SAMPLE SIZE SPECIAL CASE

This forum is closed, and read-only.
Locked
alizol
PLS User
Posts: 11
Joined: Wed Nov 02, 2016 5:54 pm
Real name and title: Ali Zolfaghari

SAMPLE SIZE SPECIAL CASE

Post by alizol »

Dear professors,
Imagine that I want to test the fitness of a model for measuring performance of new product development projects. I consider the total performance of new product development (TTNPD) as a second order construct which have -for example- two dimensions which are first order constructs. Let’s name them as strategic performance (ONPD) and technical performance (TNPD).
I have ten development projects and I have ten experts to judge about different indicators of first order constructs (2 dimensions). Could I multiply ten to ten and say I have hundred samples which means the sample size is hundred or- for every person and every indicator- I must get an average of his/her judgements for different projects and get a sample size of ten which every sample is consisted of average of judgements for different projects? I just use SmartPLS2 for testing the fitness.
I myself believe that every judgment -whether it is done by one person or different persons and about one unique project or about different projects- indicates a relation between regression coefficients and it is an observation that can be used for parameters’' estimation which must not be neglected. So for just doing a confirmatory analysis there is no need to get an average. But some people may say that in this case the samples are not completely independent. What do you think? Although I think without doing an inferential statistics there will be no problem. Note that I don’t want to say anything about difference of parameters estimates of different experts so I forgot about MGA.

Thanks in Advance
alizol
PLS User
Posts: 11
Joined: Wed Nov 02, 2016 5:54 pm
Real name and title: Ali Zolfaghari

Re: SAMPLE SIZE SPECIAL CASE

Post by alizol »

For more clarification: I mean is it true to say that bootstrapping cases(=Sample size)( or no of data rows in spss)=the no. of respondents * the no. of projects?
(10*10=100)
Locked