. 2019 Dec 1;16(23):4832. doi: 10.3390/ijerph16234832

Table 4.

Differential responsiveness of cigarettes per day (CPD) to cigarette affordability.

Variable	Model 5a Coef. (S.E.)	Model 5b Coef. (S.E.)	Model 5c Coef. (S.E.)	Model 5d Coef. (S.E.)	Model 5e Coef. (S.E.)	Model 5f Coef. (S.E.)	Model 5g Coef. (S.E.)
$\ln (R I P)$	−0.099 ***	−0.170 ***	0.069	−0.207 ***	−0.163 ***	−0.193 ***	−0.185 ***
$\ln (R I P)$	(0.023)	(0.017)	(0.102)	(0.043)	(0.035)	(0.017)	(0.034)
Interaction terms
$\ln (R I P) \times A g e \geq 60$	−0.126 ***
$\ln (R I P) \times A g e \geq 60$	(0.029)
$\ln (R I P) \times F e m a l e$		0.046
$\ln (R I P) \times F e m a l e$		(0.043)
$\ln (R I P) \times P r i m a r y a n d b e l o w$			−0.269 ***
$\ln (R I P) \times P r i m a r y a n d b e l o w$			(0.104)
$\ln (R I P) \times M i d d l e a n d h i g h s c h o o l$			−0.193 *
$\ln (R I P) \times M i d d l e a n d h i g h s c h o o l$			(0.105)
$\ln (R I P) \times M a r r i e d$				0.048
$\ln (R I P) \times M a r r i e d$				(0.046)
$\ln (R I P) \times N o r t h e a s t r e g i o n$					0.093 *
$\ln (R I P) \times N o r t h e a s t r e g i o n$					(0.056)
$\ln (R I P) \times C e n t r a l r e g i o n$					−0.012
$\ln (R I P) \times C e n t r a l r e g i o n$					(0.042)
$\ln (R I P) \times W e s t e r n r e g i o n$					−0.017
$\ln (R I P) \times W e s t e r n r e g i o n$					(0.043)
$\ln (R I P) \times U r b a n$						0.064 **
$\ln (R I P) \times U r b a n$						(0.032)
$\ln (R I P) \times T i e r I$							−0.291 ***
$\ln (R I P) \times T i e r I$							(0.109)
$\ln (R I P) \times T i e r II$							0.022
$\ln (R I P) \times T i e r II$							(0.196)
ln(RIP) × Tier IV							0.023
ln(RIP) × Tier IV							(0.040)
ln(RIP) × Tier V							0.074 *
ln(RIP) × Tier V							(0.042)
Other variables	Control	Control	Control	Control	Control	Control	Control
Wald $χ^{2}$	439.94	396.19	410.22	395.51	412.75	442.23	413.23
Number of observations	N = 6652
Number of groups	N = 5077

Note: (1) The statistics reported are the coefficients of independent variables with robust standard errors in parenthesis. (2) ***, ** and * indicate statistical significance at the 1%, 5% and 10% level, respectively. (3) The results for other independent variables in regression are not included in the table due to word limit. Such variables include age group (Age ≥ 60), gender (female), education level (primary and below, middle and high school), marital status (married), economic regions (Northeast region, Central region and Western region), residential zone (urban), cigarette price tiers (Tier I, II, IV, V) and survey wave (wave 3). (4) Results were estimated by Equation (4).