Dear Colleagues:
I am focusing a ratio/quotient construct/variables which is the product of the ratio of two (latent) constructs/variables and is a dependent variable and a mediator as well.
For this purpose, I measured the two variables at the seven-points Likert scale and then calculated the mean scores of each of the two variables. Finally, I calculated the ratio/quotient variables dividing the mean values of two variables.
After this computation, I tried to run my research model in SmartPLS, however, the results show very poor regression.
I have following questions in this context:
1. Is it right way to calculate the quotient/ratio construct? I followed the methodology of the following paper for the ratio calculation.
Article "Aligning Knowledge Assets for Exploitation, Exploration, an...
2. Can SmartPLS/Partial least squares be applied for dealing with such a quotient/ratio variable? The variable is my case is not following the assumption of ordinal data points/equal data intervals.
3. What software/data technique could be best for analyzing such a ration variable?
I highly appreciate your kind feedback in advance, thanks so much,
Best regards,
Muhammad Shujahat
Are you interested in the ratio of the variables, or the ratio of the two means? One is the variable, the other is a single number. You might also say what you mean by a "poor" regression.
Daniel Wright Thanks much for your kind comment. I am interested in the ratio of two variables for which I calculated the mean value of the items of each variable separately and then calculated their ratio.
But mean(x/y) is not mean(x)/mean(y). Let's say x is problems solved and y is time, and you are interested speed, you might use x/y (or if there is some start-up time to get ready to start answering, x/(y-s) ). Maybe say what your research question is?
My research question is if benefits to share resources outperform the cost (benefit-cost analysis) then the intention to share resources is going to be high. For that purpose, I operational this benefit-cost analysis as the ratio of benefits to cost whereby benefits and costs are measured as latent constructs. Actually, I measured this construct the way you are describing i.e., the mean value of benefits items/mean value of cost items
But see my comment. mean benefit / mean cost is not a variable. Maybe I am not explaining it well. I'm going to stop following this question and let others have a go.
Dear Shujahat, if you are measuring cost and benefits via latent constructs then i think its still not the actual measure and its is one of your study limitations. I suggust you to use one scale for both and divide the average in low and high. One for cost and one for benefit. Lets think more about it. Best
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling