Exam 1

  1. Metainformation

    Tag Value
    fileReliability_eur-reliability-209-en_eur-reliability-209-en
    nameeur-reliability-209-en
    sectionReliability/Analysis/Cronbach's alpha
    typeschoice
    solutionFALSE, TRUE, FALSE, FALSE
    TypeCalculate
    ProgramCalculator
    LanguageEnglish
    LevelStatistical Literacy

    Question

    Below you see the item variances of 12 items that together form a test to measure performance anxiety. The variance of the total score is 52.5. How many parallel items have to be added to get a reliability of .8?

    Items Variance
    1 1.5
    2 2.1
    3 1.2
    4 0.8
    5 1.0
    6 1.3
    1 2.1
    2 2.2
    3 2.5
    4 0.9
    5 1.2
    6 1.7

    Use the following formulas:

    Alpha=(k/(k−1))×(1−∑Si2/Sx2)Alpha = (k / (k-1)) \times ( 1 - ∑S^2_i / S^2_x)

    n=(Rxx−revised×(1−Rxx−original))/(Rxx−original×(1−Rxx−revised))n = (Rxx-revised \times (1-Rxx-original))/(Rxx-original \times (1- Rxx-revised))

    Where Rxx-revised is the alfa you want to obtain and Rxx-original the reliability you originally had.


    1. FALSE: 20
    2. TRUE: 8
    3. FALSE: 7
    4. FALSE: 19

    Solution

    The sum of the variances is 18.5. The reliability of the test is 12÷11×(1−18.5÷52.2)=.70612 \div 11 \times (1-18.5 \div 52.2)=.706. Spearman-Brown formula can be used to calculate the lengthening factor n. This n is: .23÷.14=1.662.23 \div .14=1.662. When we product this value with 12, this is 19.9. This means that 8 items have to be added.


    1. False
    2. True
    3. False
    4. False