Dear Goi

it will be better to clarify the design you used, research purpose (questions), sample size, normality(non) of the distribution,  IV.s and DV(s).

otherwise judgment would be not logic. 

Rana,

I am sorry for not specific clarifying. I had just edit the question above... hope can give some advice on that. 

Dear Ks,

Full factorial experiment with rbd might results in difficulty to examine and explain several interactions. Since you want to find an optimal combination, i guess you have quantative factors. If it is the case, the best method is response surface analysis. If not, providing a flowchart for the effects of your factors on the response can help you to  carry out your analysis hierarchically. Please note the that full factorial design only can serve your purposes if your factors have the same importance and you need to analyze them as parallel effects. 

agree with Hormoz, response surface methodology would be useful

Forgive for my low understanding in response surface methodology.

Is there a standard procedure i could refer in carrying out RSM? 

Ks,

There is a nice software called design expert. This software can help you a lot on this topic:

http://www.statease.com/software/dx9-trial.html

RSM is a method for designing an experiment for finding optimal combination of factors. I think you can find your answers by reading software's help.

Goi,

hope this will help you

best wishes

http://www.google.com.sa/url?sa=t&rct=j&q=&esrc=s&frm=1&source=web&cd=2&cad=rja&uact=8&ved=0CDMQFjAB&url=http%3A%2F%2Fwww.brad.ac.uk%2Fstaff%2Fvtoropov%2Fburgeon%2Fthesis_luis%2Fchapter3.pdf&ei=oDRPVZ6qD8j_ygO6sYGYBw&usg=AFQjCNEWvTrE_D4yo-A1qgSGXv926f_8wQ

Hi,

May I know what is the use of residual plot in analysis of DOE ? 

@Goi 

Follow the link to get the answer of your question on residual plot 

http://www.itl.nist.gov/div898/handbook/pri/section2/pri24.htm