measures: the bare essentials. Journal of Neurology, Neurosurgery &
Psychiatry, 60(2), 127–130. doi:10.1136/jnnp.60.2.127
3.
DeVon
HA, Block ME, Moyle-Wright P et al (2007) A psychometric toolbox for testing
validity and reliability. Journal of Nursing Scholarship, 39(2): 155–64
沒有留言:
張貼留言