Openai/69640cff-e5e0-8003-a8d1-a78b118ca18b

This conversation was exported from ChatGPT

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:

1. The sign isn’t even robustly “up” in the UK evidence; it can be down locally because of compositional/native-flight dynamics.
2. 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):

1. 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.
2. 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:

1. 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.
2. 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.
3. 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.
4. 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.
5. 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):

1. 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.
2. 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.
3. “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.

gpt-5-2-thinking

User: Okay, I read through the entire response thrice, and I am still unconvinced.

Okay, I read through the entire response thrice, and I am still unconvinced.

1. Initial question to GPT: "Do not make the mistake of thinking the calculus for the government budget reflects the gains and losses to the economy as a whole."

This almost always, if not always, devolve into the same story that studies and in this case, an analysis by AI gives out-- more warm bodies in a country = higher GDP.

I know you say you account for that, but the response doesn't seem to have accounted for it enough.

1. I've heard that so many reports of the fiscal impacts of immigration in the UK simply do not capture many of the programs they use at all. An example that I've seen cited is that almost half of all social housing in London alone is occupied by foreigners, and they get folded into the local council bookkeeping and do not reflect in many fiscal impact studies. True?

Are you truly taking into account all the cornucopia of programs and benefits that immigrants avail themselves? Especially the Boriswave migrants.

1. I am skeptical that “Low-skilled” at entry ≠ “low productivity” forever. If this was true, we'd see and hear of this. Based on what I've read and the direct second hand accounts from those living in the UK I've heard, this seems too good to be true.

For example, take the typical low-skill immigrant stereotype of recent times: the Deliveroo driver from the Indian subcontinent who came to the UK in 2021 as part of Boriswave. Am I to believe these cohorts have upgraded themselves to a high-income, high-productivity job and continue to do so in large numbers?

Sounds absolutely fantastical. If so, we'd have heard about it. I'd have heard anecdotally about it.

1. Also, I am pretty sure your analysis doesn't take into account all the literature we know of long-term consequences of economic growth a nation's economic and political institutions will be changed by non-WEIRD immigration as shown by Garett Jones. There are so many effects on national wellbeing that diversity and third-world immigration cause on social trust, norms, trust in institutions etc. and these effects remain well beyond the first generation of immigrants. Did you actually take into this into account?

Assistant: You’re basically saying: “Stop giving me GDP accounting.

You’re basically saying: “Stop giving me GDP accounting. I want to know whether natives’ welfare rises once you (a) strip out pure transfers, (b) separate fiscal from real-economy effects, and (c) take seriously long-run institutional / trust channels.” That’s the right framing—and it leads to a much less triumphalist (and much less deterministic) conclusion than “warm bodies → higher GDP → good.”

Below I’ll tackle your four points directly, but first a clean way to organize the question.

A better “native welfare” ledger than GDP or the headline fiscal balance

For the welfare of existing residents (natives + earlier immigrants) the main components are:

1. Purely pecuniary, within-market effects Wage changes, returns to capital/land, consumer prices, firm profits. These are mostly transfers among residents unless there are wedges/market power. The “immigration surplus” in standard competitive models is usually small (a triangle), while distributional effects can be large.
2. Real resource / non-pecuniary effects Congestion in NHS/schools/transport, environmental crowding, queues, crime, neighborhood amenity changes, social trust/cohesion. These can be genuine welfare changes even if measured GDP rises.
3. Fiscal externalities (not the same as fiscal accounting) A negative net fiscal balance can reduce welfare only insofar as it requires distortionary taxes or displaces valuable public spending; a positive fiscal balance can raise welfare similarly. The budget ledger is not the welfare ledger—but it’s not irrelevant either.
4. Dynamic/institutional effects Productivity spillovers, innovation, entrepreneurship, and the hard-to-measure “institutional/trust/norms” channel you’re pushing on.

With that framing, here are your points.

1) “This always devolves into: more people = higher GDP”

Yes—and that’s exactly why GDP is the wrong metric.

What does the UK evidence say about the pecuniary part that matters for native welfare (wages, prices, productivity)? The most robust finding is: average wage effects on natives are small, with some evidence of slightly more pressure at the bottom and small positives at the top.

• The UK Migration Advisory Committee’s big review of EEA migration concludes impacts on wages/employment are generally small and shouldn’t be exaggerated.
• Bank of England work finds a small negative effect on average wages, with larger effects in semi/unskilled services (still not huge).
• Dustmann et al.’s distributional approach (UK) finds heterogeneous effects and emphasizes immigrant downgrading on arrival (important for how “skill” maps to wages).

If wage effects are small, then the classic “immigration surplus” (net native gain from cheaper labor / higher capital returns) is also small in aggregate. That’s not “immigration is always good,” it’s “the average market gain to existing residents is usually not large enough to dominate everything else.”

So if you’re looking for a decisive pro-immigration welfare case for low-skilled inflows, it usually won’t come from the labor-market channel. It would have to come from (a) meaningful productivity spillovers, or (b) fixing shortages in a way that measurably improves native welfare, or (c) strong positive fiscal externalities. For “low-skilled” specifically, the literature is much more mixed on those.

2) “Fiscal studies miss tons of programs (e.g., social housing) — half of London social housing is foreigners”

Two separable questions here:

(A) Is the “half of London social housing” claim true?

The cleanest fact pattern I’ve seen is the 2021 Census-based discussion: about 47.6% of London social-housing households had a foreign-born “lead tenant” (so: not “foreign nationals,” and not necessarily recent arrivals). And importantly, “foreign-born” includes British citizens and long-settled people.

So: “nearly half foreign-born” is plausibly true (depending on definition); “half foreigners” (implying non-citizens / recent migrants) is usually not.

(B) Do serious fiscal studies omit housing-related costs?

Some do; some don’t; and “housing” is tricky because it mixes cash benefits, capital spending, and in-kind subsidies.

• Dustmann & Frattini explicitly allocate housing benefit spending using administrative recipient shares and also allocate housing development (social/local authority housing expenditure) using the share of social-housing tenants in LFS. That means: the claim “these studies don’t include housing at all” is false for this flagship paper.
• The newer MAC (2025) fiscal methodology explicitly includes housing-related categories (e.g., a “Housing Development” line allocated using social-housing resident data) and also discusses restrictions like settlement/ILR affecting access.

But your deeper worry is still partly valid: many fiscal exercises struggle with the implicit subsidy in social housing (the gap between social rent and market rent) and with local-service pressures that don’t show cleanly in national accounts. Even when “housing development” spend is allocated, that is not identical to valuing the in-kind rent discount or the welfare cost of longer queues / displacement.

Also, the post-2021 system matters: many people on work/student visas have No Recourse to Public Funds (NRPF), which explicitly bars most benefits and “housing assistance” for immigration purposes (with exceptions). So the “Boriswave migrants are soaking up the whole welfare cornucopia” story is mechanically constrained for large swathes of temporary migrants—though it doesn’t remove issues like private-rental pressure or local congestion.

Bottom line on (2): the strongest claim you can defend is: “Some fiscal studies may not fully capture in-kind and local-housing rationing effects.” The strongest claim you can’t defend from the good literature is: “They ignore housing / social housing entirely.”

3) “Low-skilled at entry upgrades to high productivity? Deliveroo rider → high income sounds fantastical.”

Your skepticism here is warranted. The literature does not justify the rosy inference “entered low-skilled ⇒ later high-skilled in large numbers.”

What the evidence actually supports is heterogeneity:

• There is strong evidence of occupational downgrading on arrival for immigrants (doing jobs below formal qualifications).
• And there is UK evidence that for at least some cohorts, downgrading does not quickly unwind. For example, a UK government-commissioned analysis using ASHE–Census linked data finds substantial migrant pay gaps at entry and that gaps narrow only partially over the lifecycle; it also reports “very little evidence of substantial labour market improvement” for some downgraded groups studied.

On the other hand, newer administrative/cohort work often finds that earnings rise with years since arrival, and some cohorts catch up relatively quickly—but that can reflect visa selection (more “skilled-worker-route” entrants), and compositional attrition (the lowest earners are more likely to leave the payroll data / leave the country / move into self-employment). A UK administrative-data discussion of recent cohorts reports that median earnings for the 2022 cohort rose substantially and “caught up” to the median, and that earnings tend to rise with length of stay.

So: it’s not “fantastical” that some people transition upward (especially students → graduates; skilled-worker dependents → workers; etc.). But it is unjustified to treat that as the modal story for low-paid gig workers. The research support is closer to: “Some upgrade; many partially upgrade; a non-trivial share remain low-paid for long periods.”

4) “You ignored long-run institutional/trust effects (Garrett Jones / non-WEIRD immigration).”

Two things can be true at once:

1. Cultural persistence / intergenerational transmission is real. There’s serious evidence that traits like trust have an inherited/cultural component among descendants of migrants (in multiple settings).
2. The leap from ‘persistence exists’ → ‘UK institutions degrade in the long run from today’s migration composition’ is not empirically settled. The diversity–trust literature is mixed and effect sizes are often small, and results depend a lot on segregation, deprivation, measurement (generalized vs neighborhood trust), and causal identification.

What does the best synthesis say? A narrative + meta-analytic review of the ethnic diversity–trust literature concludes there is substantial heterogeneity; negative associations exist in many studies but are often small and sensitive to design/measurement.

And the UK-specific evidence is not one-sided:

• A well-cited London neighborhood study finds ethnic diversity is positively related to perceived social cohesion once deprivation is accounted for, while segregation predicts lower cohesion.
• Another UK-focused study (Citizenship Survey data) finds a negative association between ethnic diversity and trust overall, but does not support the claim that language fluency is the mechanism for whites; for non-white groups it finds more complex patterns.
• Micro-context causal-ish work from Denmark finds negative trust effects when exposure is extremely local (within ~80m), and that effects can vanish at more aggregated levels—again pointing to “how diversity is encountered” rather than a simple country-of-origin story.

So if your claim is: “institutional/trust externalities could swamp the tiny wage triangle,” that’s conceptually possible. But if your claim is: “the literature shows large, durable institutional harm from non-WEIRD immigration in rich democracies,” that’s not a safe read of the evidence.

My own take: the non-pecuniary channel is where the sign could flip, but it’s also where the empirical base is weakest and most context-dependent. In the UK, segregation + housing scarcity + stressed local services are plausible mechanisms for negative welfare effects even if wages/GDP look fine. The “country-of-origin institutions transplant” story is harder to validate cleanly in UK data compared to those more immediate channels.

So what does the UK literature actually imply about net welfare from low-skilled immigration?

If you force me to summarize the research-consistent position:

• The average pecuniary/native-income gain from low-skilled immigration (abstracting from fiscal and non-pecuniary effects) is likely small because measured wage effects on natives are typically small.
• The fiscal channel is not the welfare channel, but it matters at the margin; and serious fiscal work does try to include major categories like housing benefit and social housing-related spending, though in-kind and local rationing effects are still hard.
• The “they all upskill” narrative is not supported in general; mobility exists but is uneven, and some evidence suggests persistent gaps/downgrading for certain groups.
• The non-pecuniary/institutional effects are real candidates to dominate the welfare sign, but the evidence is mixed: some UK work finds negative diversity–trust associations, other UK work finds the diversity effect disappears or reverses once you account for deprivation/segregation; meta-analytic work emphasizes small, heterogeneous effects.

If your prior is “UK housing is inelastic and public services are congested, so marginal low-skilled inflows concentrated in London-like markets likely reduce welfare for a lot of low/middle-income residents,” the literature does not give you a slam-dunk reason to abandon that prior. What it does say is: don’t expect the labor-market channel to deliver huge native welfare gains, and don’t expect the trust/institutions channel to be a proven huge negative either—the decisive terms are probably housing/service congestion + segregation/deprivation dynamics, which many macro-style immigration papers only partially capture.

If you want, I can turn this into a decision-style framework: “Under what empirical conditions would low-skilled immigration be net-positive for UK resident welfare?” and map each condition to the strongest UK evidence we have (and where the evidence is missing).