2. The Friedman Test without Ties
a. Case 13.7: At the XYZ School District, three methods of recording scores
on classroom teacher performance on principal brief classroom visits are
being tested. Method 1 uses an iPad; Method 2 uses paper checklist; and
Method 3 uses a narrative summary, much like traditional physician’s
progress notes. The District CEO wants to know which method enables
the most accurate recording of classroom teacher instructional efficacy;
she is concerned about missing information and memory decay. Nine
elementary school teachers are observed during the course of the school
year, using each method. Observers were rigorously trained in the optimal
use of each method. Performance scores ranged from “0” to “50” with a
higher score suggesting greater teaching efficacy.
b. Computation Sequence
(1) If the sample sizes aren’t too small, then the T test statistic can be
compared to a critical chi square value for k – 1, degrees of freedom,
using Formula 13.7. If the test statistic is greater than the critical value,
reject the null; if not, retain the null hypothesis (Daniel, 1990, p. 265).
(2) The null hypothesis (H0) is that there are no differences between the
rankings among the 3 groups. The alternative hypothesis (H1) is that
the ranks among the 3 groups differ.
(3) After ranking the data, Data Table 13.8 emerges.
2. The Friedman Test without Ties
a. Case 13.7: At the XYZ School District, three methods of recording scores
on classroom teacher performance on principal brief classroom visits are
being tested. Method 1 uses an iPad; Method 2 uses paper checklist; and
Method 3 uses a narrative summary, much like traditional physician’s
progress notes. The District CEO wants to know which method enables
the most accurate recording of classroom teacher instructional efficacy;
she is concerned about missing information and memory decay. Nine
elementary school teachers are observed during the course of the school
year, using each method. Observers were rigorously trained in the optimal
use of each method. Performance scores ranged from “0” to “50” with a
higher score suggesting greater teaching efficacy.
b. Computation Sequence
(1) If the sample sizes aren’t too small, then the T test statistic can be
compared to a critical chi square value for k – 1, degrees of freedom,
using Formula 13.7. If the test statistic is greater than the critical value,
reject the null; if not, retain the null hypothesis (Daniel, 1990, p. 265).
(2) The null hypothesis (H0) is that there are no differences between the
rankings among the 3 groups. The alternative hypothesis (H1) is that
the ranks among the 3 groups differ.
(3) After ranking the data, Data Table 13.8 emerges.
การแปล กรุณารอสักครู่..