From https://www.census.gov/programs-surveys/decennial-census/2020-census/about.html, with emphasis added.
As mandated by the U.S. Constitution, our nation gets just one chance each decade to count its population. The U.S. census counts every resident in the United States. It is mandated by Article I, Section 2 of the Constitution and takes place every 10 years. The data collected by the census determine the number of seats each state has in the U.S. House of Representatives (a process called apportionment) and is also used to distribute billions in federal funds to local communities.
The next census in 2020 will require counting an increasingly diverse and growing population of around 330 million people in more than 140 million housing units. To get an accurate count, the Census Bureau must build an accurate address list of every housing unit, maximize self-response to the census, and efficiently follow up with those who do not respond.
I write to comment on Jonathan Siegel's statement that, "One thing Roberts' opinion emphasized is that politicians and bureaucrats have no obligation to listen to scientists on issues of public policy." The harsh anti-science attitude attributed to the Chief Justice of United States sparked me to study his actual opinion.
To my relief, I found nothing in it that frees governmental policymakers, political and judicial, from their core responsibilities to seek appropriate input from relevant and qualified experts of all types. including experts in the sciences (including mathematics and statistics). This matter was reaffirmed with respect to litigation testimony in Justice Blackmun's brilliant opinion in Daubert v. Merrell Dow.
To be sure, however, there is a passage in Roberts' opinion that expresses a truism: Policymakers are free to discount or even set aside "objective evidence"and render decisions that "are routinely informed by unstated considerations of politics, the legislative process, public relations, interest group relations, foreign relations, and national security concerns (among others)." (Page 24.) In short, government policymakers may listen intently and understand the objective evidence just fine, but they may decide to act in a manner contrary to it.
In a passage reflecting a pro-science view, or, at least, a tolerant-of-science view, Roberts acknowledged and even applauded the testimony that Secretary of Commerce (may have) "listened" to past studies related to the issue and considered alternative methodologies to obtain sound counts. But he also expressed that the Secretary had the legal right to choose the methodology himself--as long as his decision-making was based on sound and constitutionally legal reasoning, even if that reasoning was more subjective than objective.
What tilted Chief Justice Roberts to vote with the Liberal SCOTUS Four? From Pages 27-28:
Altogether, the evidence tells a story that does not match the explanation the Secretary gave for his decision. In the Secretary's telling, Commerce was simply acting on a routine data request from another agency. Yet the materials before us indicate that Commerce went to great lengths to elicit the request from DOJ (or any other willing agency). And unlike a typical case in which an agency may have both stated and unstated reasons for a decision, here the Voting Rights Act enforcement rationale-the sole stated reason-seems to have been contrived.
... we cannot ignore the disconnect between the decision made and the explanation given.
In sum, the Roberts' opinion is not antithetical to science. Rather, the Chief Justice split with the more conservative four-judge block in order to render a 5-4 decision that is congruent with (1) insisting that Trump administration officials be transparent and truthful in their motives and (2) requiring that they adhere to the rule of law, in this case a longstanding one that requires the Census Bureau (and, thus, the Secretary of Commerce, and, thus, the President of the United States) to use methods designed to minimize Census undercounting-and certainly not to increase that undercoat in a blatantly biased manner.
------------------------------
Ralph O'Brien
Professor of Biostatistics (officially retired; still keenly active)
Case Western Reserve University
http://rfuncs.weebly.com/about-ralph-obrien.html------------------------------
Original Message:
Sent: 06-27-2019 16:18
From: Jonathan Siegel
Subject: The Supreme Court Decision on the Census Citizenship Question
Today's Supreme Court's decision on the census citizenship question deserves, I think, a bit of reflection when we think about our role as a scientific community in questions of public policy. In this as in some other well-known past decisions, Chief Justice Roberts was the only justice who agreed with the entire decision, joining with the court's 4 more liberal members for part and its 4 more conservative members for a different part. As a society working in a public that sometimes has extremely divergent views, we will also sometimes have to perform similar straddles. I think its points, agree with them are not, are useful ones for a discussion on our appropriate role.
One thing Roberts' opinion emphasized is that politicians and bureaucrats have no obligation to listen to scientists on issues of public policy. Public policy is not merely a matter of fact or technique; it involves values. What may appear to be the less efficient method will often be preferable to the more efficient method because of value considerations. There is rarely only one goal in public policy. The obviously best method to achieve one goal will often run contrary to other goals. It is not the role of the technocrats to say what the goals are. That is the job of the elected politicians and the politically appointed administrators. In particular, the census has never served only the goal of the best possible enumeration. It has always collected other data serving other goals. The opinion suggested the Census Bureau could, through an open and honest process, potentially add a citizenship question and doing so could potentially serve legitimate purposes.
At the same time, administrators have to be honest about what their goals are, and there has to be some alignment between the stated goals and their means. "The reasoned explanation requirement of administrative law, after all, is meant to ensure that agencies offer genuine justifications for important decisions, reasons that can be scrutinized by courts and the interested public. Accepting contrived reasons would defeat the purpose of the enterprise."
This opinion, in other words, sets out a view of the appropriate role of technical and scientific opinion in the government administrative system. On the one hand, government officials don't have to agree with the scientists, especially on goals. Scientists' values and goals get no more weight than anyone else's. The four justices who said they should were in the minority. Perhaps most importantly for our profession, Justice Roberts' opinion specifically said political administrators are free to be skeptical about statistician's claims about the practical reliability of their models as optimistic, and to regard their assumptions with skepticism, based on nothing more than gut feel and general life experience. At the same time, the opinion suggests that scientists play an important role in keeping politicians honest, in discussing the consequences of goals, and in discussing whether goals and actions are congruent.
I imagine most ASA members would probably prefer the greater role given scientific and technical advice, and particularly statistical advice, in the 4-Justice concurring opinion authored by Justice Breyer, who argued that courts ought to defer to the scientific expertise of the Census Bureau's technical staff, not the political values and views of its politically appointed administrator. The difference is an important one, and the 5-4 split shows how closely divided the court, and our society, is on these issues.
But the majority opinion is the one we have to live with. And while the majority opinion calls for a lesser role, it is still an important one. We may have to learn how to live, and how to be as effective as we can, within it.
------------------------------
Jonathan Siegel
Deputy Director Clinical Statistics
------------------------------