Hey guys,
I am currently writing my thesis and currently struggle with the implementation of my model.
The goal of my analysis is to find out in how far a companies perceived risk influences the supplier engagement strategy. Thus, I planned to conduct a regression in order to find out between which risk and engagement strategy the correlation is the biggest (implying then, that the risk triggers the engagement strategy with the highest correlation).
Thereby the companies from the data set indicate one risk but sometimes multiple engagement strategies with different intensity. These engagement strategies must be weighted according to the percentage of suppliers they apply the strategy on. To give you an example: a company perceives reputation as the risk and uses the strategy "Codes of conduct" on 70% of their supplier while they use the strategy "technology improvement" on 10% of their suppliers.
I am wondering, how I can implement this weighting of engagement strategies in Stata. Coming back to the example: How can I tell STATA that "codes of conduct" and "technology improvement" are not equally used and how can I make STATA show that in my results?
If you have any idea, please reach out to me, I will be very grateful.
Thank you so much in advance!!
Related Posts with Weighted correlation
Using cii proportions with loopHello, I am trying to compute confidence intervals for proportions (number of cases / total) on eac…
LSDV and collinearityHi everyone, I am having trouble implementing a simple least square dummy variable (LSDV) model. The…
Please help cant work out how to t-test. Im new to stataHi guys I'm struggling to compare 2 different regions with a t-test. As seen from the screenshots I…
please help. making bar graph more simple with "over" optionsHi, guys. I'm a newcomers with stata, and there is some trouble in making bar graph. My data has 4…
Pseudo Panel Data and Mediation AnalysisDear Stata Experts I'm a PhD student, and I'd like to know how to use the codes to perform the Medi…
Subscribe to:
Post Comments (Atom)
0 Response to Weighted correlation
Post a Comment