A comparison of the exact and approximate power of the chi-square goodness-of-fit test.
comparisonofexac00wrig.pdf (4.544Mb)Abstract
This thesis presents a numerical comparison of the exact
and approximate powers of the chi-square goodness-of-f it
test for small numbers of classes and small sample sizes for
the equiprobable null hypothesis . The comparison was performed
using an IBM 360 computer and the computational
details are presented within the thesis. In addition a
comparison of critical points was conducted for the chisquare
distribution and the associated exact, (multinomial),
distribution. The results of the power comparisons show
that the approximate power is surprisingly good and is
recommended as an efficient method for determining type two
error associated with the test. Further, use of the chisquare
distribution for determining a critical point is
reinforced through the numerical comparison of significance
levels.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Approximate interval estimation methods for the reliability of systems using component data with exponential and Weibull distributions.
(Monterey, California. Naval Postgraduate School, 1989-09);Two approximate parametric interval estimation methods for system reliability using component test data are developed and evaluated. One method can be applied to any coherent system with components which have exponential ... -
Determining Operational Hit Probabilities for Field Artillery Weapons Systems
(Monterey, California. Naval Postgraduate School, 1968-06);The Department of the Army has expressed a need for the determination of the operational hit probabilities of several weapons systems in use throughout the Army. These hit probabilities, together with lethality models, ... -
The effect of error non-normality on the power of parametric and non-parametric ANOV tests.
(Monterey, California ; Naval Postgraduate School, 1971-09);The purpose of this thesis is to determine the power relationship, through computer simulation, between the parametric ANOV and non-parametric Wilson tests under controlled conditions of error non-normality. Data is ...
