I have a data set with 2 time frames. Each time frame has a categorical dependent variable, 6 continuous predictor variables, and 4 sociodemographic control variables. I plan to use multiple regression to examine the relationships between the 6 predictors and outcome variable but I have two time points and I want to examine if there is any change between time 1 and time 2 (5 years apart). Please what is the best statistical method to apply in this case?
If I understand you correctly you might refer to the following:
Davidian Notes
https://www4.stat.ncsu.edu/~davidian/st732/notes.html
Multivar. Long. Models:
https://www.researchgate.net/post/What_statistical_test_is_appropriate_for_pre_and_post_trails_with_1_before_treatment_value_and_4_after_treatment_values_assessed_weekly
Best wishes, David Booth
Multiply regression is not used to find the change. It is used to construct a model or a relationship. T-test can be used to find the difference or change between two groups.
I agree with Abdulmuhsin.
The classic method of determining a difference is through a T-test, where an ANOVA or ANCOVA handle multiple samples, classes, etc... I would suggest an ANCOVA, because this method would correct for any confounding factors within your data. Although, sometimes it's best to go simple and perform a simple T-test, better yet, you can use a difference column (where you take the difference between each time frame) and test that series alone.
- Badges
- Science topic
- Similar topics
- Linguistics
- Composition Studies
- Publication