Table 3

Results from probit regression model: the effect of magazine readership characteristics on the probability of a cigarette brand advertising in a magazine

Independent variable^3-151	Coefficient	Standard error
% Black youth readers	−0.957	0.728
δ ^3-150 (% Black youth readers)	4.389^3-160	1.808
% Young adult readers	3.688^3-160	1.224
δ ^3-150 (% Young adult readers)	−1.804	2.705
% Female readers	0.878^3-160	0.296
δ ^3-150 (% Female readers)	−0.849	0.704
% Hispanic readers	−1.903	2.587
δ ^3-150 (% Hispanic readers)	3.721	5.850
Total readers	40.778^3-160	14.754
δ ^3-150Total readers	3.066	33.893
% Smokers	−0.674	1.938
δ ^3-150 (% Smokers)	4.989	4.154
% Heavy smokers	−0.062	5.553
δ ^3-150 (% Heavy smokers)	13.555	13.074
% Menthol smokers	−2.919	4.024
δ ^3-150 (% Menthol smokers)	−3.602	9.253
Cost of ad	−905.855^3-150	548.269
δ ^3-150 Cost of ad	−1023.603	1254.493
Total expenditures	58.956^3-160	7.866
δ ^3-150Total expenditures	−17.063	35.559
Issues	−0.004	0.006
δ ^3-150Issues	0.024^3-150	0.014
Income	−0.105	0.284
δ ^3-150 Income	−1.761^3-160	0.709
Constant	1.453	1.773
δ	−0.355	0.725

↵3-151 δ is 0 for non-black youth cigarette brands and 1 for black youth cigarette brands.
↵3-150 Coefficient is significant at the 90% level (p < 0.10).
↵3-160 Coefficient is significant at the 95% level (p < 0.05).