. 2016 Feb 23;127(600):445–494. doi: 10.1111/ecoj.12282

Table 2.

Choice of Practice: Marginal Utility of Quality, Distance, and Practice Characteristics

	Co‐efficient
QOF 2006/7 total points	0.00222***
QOF 2006/7 total points	(0.00016)
Distance	−0.7512***
Distance	(0.0163)
Practice in different PCT	−0.881***
Practice in different PCT	(0.044)
Average GP age (months)	−0.00214***
Average GP age (months)	(0.00014)
Percentage of female GPs	0.00239***
Percentage of female GPs	(0.00034)
Percentage of non‐European qualified GPs	−0.00527***
Percentage of non‐European qualified GPs	(0.00028)
Opted out of 24 hours obligation	0.160***
Opted out of 24 hours obligation	(0.037)
PMS contract	0.148***
PMS contract	(0.033)
BIC	11,597,725
McFadden R²	0.3991
N LSOA	2,870
N practices	973
N patients	3,291,581
MRS distance for quality	0.00296***
MRS distance for quality	(0.00022)

Conditional logit model of choice of practice by patients aged 25 and over. Model also contained a dummy for missing PMS status. The distance coefficient is ${\hat{β}}_{d} + 2 {\hat{β}}_{d^{2}} \bar{d} + 3 {\hat{β}}_{d^{3}} \bar{d^{2}}$ where $\bar{d}$ and $\bar{d^{2}}$ are computed as the mean of the LSOA centroid to practice distance in km and the squared distance for the whole sample. MRS is the coefficient on quality divided by the distance coefficient. Standard errors clustered at LSOA level are in parentheses. *p < 0.05, **p < 0.01, ***p < 0.001.