The Chi2 Breakdown
How much deviation can occur before one must conclude that something other than chance is at work, causing the observed to differ from the expected?
One of the most used method for measuring varying frequencies or proportions is the Chi-square test. It is utilized to determine a particular proposition or hypothesis whether the observed data would deviate from those that are expected. The Chi-square test is a type of univariate analysis, a type that evaluates the possible effect of the independent variable (i.e. age) to the dependent variable (outcome – perception of a certain situation). It is an analysis of measure of fit or typically tagged as goodness of fit between the gathered data.
The Chi-square analysis is used to test the null hypothesis, the hypothesis which states that there is no relationship between the independent variable to the dependent variable or there is no significant difference between the expected from the observed. After comparing the value of Chi-square to the assumed probability distribution, one would be enforced either to accept or reject the null hypothesis. Those values with low probability leads to the rejection of the null hypothesis and is assumed that there’s reason or cause other than chance that created a sizeable deviation between expected and observed results.
The Answer
First determine the degree of freedom (df) which is the number of categories in the problem minus one. Then determine a relative standard to serve as the basis for accepting or rejecting the hypothesis, compute for the Chi-square value. Then refer to the Chi-square distribution table.
If the value of the degree of freedom is greater than the Chi-square value, accept the null hypothesis – there’s no relationship.
