Included Analyses
Reliability Analysis for x1, x2, x3, x4, x5, x6, x7, x8, and x9
Glossaries
Chronbach's Alpha
Reliability testing is done to assess the consistency of responses among a group of questions.
This is also referred to as internal consistency or inter-item reliability. Cronbach's alpha
coefficient is commonly used to measure reliability. The purpose of this test is to determine if a
group of questions all measure the same construct, concept, or idea. This test is used when
creating a composite score to ensure that all of the items that make up the composite score are
consistent with each other. The Cronbach reliability test calculates the reliability coefficient
alpha (α), which indicates the degree of consistency among the items. George and Mallery
(2010) suggest the following guidelines for evaluating α values: > .9 excellent, > .8 good, > .7
acceptable, > .6 questionable, > .5 poor, ≤ .5 unacceptable. The Cronbach reliability test assumes
that the items being tested measure a single construct (i.e., the construct is unidimensional), and
that observations are independent of each other.
Fun Fact! Cronbach's alpha is named after Lee Joseph Cronbach, formerly an educational
psychologist and professor at Stanford University. It was intended to be the first in a series of
statistical coefficients (hence the name "alpha").
Alpha Level for Subscales (α): Ranges from 0.00 to 1.00; gives the reliability/consistency of
the responses to the groups of questions or items that make up a subscale.
Composite Score: A single overall score (usually an average or a sum) computed from multiple
items or measurements.
Raw Output
Reliability Test for group_x
Item Statistics:
Variable n R R drop M sd
x1 10000 0.665 0.604 -0.016 1.728
x2 10000 0.659 0.599 -0.006 1.735
x3 10000 0.648 0.587 -0.008 1.725
x4 10000 0.654 0.594 0.018 1.719
x5 10000 0.661 0.6 -0.002 1.735
x6 10000 0.653 0.593 -0.005 1.732
x7 10000 0.666 0.606 -0.015 1.73
x8 10000 0.667 0.607 -0.029 1.751
x9 10000 0.662 0.603 0.009 1.74
Reliability when an item is dropped:
Variable α αstd Ravg αse
x1 0.853 0.853 0.42 0.002
x2 0.853 0.853 0.421 0.002
x3 0.854 0.854 0.423 0.002
x4 0.854 0.854 0.422 0.002
x5 0.853 0.853 0.421 0.002
x6 0.854 0.854 0.422 0.002
x7 0.853 0.853 0.42 0.002
x8 0.852 0.852 0.419 0.002
x9 0.853 0.853 0.42 0.002
Results
Reliability
Introduction. A Cronbach alpha coefficient was calculated for the group_x scale. The
Cronbach's alpha coefficient was evaluated using the guidelines suggested by George and
Mallery (2016) where > .9 excellent, > .8 good, > .7 acceptable, > .6 questionable, > .5 poor, and
≤ .5 unacceptable.
Results. The items for group_x had a Cronbach's alpha coefficient of 0.87, indicating good
reliability. Table 1 presents the results of the reliability analysis.
Table 1
Reliability Table for group_x
Scale No. of Items α
group_x 9 0.87
References
George, D. & Mallery, P. (2016). SPSS for Windows step by step: A simple guide and reference,
11.0 update (14th ed.). Boston, MA: Allyn and Bacon.
Intellectus Statistics [Online computer software]. (2017). Retrieved from
[Link]