Kimberly Strassel writes for the WSJ:
No one should be surprised if investigations show evidence of manipulation, as “downgrading” is nothing new in police departments. A New York Times story from more than a decade ago reported on an anonymous survey of nearly 2,000 retired New York City Police Department officers. It found that manipulation of crime reports—including both downgrading crimes and “discouraging victims from filing complaints”—had “long been part of the culture of the New York Police Department.” As one respondent put it: “Assault becomes harassment, robbery becomes grand larceny, grand larceny becomes petit larceny, burglary becomes criminal trespass.” Five years ago, a veteran MPD officer, Charlotte Djossou, sued the department, claiming it retaliated against her for raising concerns about unlawful searches and data manipulation designed to “make it appear crime was down.” The MPD’s summer settlement with Djossou was referenced in Comer’s letter to Smith demanding information for his probe.
The D.C. situation: There’s an additional reason to be suspect of D.C. numbers: they are pretty wild. If FBI numbers are to be trusted (and there’s a separate debate over that), violent crime has indeed come down some from the heights of 2020. But D.C.’s striking drops strain credulity, especially given that as of the beginning of this year, the MPD had only 3,200 sworn members, which the union described as a “50-year low,” and 800 below Bowser’s target of 4,000. Moreover, the crime fighters themselves don’t buy it. Union chief Pemberton suggests there was “potentially” some drop, but said it was “preposterous to suggest that cumulatively we’ve seen 60-plus percent drops in violent crime from where we were in ’23, because we’re out on the street. We know the calls we’re responding to.” And don’t forget that D.C. in recent years has danced to progressive calls to water down penalties against criminals and to pass its Comprehensive Policing and Justice Reform Act, which hamstrings police officers. The investigations will tell the real situation. Interestingly, few are casting doubt on recent figures that show Trump’s National Guard presence has rapidly reduced crimes in most categories. Perhaps instead of arguing over the numbers, mayors might look to learn what needs to be done to clean up their cities.
ChatGPT says: Philosopher Stephen Turner would probably react to the Strassel/WSJ piece by treating it as a textbook case of the politics of expertise—how statistics, bureaucratic authority, and media narratives get wrapped together into competing claims about legitimacy. Across his writings, Turner makes a few points that map directly onto this situation:
1. Expertise is always entangled with politics
Turner argues that experts don’t merely “deliver truths to power.” They operate within political structures, and their authority is mediated by bureaucracies, incentives, and traditions of decision-making. Crime stats (like labor stats, or public health numbers) are not neutral outputs of science but the result of institutional routines, classification practices, and political pressures. This makes the fight over whether DC’s numbers are “real” entirely predictable—crime categories can be downgraded, reporting can be discouraged, or bureaucrats can redefine what counts as violent crime.
2. The “problem with experts” is legitimacy
Turner stresses that experts must constantly justify themselves in two ways:
Output legitimacy: Do their numbers and claims “work,” i.e., do they produce results that make sense on the ground?
Process legitimacy: Are the procedures transparent, impartial, and insulated from manipulation?
The police union accusing DC leadership of downgrading offenses shows a breakdown of both. Officers don’t trust the process, and citizens don’t trust the outputs because they don’t match lived experience.
3. Media and selective attention
Why does the MSM focus intensely on labor stats under Trump but not crime stats under Democrats? Turner would say this reflects how expert authority gets filtered through politics and media institutions. The media treats some domains (economics, unemployment, inflation) as “objective,” central indicators of legitimacy, while treating others (crime) as less authoritative or even dangerous to touch if they cut against preferred narratives. In Liberal Democracy 3.0, Turner shows how modern liberal systems increasingly delegate contentious domains to expert bodies (“commissions”), which the press then shields from contestation by presenting their outputs as fact. Crime data under progressive mayors fits this pattern—experts pronounce, media amplifies, dissenters are treated as politicizing.
4. Statistical manipulation is normal, not anomalous
Turner has a Weberian streak: bureaucracies live off categories, and categories are malleable. “Downgrading” (assault becomes harassment, robbery becomes larceny) is exactly the kind of knowledge/power dynamic he describes—expert systems produce their authority not only by analyzing facts but by defining which facts exist. The fight is less about “truth” and more about who gets to define what counts as truth.
5. Why asymmetry between Trump-era labor stats and Dem-era crime stats?
Labor stats: Seen as technical, economic, and central to legitimacy of government. Journalists treat BLS economists as neutral experts.
Crime stats: Involve local politics, policing, race, punishment—domains where MSM prefers progressive narratives. Questioning them risks undermining broader political projects (e.g., reform, decarceration).
Turner would likely say this is not hypocrisy so much as the structure of expertise: different expert systems carry different symbolic weights, and media institutions align themselves with some while shielding others. It’s not about truth but about which expert systems are politically serviceable.
So if you pressed Turner on the Strassel piece, he’d probably shrug and say: this is exactly what happens in an age of experts. Numbers aren’t neutral; they’re weapons in political struggle. Media amplifies some expert domains (labor stats, climate science) and brackets others (crime data, border stats) depending on which align with its own coalitional politics. The real issue isn’t whether the numbers are “true” but whether the public has alternative institutional channels to contest expert claims—or whether we’re stuck in a world where politics is increasingly a fight over whose experts dominate the discourse.
Here’s how Turner would probably extend his argument to Trump’s deployment of the National Guard in D.C. as a crime-fighting move:
1. Re-politicizing an expertized domain
In Liberal Democracy 3.0, Turner describes how modern liberal systems delegate whole swathes of policy to experts—“commissions” and bureaucracies—leaving only a narrow band of issues open for public debate. Crime statistics and policing have been increasingly expertized: criminologists, mayors, police chiefs, and Justice Department officials produce numbers and narratives that are treated as authoritative. By sending in the Guard, Trump was tearing that issue back out of the hands of experts and putting it under direct political control. He was saying: I don’t trust your numbers, I don’t trust your process, and I’ll assert political will over expert consensus.
2. A challenge to “process legitimacy”
Expert systems rely on legitimacy by procedure—crime is tracked by standardized reporting, processed through FBI metrics, and publicized by media. Trump’s move implies the process itself is corrupt. He effectively bypassed the expert apparatus and created an alternative measure of legitimacy: do people feel safer when the Guard is on the streets? That reframes the standard away from statistical outputs and back toward political judgment, a very Turner-like moment of rupture.
3. Populist politics against technocratic authority
Turner often notes that expertise produces a democratic deficit: decisions are made by specialists, not by the public. Trump exploits this by presenting himself as restoring sovereignty to “the people” against elites hiding behind data. It’s not subtle—he’s saying: forget the charts, look out your window, do you feel safe? That’s populist politics puncturing expert monopoly.
4. The irony of creating a new expert body
Turner would also point out the irony: the Guard itself is a professional, disciplined expert institution. In practice, Trump isn’t abolishing expertise, he’s swapping one set of experts (police bureaucrats, statisticians) for another (military experts in control and order). In The Politics of Expertise, Turner stresses that expertise never disappears; it gets redistributed, legitimized in new ways, and aligned with different political coalitions. So the Guard is just another expertized instrument, but one aligned with Trump’s political narrative rather than Bowser’s.
5. The broader Turner-style take
Trump’s move is a reassertion of political sovereignty over expertized governance. It dramatizes the public’s suspicion that statistics are manipulated, and it shows how legitimacy can be shifted from “trust the process” to “trust the results you can see.” From Turner’s view, this is an example of how expert systems remain vulnerable to politics: when expert claims lose credibility, political actors can seize the opportunity to reframe the domain entirely.
Here’s a Turner-style riff, pitched as if it could sit inside The Politics of Expertise:
The episode of the National Guard in Washington illustrates the instability of expert authority once its legitimacy is questioned. For decades crime statistics have been presented as neutral facts, the outputs of technical procedures of classification and reporting. Their authority rested on the presumption of process legitimacy—that the categories were consistently applied, the counts untainted by politics. When this presumption failed, when police unions and whistleblowers suggested downgrading and manipulation, the numbers ceased to bind. What was once expert territory reverted to politics.
Trump’s deployment of the Guard was a paradigmatic act of re-politicization. He displaced the authority of the statistical expert with the authority of the visible result. Citizens were asked not to trust the quarterly tables but to trust their own senses: the presence of troops, the absence of crime in their immediate experience. This is not a rejection of expertise but a substitution of one kind for another. Military force is itself a form of expert knowledge—hierarchical, professionalized, routinized—but one whose legitimacy derives from its immediate and demonstrable effects rather than the opaque calculations of bureaucratic crime reporting.
The lesson is that expert systems are never immune from politics. Their monopoly persists only so long as their outputs retain credibility. Once the outputs are experienced as false or irrelevant, political actors can and will bypass the expert system, imposing new standards of judgment. The National Guard became, in this sense, an alternative expert body: one that could be trusted precisely because its work was visible, not buried in spreadsheets.
Here’s a Turner-inflected extension on the media asymmetry:
The differing treatment of economic versus crime statistics illustrates how expert domains are stratified in modern liberal democracies. Some domains—macroeconomic indicators, employment figures, inflation—have been institutionalized as central to state legitimacy. The Bureau of Labor Statistics speaks with an authority that is rarely challenged, and journalists position themselves as guardians of these numbers, treating them as neutral facts against which governments must be judged. In Turner’s terms, these are “expertized” domains whose legitimacy is reinforced by both bureaucratic pedigree and media ritual.
By contrast, crime statistics occupy a less secure place. They are both closer to lived experience and more open to manipulation through classification. To question them is to open a Pandora’s box of racial politics, policing debates, and urban governance. Here the media, rather than acting as watchdog, often acts as shield: accepting official narratives, protecting the authority of local expert systems, and deflecting scrutiny. This is not inconsistency but structure. Some expert domains are politically useful, aligned with the coalitions that dominate the press; others are too fraught, and their expert claims are insulated instead of interrogated.
Thus the asymmetry is not about truth but about which kinds of expertise the media treats as politically serviceable. Labor statistics during Trump’s presidency were the chosen battlefield because they bore directly on his legitimacy. Crime statistics under Democratic mayors are treated as settled fact because to contest them would disrupt coalitional commitments. What appears as bias is, in Turner’s framework, the ordinary functioning of an age in which politics is increasingly a struggle between competing expert systems, each backed or shielded by different segments of the press.