Yes Ravi, SEM is a very good option. I would suggest to use AMOS for SEM, it is very user friendly and provides good model building tools.
Of course you can repeat the process on monthly basis. For that may I suggest you to determine some kind of overall satisfaction score on the basis of all the respondents' data. Then you can see whether that score is going up or down. Also, for finding out the critical variables (or process areas), you can track down the changes in score for each process and prioritize them as you want.
Nishant
On Fri, Nov 7, 2008 at 11:01 AM, vishwesh haldavanekar <vishwesh_s_h@...> wrote:
Hi Ravi,there are several other analysis which you can do on this data such as SEM.Thank you,VishweshHello all,
I have some customer satisfaction survey data wherein customers have rated metrics such as on-time delivery,product quality, price paid etc on a scale of 1-7 (1 being least satisfied,7 being very satisfied). Based on these independent variables they have also rated their likelihood of repurchase, likelihood of referring stores to a friend,overall satisfaction on the same scale.
I have conducted Ordered logistic regression and came up with most significant variables and also the odds ratios. I repeated this to measure 3 dependent variables as 3 separate regression analysis.
I would like to know if I could go deeper and further analyze this data(given the fact that all the information is ordinal). Can any of you think of any other analysis that could be insightful?
Also, can I repeat this process on a monthly basis to measure customer satisfaction? (with new survey responses and say that so and so variables have been crucial for this month etc?)
Please let me know.
Thanks
Ravi
Add more friends to your messenger and enjoy! Invite them now.
Offline 
Send Email
