Do newly marketed generic medicines expand markets using descriptive time series analysis and mixed logit models? Korea as an exemplar and its implications

Table 4 Mixed logit model results on factors contributing to generic atorvastatin prescription

Parameter		Estimates	SE	Odds Ratio [95 % CI]
Intercept		– 3.059***	0.356	0.05 [0.03: 0.07]
Sex (ref = female)	Male	– 0.080	0.131	0.92 [0.71: 1.19]
Age (ref = < 50)	50 ~ 59	– 0.189	0.164	0.83 [0.60: 1.15]
	60 ~ 69	0.351*	0.172	1.42 [1.01: 2.00]
	70+	0.279	0.184	1.32 [0.92: 1.91]
Education (ref: < = primary)	Middle school	0.165	0.168	1.18 [0.85: 1.64]
	High school	0.002	0.201	1.00 [0.68: 1.49]
	College +	0.233	0.199	1.26 [0.86: 1.87]
Insurance type (ref = medical aid)	NHI	– 0.027	0.189	0.97 [0.53: 1.77]
Number of comorbidities		– 0.044***	0.010	0.96 [0.94: 0.98]
Newly treated group (ref = previously treated)		0.951***	0.003	2.59 [2.07: 3.23]
Type of Hospital (ref = teaching hospitals)	General hospitals	1.378***	0.213	3.97 [2.60: 6.06]
	Hospitals	2.223***	0.229	9.23 [5.86: 14.56]
	Clinics	2.283***	0.201	9.81 [6.58: 14.61]
Specialty (ref = others)	Intemalist	– 0.057	0.076	0.95 [0.81: 1.10]
AR(1)		0.729***	0.008
Residual		1.021***	0.029
–2 log Likelihood		25525.50

ISSN: 1472-6963