Please i would like to apply DEA model with weight restrictions to a sample of universities, how could i know the relation between weights attributed to input/output variables that i will introduce. Is it necessary to apply bootstrap technique then?
the weights are seen as virtual multipliers (its value is always positive) and they are associated to the multiple outputs and multiple inputs. The DEAP program estimate them per si.
There are various methods to apply weight restrictions in a DEA model. Literature is available. I have applied one method in the transport sector. If you want I can mail you a copy of that paper.
The use of weight restrictions is problematic if you do not know of the meaning of weights - as is the case mostly. Usually, the weights are used to take into account the preferences of the use, but unfortunately the weights mostly describes very weakly the the importance of various factors. Please, find below our quite new book in which we have reviewed various ways to incorporate preference information into the DEA analysis.
Joro, Tarja and Korhonen, Pekka (2015): Extension of Data Envelopment Analysis with Preference Information- Value Efficiency, Springer
I have a Springer book, too, which is about Efficiency Measures in the Agricultural Sector: With Applications. edit by Armando Mendes,Emiliana Silva,Jorge Santos (2013). The link is: https://books.google.pt/books?id=uuIlcpZ96SMC&pg=PR9&lpg=PR9&dq=Efficiency+measures+Emiliana+Silva&source=bl&ots=62WzKUJs5k&sig=vRQx49KEuBXW64YZe2H0BI2VaFM&hl=pt-PT&sa=X&ved=0ahUKEwiim8ywmczJAhWFChoKHQN-BvwQ6AEIKDAB#v=onepage&q=Efficiency%20measures%20Emiliana%20Silva&f=false