Describe the chi-square goodness-of-fit test. Provide a detailed explanation of what this test
measures, and how it is similar to and different from the independent t-test. How do you
know when to use one analysis over the other? Provide a real-world example
Chic-square goodness-of-fit test
Chic-square goodness-of-fit test aims at testing the significance difference between
observed distribution and expected. This type of test intends to investigate categorical statistics.
The test is used to investigate whether a given sample of data is dependent to the hypothesized
distribution. In other words, data has to be categorized, since it cannot analyze parametric or
even continuous statistic like heights. In addition, chic-square test of goodness is used to
establish how a given distribution estimates another. On the other hand, independent t test is
used in cases where one wants to compare the mean of normally distributed variables such as
determining whether the mean height for female and male of a given sample is similar (Bruin,
2006).
To some degree, chic-square goodness of fit is similar to independent t-test because only
two variables are used. It is not similar to independent t-test because Chic-square goodness-of-
fit, uses frequency that are mostly discrete variables while independent t test involves parametric
or continuous variables (Bruin, 2006). This test can be used to analyze gender. For instance, a
school with 35%or 10 male and 65 % or 14 female. The specifics of this analysis are to get
nominal variable (gender), current group (24 students) and comparing the two frequencies. Two
significant theories are used: observed frequency as well as anticipated frequency. Experimental
rate of recurrence is the count of observations for the present group- in this regard, the 24
students. Anticipated frequency is the tot up of frequencies in the assessment group- all
secondary school learners. The difference of observed frequencies as well as anticipated
Chic-square goodness-of-fit test 2
frequencies is known as the chi-square review. This form of analysis is normally represented
using a cross-tabulation figure.
References
Bruin, J. (2006). Newest: command to compute new test. UCLA:
Statistical Consulting Group.