Table 3.

Regression results from mixed logit model

	No interaction	Interacted with Tier 1	Interacted with Tier 2	Interacted with Tier 3
Random Coefficients
Cigarette tier price - mean	−0.314*** (0.049)
Cigarette tier price – std. dev.	0.221*** (0.031)
Constant – mean		4.565*** (1.006)	5.101*** (0.777)	2.558*** (0. 631)
Constant – std. dev.		1.119*** (0.256)	1.159*** (0.129)	1.524*** (0.105)
Fixed Coefficients
Male		0.961 (0.614)	0.803** (0.340)	0.760*** (0.240)
Age		−0.087*** (0.009)	−0.075*** (0.008)	−0.033*** (0.007)
Income: < ¥1,000		−3.644*** (0.385)	− −2.692*** (0.308)	−1.009*** (0.291)
Income: ¥1,000 –2,999		−2.509*** (0.310)	−1.544*** (0.267)	−0.512** (0.262)
Income: ¥3,000 –4,999		−1.265*** (0.324)	−0.648** (0.286)	−0.386 (0.281)
Income: ≥ ¥5,000 (omitted)
Education: Primary school and below (omitted)
Education: Middle school		0.496 (0.340)	0.499** (0.243)	0.678*** (0.212)
Education: High school		1.337*** (0.330)	1.204*** (0.254)	0.899*** (0.225)
Education: Beyond high school		2.505*** (0.380)	2.039*** (0.310)	1.277*** (0.260)
Cigarette consumption at Wave 1		−0.011 (0.009)	−0.016** (0.008)	−0.005 (0.007)
Wave fixed effects	Yes
City fixed effects	Yes
Number of persons	3,477
Number of person-years	8,552
Number of observations	34,208

Note: Robust standard errors, in parentheses, are clustered at the person level and weighted for survey sampling. The omitted category for categorical variables is: income above ¥5,000, primary education and below, Wave 1, and Beijing. The model includes tier-specific constants. “Interacted with Tier x” means the coefficient is on the interaction term between the variable listed in the first column with Tier x (x=1, 2, 3, 4), as mixed logit model allows variables that vary over choice alternatives which is similar to conditional logit.

Significance:

^*p < 0.10

^**p < 0.05

^***p < 0.01.