A binary logistic regression analysis was performed to predict 1-year survival outcomes for male patients who had initially survived a first heart attack. The outcome variable death was coded 0=alive and 1=dead. One predictor variable was included in the model: this was a response to a survey question about whether or not each patient owned a dog. Interpret the exp(B) of the independent variable dog owner in the analysis output below:

Binary Logistic Regression analysis: prediction of death 1 year after heart attack from dog ownership

						95% CI for exp(B)
	B	S.E.	df	Sig.	Exp(B)	Lower	Upper
No Dog owner	1.879	0.693	1	0.007	6.548	1.684	25.456
Constant	-2.813	0.594	1	0.000	0.60