全球智库信息集成服务系统

In the past four decades, the United States has undergone significant demographic changes.¹ Immigration patterns have altered our racial composition, medical advances have aged our population by prolonging our lives, and economic forces have driven us to educate ourselves at unprecedented levels. Transformations of this magnitude will shape this century’s social and political landscape as well as test many of society’s institutions.

Among these tests, perhaps the most important will be representational in nature. To represent people, as Hanna Pitkin was wont to point out, is to make them present again. It is injecting the people’s voices and perspectives into our public policy process. It is speaking and advocating for their interests. It is the countless symbolic and substantive acts that contribute toward their inclusion in society.

Historically, our political institutions have struggled to represent a society that is demographically different than its electorate. The systematic disenfranchisement of women and communities of color, for example, contributed to a public policy process that ignored and underserved large portions of the population. Functionally, they created what we will refer to as representation gaps—the difference between the percentage of voters who belong to a given group and the percentage of the whole population that belong to that same group. While an electorate that resembles the general population is no guarantee of a representative polity, we believe it creates conditions favorable to one.

Representational gaps such as these persist in modern America politics. They are obviously different in size and arise as the result of different processes, but the problems they induce are similar. Given their continued existence, the goal of this report is as follows:

• Document the representation gaps we have observed along age, education, gender, and race lines over the last several decades.
• Predict what those gaps might look like going into the future using the best available demographic projections and turnout data.
• Facilitate a conversation about the representational challenges the United States is likely to face in the coming decades and what solutions might work best to confront them.

Our analysis finds the white overrepresentation and minority underrepresentation has been a defining feature of American politics for decades. In fact, we may currently be at peak levels of both overrepresentation and underrepresentation. We also find that white overrepresentation is likely to decline in the future, as underrepresentation of Latinos and Asians declines significantly due to projected increases in citizenship among these groups. This trend will be especially noticeable in states that currently have the highest white representation gaps, such as Arizona, California, and Texas. By 2060, we expect the states with the highest white representation gaps to be interior states, such as Kansas, Utah, and Wyoming.

However, while representation gaps will likely decline in future decades, they will by no means be eliminated. Significant white overrepresentation and Latino and Asian/other underrepresentation will likely remain, primarily because of participation gaps reflecting the relatively low registration and turnout rates of the latter groups. Simulations indicate that the most successful route for minimizing future representation gaps lies in equalizing registration and turnout rates across races, perhaps due to some combination of registration reform and changes in mobilization practices. Progress in this direction would leave only a small representation gap due to the younger age structure among Latinos and Asians/others. It would also tend to equalize representation gaps across presidential and congressional elections in contrast to the current situation where gaps in congressional representation are much larger.

We will begin by reviewing the basic demographic landscape of the American population and how it is likely to change in the coming decades. The vast majority of early American immigrants were of European descent. This resulted in a 20th century populace that was mostly white—about 80 percent of the whole population in 1980.

However, newer immigrants have been coming from different places—mainly Asia and Central and South America. In addition, we have seen rates of interracial marriage increase, going from about 7 percent of all new marriages in 1980 to 15 percent in 2010.² These concurrent and interrelated trends have resulted in a modern U.S. population that is significantly more diverse, with about 61 percent identifying as white³. If current trends persist, this number will fall below 50 percent sometime in the mid-2040s, and by 2060, we project that white Americans will constitute less than 44 percent of the population.

This 36-point drop over 80 years has been and will mainly be the result of growing Hispanic and Asian/other⁴ racial communities, each growing about 22.5 points and 12.5 points, respectively. African Americans⁵ have held and will largely hold steady, growing only 1 point over this time period.

An important feature of these racial changes is that they have not and will not be evenly distributed—places and age groups are shifting at different rates. Looking at Figure 1, we can see that states along the coasts and the southern border have diversified at a much faster pace, with New Mexico, California, and Texas becoming so-called majority-minority states between 1980 and 2016. In contrast, the Midwest, Plains, Rocky Mountain, and upper New England states generally started off less diverse and shifted more slowly. As we go forward, this same general geographic patterns holds, with 18 more states becoming majority-minority over the next 44 years.

The nation’s diversification can also be described as bottom-up, with younger cohorts changing at a faster rate than older age groups. Those age groups below 30 will become more than 50 percent nonwhite in the 2020s, 30- to 44-year-olds joining them in the mid-2030s, and 45- to 64-years-olds flipping in late 2040s.

Accompanying this racial diversification has been the aging of the population. As shown in Figure 3, the two age groups that compose those younger than 30 both drop as a percentage of the whole population dramatically between 1980 and 2060—15 points collectively. Over this same time period, we see the oldest age groups increase in size as life-expectancy gains trickle up and the large Baby Boom generation ages. Those aged 45 to 64 and 65 and up go from 20 percent to 24 percent and 11 percent to 23 percent of the whole population, respectively.

Finally, we have also the seen the U.S. population become more educated. From 1980 to 2014, the percent of the voting age population with a college degree has roughly doubled—going from 15 percent to 30 percent—with two-thirds of that growth coming from an increase in the number of college-educated whites.

Among whites, this has coincided with an incredible 25-point decline in adult noncollege whites among the voting age population, going from 69 percent to 44 percent. The black noncollege population has also shrunk but only by less than a point. On the other hand, noncollege Hispanics and Asians/others have actually increased as a percentage of the overall voting age population—8 points and 3 points, respectively. This is happening despite rising educational levels among all races because these groups are, more generally, growing quickly.

Taken together, these trends constitute a level of change that can only be described as transformative. In some ways, we are just beginning to come to grips with the ways these changes have already altered our society—and many of the largest changes are yet to come. There is no doubt that they will challenge the country’s policies, institutions, and people.

Among these challenges, perhaps the most important will be representational in nature. How well have different groups in the United States been represented in the electorate, and how will that change going into the future?

To tackle these questions, we rely on what we refer to as total representation gaps—a measure that captures the level of overrepresentation or underrepresentation experienced by a demographic group in the electorate. Functionally, it is calculated by taking the difference between the percent of the whole population that belongs to a given group and the percent of voters who belong to that group. Positive values indicate overrepresentation among voters while negative values indicate underrepresentation.⁶

Race gaps

White overrepresentation has been one of the defining features of American politics over the past several decades. With the exception of blacks in the 2012 election, communities of color have been consistently underrepresented in the electorate. Beginning in 1980, the levels of underrepresentation we witnessed among these groups were driven in roughly equal measure by the older age distribution, higher citizenship rate, and higher political engagement levels of whites. In the past three decades, the immigration-based growth of the Hispanic, Asian, and other race populations has lowered the citizenship rates of these groups and increased the overrepresentation of whites in the electorate. As we move forward into the future, we can expect some of this white overrepresentation and Hispanic underrepresentation to taper off. As growth from Hispanics, Asians, and those of other races comes increasingly from native births, political participation deficits in the form of registration and turnout gaps will come to be the key drivers of underrepresentation between racial groups.

Here is how these broad trends will evolve. Start with how well different racial groups—whites, blacks, Hispanics, and Asians/others—have been represented in the electorate. As we can see in Figure 4, whites have been consistently overrepresented among voters in both presidential and midterm elections for past 36 years. Even as their share of the population has declined, their overrepresentation has actually increased, going from a 7-point gap in the 1980 and 1982 elections to a 10- and 14-point gap in 2012 and 2014. This is notable because we generally expect representation gaps to grow as a population grows and to shrink as a population shrinks.

The steady overrepresentation of whites during these years was mirrored by the underrepresentation of communities of color. For blacks, the underrepresentation gaps in presidential and midterm elections hovered around -2 points between 1980 and 1994. However, after 1996, these gaps began to shrink, especially for presidential elections. During the election and re-election of America’s first black president, Barack Obama, we saw underrepresentation reduced to essentially zero in 2008 and actually flip to a slight overrepresentation in 2012. There’s been a similar movement in the past two midterm elections, where we saw black representation gaps move above -1 for the very first time.

In contrast to whites and blacks, Hispanics’ representational fortunes have moved in the opposite direction. In 1980 and 1982, there were representation gaps of -3 and -4 points, respectively; by 2012 and 2014, these gaps had grown to -8 and -10 points. This makes Hispanics the racial group that is most underrepresented as well as the group that has seen the largest increase in their underrepresentation over time.

A similar pattern of underrepresentation has occurred for Asians and those of other races. There has been an increase in the level of underrepresentation, going from about -1 point in 1980 and 1982 to just about -3 points in 2012 and 2014.

Using the data created in the first two years of the States of Change project, we can also project these gaps forward into the future, indicated in Figure 4 by the dotted lines going out to 2060. These projections assume that the underlying demographic features of the U.S. population continue to change but that the political behavior of various demographic groups remains the same. In this case, the same means that relatively fine-grained demographic groups⁷ register and turnout at rates identical to those from the most recent election for which we have data—2012 for presidential elections and 2014 for midterm elections.

These are not predictions nor should they be considered in that light. Rather, they are thought experiments that we can use as a baseline for understanding what the future might hold for the country’s representational challenges.

All of that said, these projections suggest that representation gaps will shrink substantially in the future but remain with us well into the 21st century. For whites, we project that underlying demographic shifts by 2060 could push their overrepresentation gap down about 3 points for both presidential and midterm elections. Specifically, they would drop to 7- and 11-point gaps by 2060 and 2058. For presidential elections, this brings overrepresentation roughly back to its 1980 levels.

For blacks, we project demographic changes to increase their level of overrepresentation in presidential elections only slightly, going up about a point over this 44-year period to about 1.4 points. In midterms, we project a gradual reduction of black underrepresentation in these elections until slight underrepresentation flips to slight overrepresentation by the 2030 election.

For Hispanics, underrepresentation will continue but there will also be significant strides toward a more representative electorate. These changes will not be overwhelming—a 3-point improvement in presidential elections and a 2-point shift in midterms over the next 44 years—but these changes occur even as their population share is projected to grow by about 11 points. All things equal, we would normally expect an increase in population size to result in a larger representation gap. That we actually see the opposite occurring suggests some rather favorable trends for Hispanics over the next 44 years.

In contrast, our projections for Asians/others indicate that we should expect a steady level of underrepresentation as we move into the middle of the 21st century. Once again, this number can be somewhat deceptive if we do not take population growth into account: Stability in this representation measure, even as the group grows about 7 points as a share of the population, suggests relatively favorable demographic changes.

Race gaps: Decomposition

An additional feature of the data we have built is that we can decompose these total representation gaps into their constituent parts. Both underrepresentation and overrepresentation occur for a variety of demographic and behavioral reasons. This analysis allows us to pinpoint these sources and see how they fluctuated over time and between different types of elections. These constituent parts are roughly divided into demographically oriented pieces—the age and citizenship gaps—and behaviorally oriented pieces—the registration and turnout gaps. See text box for a full description of these concepts.

Taking these in turn, Figure 5 displays our four racial groups’ age gaps—the portion of the total representation gap that exists due to unequal age distributions between different groups. Since 1980, whites have had a far lower percentage of their population in the zero to 17 age category, and this has resulted in a positive age gap for them and a negative gap for all other racial groups. While demographic shifts have caused blacks to become less underrepresented during this time period, Hispanics and Asians/others have seen relatively large increases in their age gaps. As we project out into the future, this trend should reverse course as blacks and Hispanics have larger and larger portions of their population age into the voting age population. Asians/others will continue to see their age gap increase, but the change will be less dramatic than what we’ve seen in the last three decades.

Next, we will examine the citizenship gap—the portion of the total representation gap that exists because of unequal levels of American citizenship between groups—which is displayed for our groups in Figure 6. Although there are a number of stories to tell here, the most consequential is about the rising Hispanic population. High levels of immigration in the decades after 1980 resulted in a rapidly growing population—but also one that had relatively low levels of citizenship. During this time period, the citizenship gap for Hispanics more than doubled, going from -1.5 points in 1980 to about -3.5 points in 2016. This underrepresentation growth was mirrored with a roughly identical growth in overrepresentation among whites.

According to our projections, these two large deviations from representational equality will shrink substantially over the next 44 years, especially the citizenship gap. The reason for this is that the majority of the growth among Hispanics will come from native births rather than immigration. As more native-born Hispanics enter the voting age population, they will start to bring their citizenship rate into alignment with that of whites and blacks. Accompanying this will be a similar trend among Asians/others, who will see a smaller but still substantial drop in their underrepresentation levels due to citizenship issues. Even absent any legislative action, we expect the citizenship gaps of both Hispanics and Asians/others to return to their 1980 levels in the 2030s and 2020s, respectively. By the 2050s, both these groups will have effectively zeroed out their eligibility issues.

Before presenting the remaining measures—registration and turnout gaps—it is worthwhile to give them a little context. For the purposes of this report, we felt it necessary to separate them into distinct parts of the total representation gap, given that they do, technically, represent different steps of political participation. Furthermore, there is a value in determining how much of the underrepresentation and overrepresentation gaps we see among groups is attributable to the difference between the eligible population and the registered population—the registration gap—versus the difference between the registered population and the voting population—the turnout gap.

That said, we do not wish to be misleading in regard to what these measures might mean. Hypothetically, say that the registration and turnout gaps for a given group collectively constituted a large portion of the total representation gap but that the former was significantly bigger than the latter. For those interested in reducing representation gaps, a common but likely mistaken interpretation of this data might be something akin to, “If we can just get X group registered to vote, then we can close most of the gap.”

The reason this interpretation is suspect is that these two gaps are part and parcel of the same behavioral characteristic—political engagement. Individuals who register to vote and then vote have a higher level of engagement than those who do not register to vote and, subsequently, do not vote. Closing a part of the registration gap—say, by making registration easier—would not necessarily produce individuals who turn out to vote at the same rate. In fact, we would almost certainly expect these individuals—who are less politically engaged than individuals who were able to register themselves previously—to turn out at a lower rate. Instead of being entirely eliminated, a significant portion of the total representation gap you might close through higher registration could simply manifest itself as a higher turnout gap.

All of this is to say the following: While we do present the registration and turnout gaps separately, there is considerable value in thinking about them as highly interrelated measures that cannot be divorced from one another easily.

That throat clearing aside, we can see the past and projected registrations gaps for presidential and midterm elections in Figure 7. For most of the presidential elections after 1980, we saw whites systematically overrepresented among registered voters as a result of their higher registration rates. While the white registration gap in presidential elections has moved from a low of 1.4 in 1984 to 2.5 in 2012, we have seen the registration gaps of Hispanics and Asians/others increase by about a point each due, mainly, to population growth.

In contrast, the black registration gap that hovered between -1 and -0.5 between 1980 and 2004 essentially zeroed out in 2008 and flipped from underrepresentation to overrepresentation by 2012. Spurred on by the election of America’s first black president, the relative registration rates of this group rose dramatically and contributed to one of the few flips we see anywhere in our data.

The story for midterm registration gaps is very similar for the elections between 1982 and 2014 except that all the gaps tend to be slightly larger than their presidential counterparts. Whites were overrepresented while Hispanics and Asians/others were underrepresented. Each of those groups has seen their representation gaps grow larger and move away from zero. Blacks have been underrepresented at relatively low levels in midterms and have seen smaller gaps in the last several election cycles, but unlike in presidential elections, these improvements have not yet resulted in a positive representation gap.

Projecting out to 2060, what can we expect if registration rates are identical to the ones we observed in 2012 and 2014? Unlike the more demographically oriented pieces of the total representation gap, registration issues will generally make racial registration gaps larger as we move forward.

One reason for this is that there is a strong relationship between age and registration—with younger Americans tending to register at a lower rate than older Americans. However, not all racial groups are aging at an equal rate. With their bottom-up growth driven primarily by relatively high fertility rates, Hispanics and Asians/others will age more slowly as a group than whites and blacks. Additionally, as eligibility gaps close during this time period, that now-larger eligible voter population will register at a lower rate than whites and blacks. In this way, diminishing eligibility gaps can turn, in part, into increasing registration gaps.

We expect that white registration gaps will go up from 2.8 and 4.1 points in 2016 and 2018 to 3.9 and 5.1 points in 2060 and 2058. Similarly, blacks will continue to increase their positive registration gaps, although these changes will be much smaller at 0.4 and 0.1 to 1.0 and 0.6 during the same timespan. Mirroring the growth of those two groups’ gaps, the projections indicate that we should anticipate larger, negative registration gaps for Hispanics—from -2.2 and -2.7 to -3.2 and -3.6—and Asians/others—from -1.1 and -1.4 to -1.6 and -2.0.

Finally, we’ve displayed the turnout gaps for presidential elections and midterm elections in Figure 8. For whites, we have observed two markedly different trends since 1980—a modestly declining level of turnout overrepresentation in presidential elections and a substantially increasing level in midterms. In 1980 and 1982, the presidential and midterm gaps were nearly identical at 0.7 and 0.5, but by 2012 and 2014, they had become quite distinct at 0.1 and 2.6. Interestingly, 2012 and 2014 represent both the lowest—presidential—and highest—congressional—turnout gaps we have observed in the past 36 years.

For blacks, the story varies somewhat depending on the start year one uses, but it is clear that negative turnout gaps have been the norm since 1980. However, since the late 1980s to early 1990s, those gaps have been shrinking significantly as black turnout has increased. The midterm turnout gap for blacks actually turned positive in 2010, though it slipped back to very slightly negative in 2014. The presidential turnout gap for blacks went from negative to positive starting in 2008 and, strikingly, was actually larger than the white registrant turnout gap in both 2008 and 2012.

In contrast, Hispanics started with negative turnout gaps and have seen those gaps grow larger over the last 36 years. Their presidential and midterm turnout gaps were essentially equal in 1980 and 1982—hovering around -0.2—but changed at notably different rates over time. As of the 2012 and 2014 elections, these gaps stood at -0.5 and -1.7. We can tell a nearly identical story for Asians/others from the roughly similar negative gaps in 1980 and 1982—both were below -0.1—to the divergent rates of change leading up to 2012 and 2014—in which the gaps stood at -0.2 and -0.6.

Assuming that the turnout rates of registered voters remains the same, we see relative stability in the turnout gaps for presidential elections and larger changes afoot for midterms. By 2060 whites, blacks, Hispanics, and Asians/others are expected to shift 0.4, 0.2, -0.4, and -0.2 from their presidential baselines in 2016, respectively. In midterms, we would anticipate changes rough twice that size at 0.8, 0.5, -1.0, and -0.3 from 2014 to 2058.

Taking a step back, we might ask about the relative impact of each of these factors over time and how they might change in the future as the American population shifts. To assess this, let us take the single racial group that is consistently overrepresented during our analysis—whites—and see how each of the gaps contributes to their overrepresentation in a given year. Figure 9 displays those composition values for every presidential and midterm election between 1980 and 2060.

In general, the early 1980s were a time when age, citizenship,