The Chi Square Test For Independence

Chi-Square is a statistical test that is utilized to make comparisons of observed data with data that the researcher expects to find with respect to a specified hypothesis. The test is used to determine whether the deviations in the data observed from the expected data have occurred just by chance or is caused by other factors (Brooks, 2008). The Chi-Square is usually employed to test the null hypothesis. For instance, it can be used to test whether there is no significant difference between the expected and observed outcomes. The Chi-Square is used in two circumstances as below: i) When the researcher want to estimate how closely the observed distribution matches the proportions that is expected. This is called ‘goodness of fit’ test. ii) When the researcher wishes to estimate whether random variables used are independent. Assumptions of the Chi-Square Test: i) To use Chi-Square test for independence, the two variables that are used must be of categorical data i.e. the data ought to be measured at nominal or ordinal levels. Furthermore, the two variables used ought to be composed of at least two categorical and independent groups (Brooks, 2008). For instance, ethnicity could consist of two groups i.e. Hispanic, Caucasian, and American) and gender can consist of two groups of females and males. ii) When using Chi-Square, the data ought not to be correlated. Therefore, the test cannot be performed when the data employed in the research is correlated. iii) The data must also be quantitative and the observations that are made must be independent. This means that the Chi-Square cannot be used when the data that is used in the research is qualitative. iv) The Sample size should be sufficiently large. This means that the sample size... ... middle of paper ... ...hip between the two variables. A regression coefficient close to zero means there is a weak relationship between the two variables. On the other hand, a regression coefficient close to 1 shows a strong relationship between the two variables. I will use Chi-test to address the study hypothesis. This is because the test is normally used when the researcher wants to determine whether there are differences in the categorical variables. For instance, social features such as religion, political differences, ethnical differences, etc. Therefore, I will come up with two hypotheses. Afterward, I will choose the significance level, calculate the test value then compare this to the critical value. If the test value is less than the critical value, I will not reject null hypothesis. However, if the test value is larger than the critical value, I will reject the null hypothesis.
Get Access