Do excise tax hikes cause adult smoking rates to drop?


Antismoking groups always justify proposed excise tax increases, in part, by promising higher prices will reduce adult smoking rates.  The purpose of this report is to obtain cigarette excise tax rates for each state for 2005, and compare these to adult smoking rates for each state in 2005 to determine if a relationship exists between cigarette prices and adult smoking rates. Vassarstats is an online regression program designed to determine if any statistical relationship exists between two variables. http://faculty.vassar.edu/lowry/corr_stats.html

 

I obtained the state excise tax rates for 2005 from The Tax Burden on Tobacco, vol. 40, 2005.

I obtained each state’s adult smoking rate for 2005 from the U.S. Centers for Disease Control at
http://apps.nccd.cdc.gov/brfss/list.asp?cat=TU&yr=2005&qkey=4396&state=All

 

The vassarstats program analyzes data pairs and calculates, among other results the Pearson product-moment correlation and the coefficient of determination which are described in more detail below.  What my analysis found, is that there is only a 35% chance that states’ ( this is the ‘r’ variable reported below) high excise tax rates cause low adult smoking rates. EG: there is an 65% chance that adult smoking rates are controlled by other variables.  As can also be seen below, the r-squared was .12 which means there is an 88% chance adult smoking rates are not related to excise tax rates.

 

The Measurement of Linear Correlation  for a more detailed description, please visit
http://faculty.vassar.edu/lowry/webtext.html
According to this statistics website,

 “The primary measure of linear correlation is the Pearson product-moment correlation coefficient, symbolized by the lower-case Roman letter r, which ranges in value from r=+1.0 for a perfect positive correlation to r=—1.0 for a perfect negative correlation. The midpoint of its range, r=0.0, corresponds to a complete absence of correlation. Values falling between r=0.0 and r=+1.0 represent varying degrees of positive correlation, while those falling between r=0.0 and r=—1.0 represent varying degrees of negative correlation.

 

A closely related companion measure of linear correlation is the coefficient of determination, symbolized as r2, which is simply the square of the correlation coefficient. The coefficient of determination can have only positive values ranging from r2=+1.0 for a perfect correlation (positive or negative) down to r2=0.0 for a complete absence of correlation.”



 

VassarStats Printable Report
Linear correlation and Regression
Tue May 16 11:44:24 CDT 2006

 

Data SummaryT

 

r

r2

Slope

Y
Intercept

Std. Err. of
Estimate

-0.349

0.122

-0.067

2.3207

0.5661

 

0.95 and 0.99 Confidence Intervals of rho

Lower Limit

Upper Limit

0.95

-0.569

-0.082

0.99

-0.626

0.007



STATES

adult smoking rate 2005

excise tax 2005

AL
AK
AZ
AR
CA
CO
CT
DE
DC
FL
GA
HI
ID
IL
IN
IA
KS
KY
LA
ME
MD
MA
MI
MN
MS
MO
MT
NE
NV
NH
NJ
NM
NY
NC
ND
OH
OK
OR
PA
RI
SC
SD
TN
TX
UT
VT
VA
WA
WV
WI
WY

24.8
24.9
20.2
23.5
15.2
19.8
16.5
20.6
20.0
21.7
22.1
17.0
17.9
19.9
27.3
20.4
17.8
28.7
22.6
20.8
18.9
18.1
22.0
20.0
23.6
23.4
19.2
21.3
23.1
20.4
18.0
21.5
20.5
22.6
20.1
22.3
25.1
18.5
23.6
19.8
22.5
19.8
26.7
20.0
11.5
19.3
20.6
17.6
26.7
20.7
21.3

.452
1.60
1.18
.59
.87
.84
1.51
.55
1.00
.339
.37
1.40
.57
.96
.555
.36
.79
.3
.36
2.00
1.00
1.51
2.00
1.485
.18
.17
1.70
.64
.80
.80
2.40
.91
1.50
.30
.44
1.25
1.03
1.18
1.35
2.46
.07
.53
.20
.41
.695
1.19
.30
2.025
.55
.77
.60





Plans to Increase State Revenue Could Go Up In Smoke
March 2004. by Amy K. Frantz
Read

Heartland Institute
Policy Bot
Read

Keep Tobacco Money Out Of Our Hospitals
Proposition 86 - By John R. Graham

American Journal of Public Health finds Price Hikes do not cut Adult Smoking

HOME