Following Dehejia and Wahba (1999, 2002), this paper uses the stratification matching method.
Tables 3 and 4 show the estimates for the average treatment effect on the treated (ATET) based on the propensity score and the stratification matching method.
And, thirdly, we have applied stratification matching approach: The main idea of this method is to divide the common support region into intervals (or "blocks") and then calculate the average treatment effect on treated for each interval.
Two alternative methods are explored in the robustness exercises, kernel and stratification matching.
Table 5 reports the cumulative GBL and LBG effects estimated when using Kernel and Stratification matching techniques.
Kernel and stratification matching refer to alternative techniques for constructing the control group (see the main text for more details).
Table 4 presents the estimated effects of the adaptation options on the household food security by nearest neighbor matching (NNM), Kernel-based matching (KBM), and stratification matching methods.
After calculating the propensity scores, the nearest neighbor matching (NNM) method, Kernel Matching, Stratification Matching, and Radius Matching were employed to match the control group of individuals (non-adapters) to the treated group (adapters) based on similar propensity scores.
There are a variety of approaches to adjust measured confounders to create comparison groups of patients with similar characteristics, such as propensity scores, stratification, matching, and regression (Austin 2011; Stuart 2010; Glass et al. 2013).
Fig. 5 Propensity score Table 4 Impact of adaptation Outcome indicators Matching algorisms Matched samples Impact (ATT Standardd error t test Affected Non-affected Food security Nearest neighbor matching 359 27 2634.93 311.94 8.447 Kernel matching 359 80 2660.163 267.603 9.941 Stratification matching 359 80 2825.114 306.477 9.218 Radius matching 199 76 0.331 0.082 4.034.
