Dear Avishek
I want just to ask a question one of the recommendation to use DEA software is to avoid imbalances in the data set and comprise of a similar magnitude. in the exemple you took this rule is not respected, one way is to divide by the mean of each variable. I don’t know it for DEAP the preparation of data is required or not if yes I just want to know because i’d done the test why if the range of the amplitude of the variable is less than 1 the Sowtware don’t give results.
I am litlle bit lost.
Thanks by adavance for clarifications.
Nadjwa.

Hi Avishek,

I’m running a model with the following characteristics:
– 2 Outputs
– 9 Inputs
– 16 DMUS’s

The dataset is in the form of a panel spanning 12 years and all variables have been mean normalized for that particular year. I’m currently using Malmquist DEA method to get results on yearly frequency with VRS approach and Input Orientation. However, I am not getting any variation in efficiency for 9 DMU’s and all these 9 are coming out as efficient. Is there something I’m not doing right?