Chi-square test is utilized when testing for independence and this is done through determining the level of association between two categorical variables (Shih " Fay, 2017). In my area of research, the test will be employed in finding the relationship between children with autism and parental stress. In this case, the frequencies of each categorical variable; children with autism and parental stress are compared across the categories of the other nominal variables. The data is displayed in a contingency table having rows and columns with values of every categorical variable. The “null hypothesis (H0) and the alternative hypothesis (H1)” will be stated as:
H0: There is no relationship between children with autism and parental stress.
H1: There is a relationship between children with autism and parental stress.
The value of the observed frequencies and the expected frequencies are determined and are used to calculate the critical value
The calculated Chi-square critical value (χ2) is given as follows:
χ2 = ∑ Expected Frequency
The degrees of freedom (DF) will then be calculated as DF = (number of rows-1)*(number of columns -1). This is given as (r-1)(c-1).
The critical value will be determined at 5% level of significance.
The p-value is then computed through using chi-square tables with the respective values of the degree of freedom and at a given significance level (5%). The P-value is then compared with the calculated critical value (Shih " Fay, 2017).
The H0 (null hypothesis) is rejected if the tabulated p-value is greater than the critical value; otherwise do not reject (McHugh, 2013). Rejecting the null hypothesis means that there is a relationship between children with autism and parental stress.
References
McHugh, M. (2013). The Chi-square test of independence. Biochemia Medica, 143-149. http://dx.doi.org/10.11613/bm.2013.018
Shih, J., " Fay, M. (2017). Pearson's chi-square test and rank correlation inferences for clustered data. Biometrics, 73(3), 822-834. http://dx.doi.org/10.1111/biom.12653
