The elasticity of taxable income over the 1980s and 1990s.

by Giertz, Seth H.

National Tax Journal • Dec, 2007 •

(0.015) (0.133) Observations 218,771 193,809 Notes: Estimates are based on Continuous Work History Survey data for 1979 to 2001. Estimates are from 2SLS regressions. The income range is $10,000 and above. Regressions are weighted by income. All regressions include dummies for marital status and dummies for each base year. Robust standard errors (clustered by individual) are in parentheses. TABLE 6 THE EFFECT OF EXCLUDING THE MOST INFLUENTIAL OBSERVATIONS OF INCOME-WEIGHTED ESTIMATES FOR THE 1980s (a) Dropped Observations Sample Size Estimated ETI 0 54,136 0.373 10 54,126 0.235 25 54,111 0.174 50 54,086 0.116 100 54,036 0.084 Notes: Estimates are based on Continuous Work History Survey data for years 1979 to 1990. (a) Estimates are based on the specification with a 10-piece spline. Observations are dropped based on the size of their impact on the estimated ETI and as measured by a dfbeta test. TABLE 7 FULL SOI TAXABLE AND BROAD-INCOME ELASTICITIES FOR THE 1980s

Base-Year Income

No Income Controls Controls

Broad Taxable Broad Taxable

Income Income Income Income In([mtr.sub.t+3]/[mtr.sub.t]) -0.033 -0.001 0.309 0.648

(0.036) (0.059) (0.048) (0.081) Married 0.079 0.011 0.118 0.069

(0.008) (0.011) (0.008) (0.012) Single 0.014 -0.012 0.023 0.007

(0.008) (0.012) (0.008) (0.012) Age 0.045 0.072 0.056 0.086

(0.003) (0.004) (0.004) (0.005) Age Squared/10 -0.011 -0.017 -0.013 -0.019

-0.001 -0.001 -0.001 -0.001 Age Cubed/100 0.008 0.011 0.009 0.012

(0.000) (0.001) (0.001) (0.001) sex 0.007 0.007 0.006 0.004

(0.001) (0.001) (0.001) (0.001) itemzer_base -0.004 -0.039 -0.055 -0.117

(0.004) (0.006) (0.005) (0.008) ln(income) -0.091 -0.145

(0.005) (0.008) decile 1 decile 2 decile 3 decile 4 decile 5 decile 6 decile 7 decile 8 decile 9 decile 10 Constant -0.73 -1.12 0.049 0.111

(0.070)

(0.054) (0.073) (0.098) Observations 248,940 250,140 248,940 250,140

Spline Income

Controls

Broad Taxable

Income Income In([mtr.sub.t+3]/[mtr.sub.t]) 0.210 0.425

(0.048) (0.081) Married 0.140 0.096

(0.009) (0.012) Single 0.031 0.028

(0.008) (0.012) Age 0.065 0.10

(0.004) (0.005) Age Squared/10 -0.015 -0.022

-0.001 (0.001) Age Cubed/100 0.010 0.014

(0.001) (0.001) sex 0.005 0.003

(0.001) (0.001) itemzer_base -0.069 -0.126

(0.005) (0.008) ln(income) decile 1 -0.918 -0.61

(0.186) (0.016) decile 2 -0.219 -0.235

(0.017) (0.018) decile 3 -0.169 -0.213

(0.018) (0.025) decile 4 -0.123 -0.168

(0.022) (0.030) decile 5 -0.142 -0.176

(0.022) (0.033) decile 6 -0.041 -0.021

(0.027) (0.034) decile 7 -0.004 -0.069

(0.024) (0.031) decile 8 -0.033 0.006

(0.041) (0.054) decile 9 -0.066 -0.136

(0.054) (0.10) decile 10 -0.137 -0.131

(0.035) (0.069) Constant 7.738 4.119

(1.732) (0.157) Observations 248,940 250,140 Notes: Estimates are based on Statistics of Income data for years 1979 to 1990. Estimates are from 2SLS regressions. The income range is $10,000 and above. Regressions are weighted by the inverse of sampling probabilities and by income (see the third section). Robust standard errors (clustered by individual) are in parentheses. TABLE 8 FULL SOI TAXABLE AND BROAD-INCOME ELASTICITIES FOR THE 1990s

Base-Year Income

No Income Controls Controls

Broad Taxable Broad Taxable

Income Income Income Income ln([mtr.sub.t+3]/[mtr.sub.t]) 0.478 0.745 0.133 0.144

(0.044) (0.071) (0.038) (0.058) Married 0.091 0.013 0.139 0.082

(0.010) (0.011) (0.009) (0.010) Single 0.017 -0.024 0.029 0.002

(0.009) (0.011) (0.009) (0.010) Age 0.016 0.028 0.028 0.043

(0.006) (0.007) (0.006) (0.006) Age Squared/10 -0.006 -0.008 -0.007 -0.01

(0.001) (0.001) (0.001) (0.001) Age Cubed/100 0.004 0.006 0.005 0.006

(0.001) (0.001) (0.001) (0.001) sex 0.004 0.002 0.001 -0.002

(0.001) (0.001) (0.001) (0.001) itemzer_base 0.012 -0.023 -0.096 -0.127

(0.005) (0.005) (0.006) (0.006) ln(income) -0.107 -0.120