The effect of a mystery shopper scheme on prescribing behavior in primary care: Results from a field experiment

Health Economics Review

Table 16 Robustness of average intervention effects on physician prescribing, audit 2

	clustering 1	clustering 2	clustering 3	clustering 4
Panel A: Prescribing pattern
Antibiotics	0.630^***	0.630^***	0.630^***	0.630^***
	(0.069)	(0.197)	(0.151)	(0.180)
Other Rx	-1.481^***	-1.481^***	-1.481^***	-1.481^***
	(0.117)	(0.294)	(0.132)	(0.277)
OTC	1.551^***	1.551^***	1.551^***	1.551^***
	(0.080)	(0.269)	(0.117)	(0.295)
Alternatives	-2.418^***	-2.418^***	-2.418^***	-2.418^***
	(0.353)	(0.531)	(0.350)	(0.466)
Panel B: Average intervention effects
Average intervention effect	-0.214^**	-0.214^***	-0.214^**	-0.214^**
	(0.086)	(0.077)	(0.091)	(0.085)
Number of observations	752	752	752	752
Log-Likelihood	-175.4	-175.4	-175.4	-175.4
Pseudo R²	0.327	0.327	0.327	0.327

Other Rx: Other prescription drugs; OTC: Over-the-counter drugs; Alternatives: Alternative and nonpharmacological treatments. Estimated odds ratios are presented with standard errors in parentheses. The standard errors are adjusted for clustering on groups following four clustering criteria. Clustering 2 is applied in the models in the main paper
^* p<0.1, ^** p<0.05, ^*** p<0.01

ISSN: 2191-1991