# How to use chi-square to find association between two particular categories of two nominal variables?

2 messages
Open this post in threaded view
|
Report Content as Inappropriate

## How to use chi-square to find association between two particular categories of two nominal variables?

 This post was updated on . Dear members, I'm working with a dichotomous DV and various nominal IVs. I'm using crosstabs (chi-square) for bivariate analysis. My DV is satisfaction with response categories of "satisfied" and "not satisfied". Now I want to use chi-square to see what category of a particular IV is associated with "not satisfied" category of the DV. For example for a IV variable "type of pregnancy" with response categories of unintended pregnancy and intended pregnancy I want to see if "having an unintended pregnancy" is associated with "being not satisfied with childbirth care" but I don't know how to interpret the results of chi-square for this purpose. I don't want to merely observe whether two variables are associated rather I want to be more specific . I know it is possible, I have studied a research article where this has been done using chi-square but I don't know how? Could somebody guide me about this? Do I have to use some sort of post-hoc test for this purpose?
 See e.g. https://stats.stackexchange.com/q/74708/3277 13.08.2017 10:25, Sidra пишет: ```Dear members, I'm working with a dichotomous DV and various nominal IVs. I'm using crosstabs (chi-square) for bivariate analysis. My DV is satisfaction with response categories of "satisfied" and "not satisfied". Now I want to use chi-square to see what category of a particular IV is associated with "not satisfied" category of the DV. For example for a DV variable "type of pregnancy" with response categories of unintended pregnancy and intended pregnancy I want see if "having an unintended pregnancy" is associated with "being not satisfied with childbirth care" but I don't know how to interpret the results of chi-square for this purpose. I don't want to merely observe whether two variables are associated rather I want to be more specific . I know it is possible, I have studied a research article where this has been done using chi-square but I don't know how? Could somebody guide me about this? Do I have to use some sort of post-hoc test for this purpose? -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/How-to-use-chi-square-to-find-association-between-two-particular-categories-of-two-nominal-variables-tp5734644.html Sent from the SPSSX Discussion mailing list archive at Nabble.com. ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD ``` ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD