################
##### Notes:
################
### Source ----------> Input ----------> Model ----------> Policy Estimates (output)
### (_so) (_in) (_mo) (_pe)
### values functions functions values
### & values & values
# - call_sources_f- tax_elasticity_in_f - tax_revenue_mo_f - ten_year_revenue_pe
# - policy_f - est_billionares_in_f - total_rev_mo_f - ten_year_top_tax_pe
# - ten_years_mo_f - total_rev_pe
### arguments in functions should used "_var" and functions should "_f"
# DESCRIBE FUNCTIONS STRUCTURE
# - inputs: list
# - outputs: list
#### function:
#sample_function_f <- function(){
##########################################
##########################################
#
# ...
#
##########################################
##########################################
# return( ) # A list with all (most?) the elements
# # generated inside the function
#}
#invisible( list2env(policy_f(),.GlobalEnv) ) The wealth tax applies to net worth (sum of all assets net of debts) above $50 million, and obeys the following structure:
| Bracket (millions of $) | Marginal Tax Rate (%) |
|---|---|
| 10 | 0 |
| 25 | 0 |
| 50 | 2 |
| 100 | 2 |
| 250 | 2 |
| 500 | 2 |
| 1000 | 3 |
Household net worth above $50 million would be taxed at 2%. Any wealth over $1 billion would be taxed an additional 1% (a billionaire surtax).
To calculate the revenue from this wealth tax, the extent of wealth tax evasion/avoidance is estimated based on recent research showing that it depends crucially on loopholes and enforcement. The tax-avoidance elasticity is computed as the average elasticity from four studies. The table lists the four studies and the avoidance/evasion response to a 1% wealth tax.
| Authors | Year | paper | Publisher | Avoidance/evasion response |
|---|---|---|---|---|
| Seim, David | 2017 | “Behavioral Responses to an Annual Wealth Tax: Evidence from Sweden” | American Economic Journal: Economic Policy, 9(4), 395-421 | 0.5 |
| Jakobsen, Kristian, Katrine Jakobsen, Henrik Kleven and Gabriel Zucman. | 2018 | “Wealth Accumulation and Wealth Taxation: Theory and Evidence from Denmark” | NBER working paper No. 24371 | 0.5 |
| Londono-Velez, Juliana and Javier Avila. | 2018 | “Can Wealth Taxation Work in Developing Countries? Quasi-Experimental Evidence from Colombia” | UC Berkeley working paper | 2-3 |
| Brülhart, Marius, Jonathan Gruber, Matthias Krapf, and Kurt Schmidheiny. | 2016 | “Taxing Wealth: Evidence from Switzerland” | NBER working paper No. 22376, 2016 | 23-34 |
Seim (2017) and Jakobsen et al. (2018) obtain small avoidance/evasion responses in the case of Sweden and Denmark, two countries with systematic third party reporting of wealth: a 1% wealth tax reduces reported wealth by less than 1%. Londono-Velez and Avila (2018) show medium avoidance/evasion responses in the case of Colombia where enforcement is not as strong: a 1% wealth tax reduces reported wealth by about 2-3%. The study on Switzerland by Brülhart et al. (2016) is an outlier that finds very large responses to wealth taxation in Switzerland: a 1% wealth tax lowers reported wealth by 23-34%. This extremely large estimate is extrapolated from very small variations in wealth tax rates over time and across Swiss cantons and hence is not as compellingly identified as the other estimates based on large variations in the wealth tax rate. Switzerland has no systematic third party reporting of assets which can also make tax evasion responses larger than in Scandinavia.
The final 16% tax avoidance/evasion response to a 2% wealth tax was computed as and average across these four studies (2%*(0.5+0.5+2.5+28.5)/4).
Three data sources were used in this analysis:
From each data set three variable were extracted: networth that contain information on wealth, weights represents the number of households that each observation represents and data which tracks the data of origin.
The following transformations were applied to the data:
The total household net worth projection is $94 trillion for 2019 (the SCF records a total household net worth of $87 trillion in 2016).
In this section, the microdata generated before (wealth.dta) is aggregated into percentiles and fractions of a percentile. The final analytic file contains: percentile or fraction of percentile (gperc), number of households in that group (nb), lowest level of wealth in that group (thres), and average level of wealth in that group (avg)
To compute the relevant universe the evasion parameter of 16% is applied to both the threshold and the average wealth of each percentile (and fraction of a percentile)
In 2019, there would be around 63000 households liable for the wealth tax (78000 before accounting for avoidance). This would be less than 0.05% of the 130 million US households in 2019.
The 62616 households with assests totaling over $50 million would have a total taxable wealth (above the $50million) of $8.9 trillion, i.e. approximately 9% of the $94 trillion population-wide, total household net worth.
The 963 households with assests totaling over $1 billion dollars would have a total taxable wealth (above the $1billion) of $2.2 trillion, i.e. approximately 2% of the $94 trillion population-wide, total household net worth.
Starting with the $8.9 trillion tax base of wealth above $50 million ($11.4 with no avoidance), a 2% tax would raise $178 billion in 2019. The billionaire surtax is estimated to apply to a base of $2.2 trillion ($2.8 with no avoidance) from about 1000 billionaire families (1300 with no avoidance). Thus the billionaire surtax would raise $22 billion in 2019. The combination of the 2% tax above $50 million and the billionaire surtax would raise 178.1 + 21.6 = 199.8 billion in 2019.
To project tax revenues over a 10-year horizon, we assume that nominal taxable wealth would grow at the same pace as the economy, or 5.5% per year as in standard projections of the Congressional Budget Office or the Joint Committee on Taxation. This growth is decomposed into 2.5% price, 1% population growth, and 2% of real growth per capita. This implies that tax revenue over 10 years 2019-2028 is about 12.9 times the revenue raised in 20193. This uniform growth assumption is conservative as the wealth of the rich has grown substantially faster than average in recent decades. The estimates by Saez and Zucman4 show that, from 1980 to 2016, real wealth of the top 0.1% has grown at 5.3% per year on average, which is 2.8 points above the average real wealth growth of 2.5% per year. Average real wealth of the Forbes 400 has grown even faster at 7% per year, 4.5 points above the average. The historical gap in growth rates of top wealth vs. average wealth is larger than the proposed wealth tax. Therefore, even with the wealth tax, it is likely that top wealth would continue to grow at least as fast as the average.
This 10-year projection implies that revenue raised by the progressive wealth tax would be 12.9 * 199.8 = $2572 billion, rounded to $2.6 trillion. Out of this $2.6 trillion, the billionaire surtax would raise 21.6 * 12.9 = $278.7 billion, rounded to $0.3 trillion.
It is important to emphasize that our computations assume that the wealth tax base is comprehensive with no major asset classes exempt from wealth taxation. Introducing exemptions for specific asset classes would reduce the revenue estimates both mechanically and dynamically as wealthy individuals would shift their wealth into tax exempt assets. Because Senator Warren’s proposal does not include any large exemptions, we do not believe our revenue estimate needs to be adjusted.
# test to run from the beginning (only functions)
rm(list = ls()[!(ls() %in% ls(pattern = "_f\\b"))])
invisible( list2env(call_sources_f(), .GlobalEnv) )
invisible( list2env(policy_f(), .GlobalEnv) )
invisible( list2env(tax_elasticity_in_f(), .GlobalEnv) )
invisible( list2env(tax_revenue_mo_f(), .GlobalEnv) )
invisible( list2env(total_rev_mo_f(), .GlobalEnv) )
invisible( list2env(ten_years_mo_f(),.GlobalEnv) )
sapply(ls(pattern = "_pe\\b"), get)The figure below illustrates the distribution of wealth tax across the population:
Tax revenue from wealth tax over 10 year: $2.6 trillion
Percentage of US households paying the wealth tax: 0.05%
Click here/ADD APP URL to explore different policy proposals and to see how the assumptions of the analysis affect the results.
There are two ways to edit the code behind this document:
1 - Download/Clone this repository into your computer. You will need to install R and RStudio.
2 - Go to this link and reproduce all the results in a computing enviroment (supported by project binder). You will not need to install anything in your computer.
One of the key motivations for introducing a progressive wealth tax is to curb the growing concentration of wealth. The top 0.1% wealth share has increased dramatically from about 7% in the late 1970s to around 20% in recent years. Conversely, the wealth share of the bottom 90% of families has declined from about 35% in the late 1970s to about 25% today. This fall has been primarily the consequence of increased debt for the bottom 90% (through mortgage refinance, consumer credit, and student loans). As a result, the top 0.1% today owns almost as much wealth as the bottom 90% of US families.
The estimates of Piketty, Saez, and Zucman (2018) show that the total burden (including all taxes at the federal, state, and local levels) of the wealthiest 0.1% families is projected to be 3.2% of their wealth in 2019 (they have on average $116 million in wealth, and pay total of $3.68 million in taxes). The proposed progressive wealth tax would add an extra $1.27 million (or 1.1% of wealth) to their tax burden for a total tax burden (relative to wealth) of 4.3%.
In contrast, the bottom 99% families have a total tax burden of 7.2% relative to their wealth. Their tax burden relative to wealth is much higher than for the top 0.1% because the bottom 99% relies primarily on labor income, which bears tax but is not part of net worth. In contrast, the majority of the income of the top 0.1% wealthiest comes from returns to their wealth.
Note: Our analysis complies with the highest levels of transparency and reproducibilty for open policy analysis proposed by the Berkeley Initiative for Transparency in the Social Sciences. We invite contributors and critics of this analysis to follow similar standards.
The authors would like to particularly acknowledge the excellent research assitanship of Katie Donnelly Moran and Clancy Green.↩
This dynamic document is part of an Open Policy Analysis which follows the guidelines of the Berkeley Initiative for Transparency in the Social Sciences↩
With r=5.5%, we have [1+(1+r)+..+(1+r)^9]=[(1+r)^10-1]/r=12.9, or approximately 13.↩
Saez, Emmanuel and Gabriel Zucman, “Wealth Inequality in the United States since 1913: Evidence from Capitalized Income Tax Data”, Quarterly Journal of Economics 131(2), 2016, 519-578, updated series available at http://gabriel-zucman.eu/usdina/↩