Working Paper: NBER ID: w7558
Authors: Austan Goolsbee
Abstract: Conventional estimates of the impact of taxes on investment may be seriously biased by measurement error in the cost of capital. The existence and size of such error, however, has not been documented. Using panel data on different types of capital equipment, this paper provides direct evidence of measurement error in the tax component of the cost of capital, accounting for about 20 percent of the tax term's variance. Correcting for the error with IV estimation shows that taxes significantly affect both prices and investment and that conventional results may be off by as much as a factor of four.
Keywords: measurement error; cost of capital; tax policy; investment
JEL Codes: E62; C23
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Conventional regression analysis (C29) | Small and statistically insignificant coefficient for the tax cost of capital (H29) |
| Measurement error in the tax term (H20) | Biased estimates of the tax component of the cost of capital (H32) |
| Measurement error in the tax term (H20) | Understated impact of taxes on investment (H32) |
| Tax policy (H29) | Investment (G31) |
| Tax policy (H29) | Prices (D49) |
| Measurement error (C20) | Downward bias in first differenced regressions (C22) |
| Measurement error (C20) | Underestimated true effects of tax policy (H31) |
| Measurement error (C20) | Conventional results off by a factor of ten (C51) |