Editing Openai/69640cff-e5e0-8003-a8d1-a78b118ca18b (section)

== gpt-5-2-pro ==
=== User: What does the research literature show on whether the United Kingdom reaps net welfare gains from low-skilled immigrati… ===
What does the research literature show on whether the United Kingdom reaps net welfare gains from low-skilled immigration? Keep in mind that some initiall low-skilled workers eventually go on to acquire skills and earn more. And do not confuse pecuniary vs. non-pecuniary externalities. For instance, if home prices go up that is a capital gain to (mostly domestic) landlords, not a cost for the economy as a whole. Do not make the mistake of thinking the calculus for the government budget reflects the gains and losses to the economy as a whole. Do survey this literature, and feel free to add your own thoughts as well.

=== Assistant: Below is what the UK-focused research literature implies about net welfare real income effects for UK residents from lo… ===
Below is what the UK-focused research literature implies about net welfare (real income) effects for UK residents from low-skilled immigration, along with the main caveats that matter for exactly the confusions you flagged (fiscal vs. social welfare; pecuniary price changes vs. real externalities; and dynamics/skill acquisition).

==== When economists ask whether the UK “reaps net welfare gains” from immigration, they typically mean: does the set of people already in the UK end up with higher total real income (and/or utility) because of immigration, after accounting for all relevant channels? ====

It helps to separate three objects that are often conflated:
* (A) National income / real GDP: Immigration almost mechanically raises total output because there are more workers. That’s not the same as gains to pre‑existing residents, because the additional output partly accrues to the migrants themselves.
* (B) Residents’ welfare (often: natives’ welfare): In the simplest competitive model, the gain to pre‑existing residents is the classic “immigration surplus” (a typically small triangle) plus any genuine externalities/spillovers, minus any genuine costs. The distribution can change a lot even if the net is small and positive.
* (C) Government budget / fiscal balance: A positive fiscal contribution can raise residents’ welfare (e.g., lower tax rates or better services), but the fiscal balance is not a welfare measure because it treats transfers as “costs/benefits” even when they are redistribution among residents; and because welfare includes non-fiscal channels like consumer prices, productivity spillovers, and amenity/congestion effects. Ian Preston’s conceptual survey emphasizes how accounting exercises can miss behavioural/general equilibrium and “indirect” effects.

Also, on your point about prices:
* Pecuniary effects (price changes that reshuffle purchasing power among residents, e.g., higher rents benefiting landlords and hurting renters) are mostly redistribution, not a social cost “for the economy as a whole.”
* Real externalities (true social costs/benefits) include congestion, crowding of a public good, pollution, crime, productivity spillovers, etc.

Housing is a good example: higher rents can redistribute from renters to landlords; whether there is a net welfare loss depends on things like housing supply constraints, distortions, crowding, and who you include in the welfare objective.

==== In the UK (especially post‑2004 EU enlargement), many migrants worked in low-paid / routine jobs despite having higher formal education (“downgrading” / mismatch). A recent UK government summary of “immigrant downgrading” highlights that some groups (e.g., A12 migrants) disproportionately start in routine occupations and that observed wage gaps partly reflect occupational allocation rather than pure productivity differences. ====

This matters because:
* If migrants are “low-skilled” only by job on arrival, but later move into better matches (or have high latent skills that raise firm productivity even in lower-tier jobs), then static low-skill classifications can understate longer-run gains.
* Conversely, if downgrading is persistent for some groups (credential recognition barriers, language barriers, discrimination), then the dynamic “they’ll all upskill” assumption is too optimistic.

So the literature’s safest message is: some upgrading happens, but it is heterogeneous and policy/institution dependent.

==== ### ====

Two cornerstone UK papers find that immigration’s wage impacts on UK-born workers are modest on average, but not uniform across the distribution:
* Dustmann, Frattini & Preston (Review of Economic Studies, 2013) estimate wage effects across percentiles. In their preferred IV-type specifications, increases in the immigrant-to-native ratio are associated with wage reductions at the very bottom (e.g., 5th/10th percentile) and wage gains around the middle/upper percentiles. They also summarize an average wage effect that is small and (in their estimates) slightly positive.
* Nickell & Saleheen (Bank of England, 2015 working paper) find small average effects but more noticeable impacts in some low-wage occupations; for example, they report that a 10 percentage-point rise in the immigrant share in semi/unskilled services is associated with about a 1.88% reduction in pay in that occupational group. That’s non-trivial for directly competing workers, but it’s still small relative to typical year-to-year wage variation and is about a large compositional shock.

For your welfare question, the key is: wage losses for some low-skilled natives are not automatically net welfare losses for “the UK”. They are primarily a distributional shift from those workers to:
* employers/capital owners (higher profits),
* complementary native workers (whose wages can rise),
* and consumers (if lower costs pass through into prices).

But if you care about native welfare with inequality aversion, the distributional effects become first-order.

===== Summaries of the empirical UK literature (and many primary studies underlying them) typically conclude little to no large aggregate employment displacement, with most effects concentrated (if at all) among specific lower-paid groups. =====

The upshot: the labour-market channel alone does not suggest large negative net welfare for residents, but it does imply that some low-skilled natives can lose.

==== This is a real welfare channel often neglected in public debate. ====

A Migration Advisory Committee‑commissioned report by Frattini (2014) studies UK regional CPI data (1997–2012) and finds:
* no effect on tradable goods prices (as expected in a small open economy),
* limited average effects on non-tradables overall,
* but negative effects on price growth in sectors that use low-wage labour intensively (examples listed include take‑away food, washing/dry cleaning, hairdressing, etc.), especially pre‑2007.

These price reductions are not a mere “transfer” among residents in the way housing price changes are. Lower service prices are a genuine real-income gain to consumers, reflecting lower marginal costs/markups. (Distributionally, they can benefit groups differently depending on consumption baskets.)

This channel tends to make low-skilled immigration look more positive in net welfare terms than an “only wages” analysis.

==== Empirically for the UK, an influential paper is Filipa Sá (Economic Journal, 2015). The IZA summary reports that she finds a negative effect of immigration on house prices, attributed to native mobility responses: natives—especially higher-wage natives—move away from high-immigration areas, reducing local housing demand. The negative effect is reported as being driven by areas where immigrants have lower education. ====

Two welfare-relevant lessons:
# The sign isn’t even robustly “up” in the UK evidence; it can be down locally because of compositional/native-flight dynamics.
# Even if prices rise, the first-order effect is redistribution (renters vs. owners), not a pure social cost. Net welfare effects come from housing-supply frictions, crowding, commuting, and distortions—issues that are real in the UK, but conceptually separate from “prices went up.”

==== ### ====

Giuntella, Nicodemo & Vargas‑Silva (2015) link Hospital Episode Statistics (2003–2012) with local immigration and find:
* reduced outpatient waiting times on average,
* no significant effects on A&E and elective care waiting times,
* but increased outpatient waiting times in more deprived areas outside London in the period right after the 2004 enlargement, which vanished in the medium run (3–4 years).

This is a good example of what you asked for: a non-pecuniary welfare channel (service quality / waiting time as rationing “price”) where the average effect is not strongly negative, but distribution across places matters.

===== Geay, McNally & Telhaj use the National Pupil Database (England) and study effects of non-native English speakers in classrooms. Their results suggest small and often inconclusive effects for reading/writing and a small positive effect in maths in some specifications, consistent with the idea that primary-aged students catch up in English proficiency and do not impede peers much. =====

Again: not obviously a large negative welfare externality on average, but local resource constraints could still matter.

==== Bell, Fasani & Machin (Review of Economics and Statistics, 2013) exploit two distinct UK migration “waves”: ====
* asylum seekers in the late 1990s/early 2000s,
* A8 inflows post‑2004.

They find:
* the asylum wave led to a modest but significant rise in property crime,
* the A8 wave had a small negative impact on property crime,
* no effect on violent crime in either case.

They interpret differences as consistent with labour-market opportunities shaping incentives.

For “low-skilled immigration,” this implies that welfare effects depend strongly on:
* legal work access,
* employment probabilities,
* and integration trajectories.

==== If immigration meaningfully raises UK productivity (TFP, within-firm efficiency, agglomeration effects), that can dominate the small wage triangle. ====

The UK evidence is not perfectly settled, but leans toward “not negative on average”:
* Ottaviano, Peri & Wright (NBER, 2015; later published) find that immigrants increase productivity in UK service-producing firms, reduce country-specific offshoring (consistent with task reallocation), and increase exports (lowering bilateral trade costs).
* Nam & Portes (IZA DP, 2023) find (at region-sector level, 2014–2019) evidence of a positive association between the non‑EU share of employment and productivity (with estimates implying “extra” non‑EU workforce shares associated with sizeable productivity differences), while EU shares show weaker/negative but typically insignificant patterns. They emphasize sensitivity to specification and caution about causality.
* Hall & Manning (CEP DP, 2024) estimate production functions for British firms and argue that much of the apparent higher productivity of migrants reflects sorting across areas/industries/firms, with smaller differences once firm fixed effects are used.

How does this relate specifically to “low-skilled” immigration?

There are two competing stories (both plausible; evidence mixed):
# Complementarity/task specialization: low-skilled immigrants allow natives (including less-educated natives) to move toward tasks with higher returns (communication/complex tasks), raising productivity and mitigating wage pressure.
# Capital-deepening / automation incentives: abundant low-skilled labour might reduce incentives to adopt labour-saving technology and training, lowering productivity growth.

The UK literature doesn’t deliver a clean “productivity loss from low-skilled migration” result; if anything, the commissioned and firm-level strands more often find positive or ambiguous effects with substantial uncertainty.

==== Two points can both be true: ====
* fiscal impact is not the welfare measure (your warning is correct),
* but fiscal impacts can still affect welfare through taxes, public goods, and distortions.

A widely cited UK study is Dustmann & Frattini (Economic Journal, 2014), which estimates that over 1995–2011:
* EEA immigrants made a positive net fiscal contribution,
* non‑EEA immigrants made a negative net fiscal contribution (in their accounting framework).

More recent UK policy work (e.g., the MAC’s newer methodology and annual reporting) emphasizes that fiscal impacts vary hugely by route and life-cycle profile, and presents dynamic/lifetime-style estimates, again highlighting heterogeneity.

For low-skilled immigration specifically, the fiscal sign depends on:
* earnings trajectory (including skill acquisition),
* family composition and dependants,
* entitlement rules,
* age at arrival and retirement location,
* and local public-service costs.

But even a negative fiscal number does not imply negative overall welfare, because:
* it can be offset by consumer-price gains, productivity gains, and capital income gains;
* and it is partly a redistribution question (who pays/receives).

==== If we restrict attention to welfare of pre‑existing UK residents (a “natives’ welfare” lens), a reasonable synthesis of the UK evidence is: ====
# Average labour-market impacts are small, with some negative wage effects concentrated among the lowest-paid and in specific low-wage occupations. → This suggests the classic “immigration surplus” is likely positive but not large.
# Consumer price effects in immigrant‑intensive low-wage services appear negative (prices lower) at least in certain periods/sectors, which is a real-income gain for consumers. → This pushes the welfare assessment more positive than a wage-only view.
# Public-service and amenity impacts (NHS waiting times, schooling spillovers, crime) do not show large uniform negative externalities; where negative effects appear, they are localized, group-specific, or short-run, and sometimes reverse or dissipate.
# Housing price effects are not a simple “cost” story, and UK evidence (e.g., Sá) can even show negative local price effects via native mobility. Even when prices rise, the first-order effect is redistribution, with net welfare hinging on supply constraints and crowding rather than the price change per se.
# Productivity effects are the biggest swing factor. UK firm/sector evidence more often points to positive or ambiguous productivity links, with important concerns about sorting and identification. If productivity gains are real, net welfare gains from immigration (including low-skilled work) can be meaningfully positive; if the productivity channel were negative, it could overturn the otherwise small positive surplus.

===== The literature does not support the claim that low-skilled immigration has imposed large net welfare losses on the UK as a whole. Instead, it supports something like: =====
* Net welfare for existing residents is likely modestly positive (or near zero but not strongly negative) on average,
* but the distributional impacts can be meaningfully negative for some low-skilled native workers and for some localities,
* and the sign/magnitude hinge heavily on productivity spillovers and on dynamic trajectories (skill acquisition, occupational mobility, family formation).

==== Three things I think are most often missing in public discourse (and sometimes even in narrow academic summaries): ====
# Prices and task allocation matter a lot for welfare. A wage-only lens misses that low-skilled immigration can reduce prices of local services and change task specialization. UK price evidence supports at least some of this mechanism.
# Local public-service strains are real welfare issues even if national averages look fine. The NHS evidence is a nice example: small average effects, but short-run increases in deprived areas. If those local strains aren’t funded/managed, you can get real welfare losses even if the national accounting looks positive.
# “Low-skilled” at entry ≠ “low productivity” forever. Credential recognition and language barriers can create large “brain waste” and keep people in low-wage roles longer than is efficient; reducing that friction can convert migration into clearer productivity and fiscal gains (and reduce distributional conflict).

Policy levers that (in my view) most plausibly raise net welfare from lower-paid migration without relying on wishful thinking:
* Housing supply responsiveness (planning, build-out constraints). This converts what would be congestion/scarcity into real expansion rather than just price redistribution.
* Targeted funding formulas for local services in high-inflow areas (schools, GP capacity, transport).
* Credential recognition and language training to speed match quality and wage growth.
* Labour standards enforcement (reduce monopsony/exploitation), which can both protect low-paid natives and raise tax receipts without needing to reduce inflows.

If you want, I can also sketch a simple welfare decomposition (immigration surplus + price effects + fiscal distortion term + public-good congestion term) and map each term to the UK evidence above, but the qualitative conclusion would stay: small average net gains, meaningful distributional and local effects, and productivity is the pivotal uncertainty.