UPC counts and availability share of cigarillos by flavour category, prepolicy and postpolicy in Providence, RI and an ROS comparison area, January 2012–January 2016
Postestimation summary results* | ||||||||
Geography | Coefficient(s)† | Number of unique UPCs (Newey-West standard error) | Share of unique UPCs in percentage points (Newey-West standard error) | |||||
Total | Concept | Explicit | Tobacco | Concept | Explicit | Tobacco | ||
Prepolicy availability | ||||||||
Providence | β0 + β2 | 96.54 | 9.12 | 50.49 | 36.68 | 9.44% | 52.41% | 37.88% |
(1.83) | (0.51) | (1.47) | (1.84) | (0.49) | (1.70) | (1.52) | ||
ROS | β0 | 137.94 | 13.30 | 75.59 | 48.50 | 9.68% | 54.78% | 35.16% |
(2.50) | (1.51) | (1.64) | (1.25) | (0.99) | (1.45) | (0.57) | ||
Postpolicy availability | ||||||||
Providence | β0 + β2 + β4 + β6 | 86.26 | 21.95 | 22.45 | 41.80 | 27.32% | 21.46% | 51.19% |
(4.51) | (1.71) | (3.28) | (4.18) | (1.77) | (3.63) | (3.62) | ||
ROS | β0+ β4 | 156.31 | 20.05 | 78.73 | 57.24 | 12.67% | 50.74% | 36.51% |
(5.80) | (2.66) | (2.85) | (2.60) | (1.67) | (2.08) | (1.00) | ||
Net policy effect on availability‡ | β6 | −28.64 | 6.08 | −31.18 | −3.62 | 14.88 | −26.90 | 11.96 |
(5.83) | (2.31) | (3.06) | (3.47) | (1.91) | (2.61) | (2.65) | ||
Total postpolicy difference on availability§ | β2 + β6 | −70.04 | 1.89 | −56.28 | −15.44 | 14.65 | −29.27 | 14.68 |
(7.34) | (3.16) | (4.35) | (4.93) | (2.43) | (4.18) | (3.75) | ||
Prepolicy trend | ||||||||
Providence | β1 + β3 | −0.22 | −0.04 | −0.20 | 0.03 | −0.02 | −0.10 | 0.13 |
(0.09) | (0.01) | (0.06) | (0.08) | (0.01) | (0.07) | (0.07) | ||
ROS | β1 | −0.15 | −0.02 | −0.09 | −0.05 | −0.003 | −0.008 | 0.006 |
(0.09) | (0.05) | (0.05) | (0.04) | (0.03) | (0.04) | (0.02) | ||
Postpolicy trend | ||||||||
Providence | β1 + β3 + β5 + β7 | −0.02 | −0.01 | −0.0005 | −0.02 | 0.001 | 0.003 | −0.01 |
(0.02) | (0.01) | (0.01) | (0.01) | (0.01) | (0.01) | (0.01) | ||
ROS | β1 + β5 | −0.20 | −0.003 | −0.13 | −0.06 | 0.02 | −0.03 | 0.007 |
(0.03) | (0.01) | (0.01) | (0.02) | (0.005) | (0.006) | (0.004) | ||
Net policy effect on trend** | β7 | 0.24 | 0.02 | 0.24 | −0.03 | −0.0004 | 0.13 | −0.14 |
(0.14) | (0.05) | (0.08) | (0.09) | (0.04) | (0.08) | (0.07) | ||
Total postpolicy difference in trend†† | β3 + β7 | 0.18 | −0.003 | 0.13 | 0.05 | −0.02 | 0.04 | −0.02 |
(0.04) | (0.02) | (0.01) | (0.02) | (0.01) | (0.01) | (0.01) |
Trends in Providence and ROS were parallel in the prepolicy period (ie, data met the parallel trends assumption). ROS=rest of state (excludes Providence).
Bold=p<0.05; significance only indicated for net policy effect (difference-in-difference analysis) and total postpolicy difference rows.
*Number or share of unique UPCs = β0 + β1(Time Trend) + β2(Providence) + β3(Providence * Time Trend) +β4(Policy Indicator) + β5(Policy Indicator *Time Trend) + β6(Providence *Policy Indicator) +β7(Providence *Policy Indicator *Time Trend).
†Reference online supplemental table 1 for detailed regression results.
‡Change in the number or share (in percentage points) of unique UPCs associated with the policy in Providence relative to ROS.
§Total difference in the number or share (in percentage points) of unique UPCs between providence and ROS.
¶Trend is the average weekly change in the number or share (in percentage points) of UPCs; if statistically insignificant, the number or share of UPCs does not significantly change from week to week during the defined period.
**Change in the trend of the number or share (in percentage points) of unique UPCs associated with the policy in providence compared with the change in ROS
††Total difference between Providence and ROS in the average weekly change in the number or share (in percentage points) of unique UPCs in the post-policy period.
RI, Rhode Island ; ROS, rest of state ; UPC, universal product code .