Effects of a Safety Letter on Metoclopramide Use in Korea: An Interrupted Time-Series Analysis

Figures & data

Figure 1 Results of the interrupted time-series analysis with segmented regression method.

Table 1 Parameters from the Interrupted Time-Series Analysis of Utilization Patterns

Utilization Pattern	Intercept		TIME1		POLICY		TIME2
	β0 Estimates (SE)	p-value	β1 Estimates (SE)	p-value	β2 Estimates (SE)	p-value	β3 Estimates (SE)	p-value
Number of prescriptions per month	831,799 (39,296)	< 0.01	3435 (1988)	0.09	−531,543 (60,898)	< 0.01	−4705 (4101)	0.26
Average administration period per prescription per month (days)	4.58 (0.08)	< 0.01	0.01 (0.003)	0.09	−1.32 (0.11)	< 0.01	−0.05 (0.01)	< 0.01
Average dose per prescription per month (mg)	19.03 (0.13)	< 0.01	−0.02 (0.007)	< 0.01	−1.88 (0.19)	< 0.01	−0.01 (0.01)	0.63

Notes: Intercept is a value of utilization pattern in January 2011. TIME1 is a continuous variable that takes the value of “1” for January 2011 and increases by one per month. TIME2 starts at 0, takes the value of “1” for October 2013, and increases by one per month. POLICY is a dummy variable representing the publication of the safety letter in October 2013.

Abbreviation: SE, standard deviation.