I am using the Quasi-experimental posttest only design, and with the data, I am using though it would establish more validity if I used the Chi-Square to determine if there is a relationship between the data. Then use the T-Test to if the intervention had an effect on the treatment group which is what you cannot use the Chi-Square to measure.
Hi. To receive any kind of informative answer, you'll have to explain what kind of variables you have (nominal, ordinal, continuous, count ? ) and the basic design of your study. Ideally, if you can share part of a data set that mimics yours (it can be fictional), that is the most helpful for people to understand what kind of data you are working with.
Hello Sherette,
In addition to the suggestions of Sal Mangiafico , I would add that it would be helpful for you to indicate the specific research question(s) you're trying to answer. That, in conjunction with information about your variables and a brief description of how data were gathered should increase the likelihood of your getting a more focused recommendation.
Good luck with your work.
Hello All,
Thank you all for your suggestions:
Question:
The research question: How has raising the age of criminal responsibility affected the placement of juveniles in adult prisons.
Rationale:
I have obtained two sets of line-by-line data that contain sex, race, age, and county, before policy implementation and after.
Now the design I am using is the Quasi-experimental posttest-only group design. so just testing the group after the policy was implemented. I was thinking to add a bit more validity to the data a Chi-square to examine the relationship between the variables (if there is a change) Then use the t-test to test the difference before and after the treatment. I could e thinking about this wrong, but since I am receiving intake (admissions) data, I am not randomly selecting the sample.
Ho: There is no change in juvenile admissions into adult prisons
H1: There is a change in juvenile admission into adult prisons
I might be obtuse, but I still don't understand what analyses are being proposed... Starting with just the post-test Chi-square idea, what variables would you be subjecting to chi-square analysis? What kind of variables are they? When you say "if there is a change", what are you comparing? That is, how are you determining a change if you are looking only at data from after the change?
read Article Relationship between Omnibus and Post-hoc Tests: An Investig...
- Badges
- Science topic
- Similar topics
- Instrumentation Engineering
- Instruments