Using PIHS data, the study first calculates the difference in socioeconomic characteristics of treated or remittances beneficiary households (RBH) and control or remittances non-beneficiary households (NRBH) ignoring endogeneity and observable differences.
This study assumes that households which receive foreign remittance are treated or remittance beneficiary households (RBH) and the control group which does not receive remittance income are called non-treated or remittance non-beneficiary households (NRBH).
First, the naive approach to calculate the mean difference in socio-economic indicators using full sample of all RBH and NRBH ignoring selection bias and counter factual.
In this approach, the impact is measured using all households-- RBH and NRBH ignoring selection bias and counter factual.
(1) It overcomes the problem of multi dimensionalities and develops an index of propensity score P(X) for the treated (RBH) and control (NRBH) groups to match.
The probability depends on households and community based characteristics of RBH and NRBH.
The second concern in this approach is to choose treatment (RBH) and comparison or control group (NRBH).
It defines the area with the common range dropping all observations from RBH and NRBH whose P values are beyond the range defined in Equation 3.
Third, the exact matching approach in which each RBH is paired with NRBH has been used which minimises the difference of their PSM within the common support area and drops the rest of the households.
The outcomes corresponding to [D.sub.REM] = I and [D.sub.REM] 0 are denoted by (YI, Y0), respectively, and X is the vector of variables that are time invariant characteristics of the treated unit RBH. The assumption underlying the matching estimator is that all relevant differences between the two groups are captured by their observables X.
These initiatives can be chronologically described as: STEP's in 1984, EDC's in 1986-87, TBI's in 2000-2001 and RBH's in 2005.
 Khanduja, Dinesh & Sahib Sartaj, 2006, Entrepreneurial Ambience of Indo-British Technology Partnership: A Case Study of RBH's, proceedings of EuroMot 2006, Birmingham, UK.