Skip to main content

Table 2 Threshold model estimates

From: The effects of a rise in cigarette price on cigarette consumption, tobacco taxation revenues, and of smoking-related deaths in 28 EU countries-- applying threshold regression modelling

  Dependent variable: (lnC* it)
  Single-income threshold model Double-income threshold model
Independent variables
 ln P* it
  Regime1(GNIitUS$5418) −1.315 b (−0.737,-1.893) −1.227 b(−0.667,-1.787)
  Regime2(GNIit > US$5418) −0.638 b (−0.427,-0.849)  
  Regime2(US$5418 < GNIitUS$8385)   −0.829 b (−0.628,-1.030)
  Regime3(GNIit > US$8385)   −0.503 b (−0.291,-0.715)
 lnGNI* it
  Regime1(GNIitUS$5418) 0.332 b (0.596,0.069) 0.282 b (0.530,0.033)
  Regime2(GNIit > US$5418) 0.596 b (0.827, 0.366)  
  Regime2(US$5418 < GNIitUS$8385)   0.423 b (0.685,0.261)
  Regime3(GNIit > US$8385)   0.576 b (0.787,0.336)
 MP* it −0.021 b (−0.006,-0.035) −0.017 b (−0.003,-0.032)
 Rural* it 1.637 b (3.006,0.269) 1.616 b (2.830,0.402)
 lnNeiP* it 0.031 (0.184,-0.122) −0.057 (0.083,-0.197)
Observations 252 252
Number of country 28 28
Sum of square error (SSE) 0.355 0.311
Test for one threshold (income threshold) γ1 43.66 a (5418)  
Test for two thresholds (income threshold) γ2   36.61 a (6494,32,040)
  1. Regime 1 countries: Bulgaria, Romania
  2. Regime 2 countries: Latvia, Poland
  3. Regime 3 countries: Austria, Belgium, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, France, Germany, Greece, Hungary, Ireland, Italy, Lithuania, Luxembourg, Malta, Netherlands, Portugal, Slovakia, Slovenia, Spain, Sweden, United Kingdom
  4. P * legal cigarette price, GNI * per capita national income, Rural * rural population %, MP * the number of MPOWER measures at the highest level of achievement. Confidence intervals are shown in parentheses
  5. aStatistically significant at 10% level
  6. bStatistically significant at 5% level