Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation

arXiv:2608.04839 · econ.EM · Submitted 2026-08-05 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Economics. The day in economics: theory, mechanisms and the evidence beneath them.

Ruth: I'm Ruth.

Warren: And I'm Warren, here with Iris.

Ruth: We're looking at the paper: "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation".

Warren: Here's the gist of the paper. In fixed-effect regressions with numerous groups, conventional t-tests often fail because fixed effects absorb most identifying variation, concentrating what remains in a few observations, leading to invalid or overly conservative critical values.

Ruth: This paper develops an exact test derived solely from the design structure to address this limitation.

Warren: A key element is a nuisance-annihilating contrast—a linear combination of treatment and fixed-effect dummies that eliminates the fixed effects without affecting the outcome.

Ruth: By sign-flipping these contrasts, an exact symmetry of the null distribution is achieved across all sample sizes, even under arbitrary heteroskedasticity.

Title and authors: Ruth: Now we’re moving into the actual summary of "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation," focusing on what the authors actually delivered in terms of their main findings.

Warren: They show that you can get an exact p-value, meaning no more relying on those asymptotic assumptions—like the things that say our results will look normal if we have enough data—when your data is really concentrated <ref:2608.04839#pg1>.

Iris: Exactly. The core mechanism they found is this nuisance annihilating contrast, which acts like a special filter. It takes the treatment effect and all those fixed effect dummies and combines them in a way that zeros out the fixed effects without touching our actual outcome variable <ref:2608.04839#pg1>.

Ruth: And then they flip those contrasts around, right? That’s what makes the null distribution perfectly symmetrical no matter how big or small your sample size is, even when things are super messy with heteroskedasticity <ref:2608.04839#pg3>.

Warren: So it means we can get a valid inference in these tricky fixed effect regressions, even when the variation tied to our treatment effect is just squeezed into a tiny corner of the data. That’s huge for situations where you have tons of groups but very little actual variation left to study <ref:2608.04839#pg1>.

Iris: It really changes how we think about identification here. Instead of fighting against concentration by adding more data, you use the structure of your design itself—the way it forms those cycles—to define what variation actually matters for the treatment effect <ref:2608.04839#pg3>.

Ruth: And they’ve built tools to help us pick the right test, Warren. They introduce this capture ratio called kappa C. It tells you how much of that total variation your chosen test actually manages to catch <ref:2608.04839#pg1>.

Warren: That means we can stop guessing at tests and start choosing one based on the design itself, balancing how much information you get against how detailed you want your result to be, which they call granularity <ref:2608.04839#pg1>.

Iris: They even have this cycle packing algorithm. It’s a way to select the supports—the groups of observations you use for your test—that are structurally fine, like edge-disjoint four-cycles, to maximize that capture ratio <ref:2608.04839#pg1>.

Ruth: That’s practical because it solves the trade-off between capturing enough signal and not making the test too coarse. It moves us away from just looking at big asymptotic benchmarks and lets us use the specific structure of our data to guide our inference choices <ref:2608.04839#pg1>.

Warren: And for binary treatments, they gave us a hard rule—a granularity floor—that tells you exactly how many independent signs you can even use before you hit a wall, which prevents you from rejecting anything unless your sample size meets certain conditions <ref:2608.04839#pg1>.

Iris: It’s less about getting the 'perfect' test and more about getting a mathematically valid one that respects the limitations of your specific data structure <ref:2608.04839#pg1>.

Ruth: So, the implication is that when fixed effects are dominating, we can use design-based metrics like that capture ratio instead of just trusting conventional tests when the data is concentrated <ref:2608.04839#pg1>.

The paper's summary: Tom: So, we’ve seen how they built this exact test using cycles in a bipartite graph to handle fixed effects when everything gets concentrated, and now we're looking at what else the authors suggest to make this method even more useful.

Warren: They point out that the method isn't perfect for every situation. The Gaussian approximations they use don't always hold up, so they introduce some diagnostics like lambda n and the Herfindahl index H n to let you know exactly when those standard math tools just stop being trustworthy <ref:2608.04839#pg2>.

Iris: That makes sense. It’s not just about having a big sample size; it’s really about the actual shape of the data structure. If those indices go above a certain point, you know the standard statistical assumptions are broken, and you need to switch gears <ref:2608.04839#pg2>.

Ruth: And they show that by comparing this exact test against conventional tests under different error structures, you can actually see where this method has an advantage. For designs that are really concentrated, this exact approach can sometimes match or even beat calibrated conventional tests in terms of size while still staying valid even when the errors are totally messy <ref:2608.04839#pg1>.

Warren: So if you’re trying to build a model that needs to be robust against unpredictable error patterns, this exact method might actually be more powerful than the standard stuff you usually try first. It’s about knowing when to trust the structure of your data over those initial mathematical assumptions <ref:2608.04839#pg1>.

Iris: They also focus on making the selection of test supports more practical by looking at how much you capture versus how detailed your result needs to be, and they introduce cycle packing algorithms. These help you pick supports that are structurally sound, like edge-disjoint four-cycles with optimal nested pairing <ref:2608.04839#pg1>.

Ruth: That means instead of guessing which groups to use for your test, you use the actual geometry of the data to guide your choice between capturing a lot of variation and keeping the result detailed enough. It’s about making that selection process systematic based on what the data looks like <ref:2608.04839#pg1>.

Warren: And they also gave us a concrete limit for binary treatments, which is this granularity floor. It means you can't reject anything unless your sample size hits a specific threshold, which is a very clear constraint you need to keep in mind when you're building these models <ref:2608.04839#pg1>.

Iris: The improvements basically take this from being just technically exact to being something that’s actually usable in the real world by giving us clear rules for when the math breaks and how to use design structure to guide our choices <ref:2608.04839#pg1>.

Ruth: It points out that you don't have to wait for perfect conditions; you can use the design itself, the graph structure, to build inference that respects what your data is actually doing <ref:2608.04839#pg3>.

Warren: It shifts the focus away from just trying to chase a p-value number and toward understanding what kind of statistical question you are even allowed to ask based on how your model is structured <ref:2608.04839#pg3>.

Iris: We’ve covered the paper "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation" and its findings about exactness versus power trade-offs.

The paper's improvements: Tom: So, to wrap up this talk on "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation," what’s the big picture we’re looking at here?

Ruth: Basically, this paper shows that when you have a ton of groups but the variation is all packed into a few points, you don't need infinite data to get a valid p-value <ref:2608.04839#pg1>.

Warren: It proves that the structure of your data—the way it forms those cycles—is what identifies the treatment effect and makes exact inference possible even under arbitrary error conditions <ref:2608.04839#pg3>.

Iris: And they do this using these nuisance annihilating contrasts, which are linear combinations designed to kill the fixed effects without messing up your actual outcome variable <ref:2608.04839#pg1>.

Ruth: So, the implication is that we can move away from relying on huge sample sizes or perfect normality assumptions when we’re dealing with complex fixed effect models <ref:2608.04839#pg1>.

Warren: It means this method could be really useful for situations where you have a lot of groups but only a small amount of variation left to study <ref:2608.04839#pg1>.

Iris: And they give us tools like the cycle packing algorithms to help us choose the right test supports, balancing how much information we capture against how detailed your result needs to be <ref:2608.04839#pg1>.

Ruth: It’s about using design-based metrics, like that capture ratio, instead of just trusting conventional tests when the data is concentrated <ref:2608.04839#pg1>.

Warren: And for binary treatments, they gave you a concrete rule about the granularity floor so you know exactly where you're allowed to go with your signs <ref:2608.04839#pg1>.

Iris: So we’ve seen how structural identification connects directly to valid inference under challenging conditions.

Ruth: It’s a solid piece of work because it shows that the underlying structure of your data can actually unlock exact results when fixed effects are dominating the picture <ref:2608.04839#pg3>.

Warren: It shows that we don't always need infinite data or perfect assumptions when dealing with complex fixed effect structures, provided you can find those right structural contrasts <ref:2608.04839#pg3>.

Ruth: That was a deep dive into how cycle space and nuisance annihilating contrasts enable finite sample inference for these tricky fixed effect models <ref:2608.04839#pg3>.

Warren: That was a deep dive into how structural identification connects directly to valid inference under challenging conditions.

Iris: It’s a solid piece of work because it grounds the abstract idea of structural identification in concrete graph theory applied to econometrics.

Conclusion: Ruth: So, to wrap up this talk on "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation," we see that even when fixed effects dominate, you don't need infinite data to get a valid p-value <ref:2608.04839#pg1>.

Warren: It proves that the structure of your data—the way it forms those cycles—is what identifies the treatment effect and makes exact inference possible even under arbitrary error conditions <ref:2608.04839#pg3>.

Iris: And they do this using these nuisance annihilating contrasts, which are linear combinations designed to kill the fixed effects without messing up your actual outcome variable <ref:2608.04839#pg1>.

Ruth: So, the implication is that we can move away from relying on huge sample sizes or perfect normality assumptions when we’re dealing with complex fixed effect models <ref:2608.04839#pg1>.

Warren: It means this method could be really useful for situations where you have a lot of groups but only a small amount of variation left to study <ref:2608.04839#pg1>.

Iris: And they give us tools like the cycle packing algorithms to help us choose the right test supports, balancing how much information we capture against how detailed your result needs to be <ref:2608.04839#pg1>.

Ruth: It’s about using design-based metrics, like that capture ratio, instead of just trusting conventional tests when the data is concentrated <ref:2608.04839#pg1>.

Warren: And for binary treatments, they gave you a concrete rule about the granularity floor so you know exactly where you're allowed to go with your signs <ref:2608.04839#pg1>.

Iris: So we’ve seen how structural identification connects directly to valid inference under challenging conditions.

Ruth: It’s a solid piece of work because it shows that the underlying structure of your data can actually unlock exact results when fixed effects are dominating the picture <ref:2608.04839#pg3>.

Warren: It shows that we don't always need infinite data or perfect assumptions when dealing with complex fixed effect structures, provided you can find those right structural contrasts <ref:2608.04839#pg3>.

Iris: It’s a solid piece of work because it grounds the abstract idea of structural identification in concrete graph theory applied to econometrics.

Ruth: That was a deep dive into how cycle space and nuisance annihilating contrasts enable finite sample inference for these tricky fixed effect models <ref:2608.04839#pg3>.

Warren: That was a deep dive into how structural identification connects directly to valid inference under challenging conditions.

Iris: It’s a solid piece of work because it grounds the abstract idea of structural identification in concrete graph theory applied to econometrics.

Ruth: We've covered "Exact Inference in Fixed-Effect Regressions with Concentrated Identifying Variation" and its findings about exactness versus power trade-offs.

Warren: It was really interesting how they use geometry, like those cycles, to define what variation actually matters for inference <ref:2608.04839#pg3>.

Jagiellonian University

econ.EM

Submitted: 2026-08-05

Updated: 2026-11-10

Code: https://github.com/profsms/PanelAdequacy.jl

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 92/100

The gist: In fixed-effect regressions with numerous groups, conventional t-tests often fail because fixed effects absorb most identifying variation, concentrating what remains in a few observations…

Key concepts

Nuisance-annihilating contrast
This is a specific linear combination of treatment and fixed-effect dummies designed to remove the fixed effects from the outcome equation without changing what we are trying to measure. This crucial tool allows the test to focus purely on identifying the treatment effect, regardless of how many groups are present in the model.
Cycle space characterization
The paper frames fixed effects and treatment identification as cycles within a bipartite multigraph structure formed by observations. The variation we care about (within variation) is mathematically defined as the squared norm of the projection of the treatment onto this specific cycle space, linking statistical inference directly to the graph's structure.
Capture ratio ($Ω_C$)
This metric measures how much of the total variation in a design can be captured by a test. A higher capture ratio means better power for detecting effects. The paper uses this to compare different test strategies, helping researchers choose a method that maximizes the information extracted from their specific experimental setup.
Granularity floor
For binary treatments, this concept sets a minimum requirement on the number of independent signs available for testing. It establishes a hard limit: you cannot reject the null hypothesis at any level unless your sample size is large enough to meet this constraint, providing a data-driven check on test feasibility.

Terminology

Summary

In fixed-effect regressions with numerous groups, conventional t-tests often fail because fixed effects absorb most identifying variation, concentrating what remains in a few observations, leading to invalid or overly conservative critical values. p. 0

Where the paper says it

pl July 2026 Abstract In fixed-effect regressions with many groups, fixed effects can absorb most identifying variation, leaving a handful of observations to carry what remains. When variation is this concentrated, conventional t-tests can reject a true null more than half the time, and any fixed critical value is either invalid or so conservative it has essentially no power.

This paper develops an exact test derived solely from the design structure to address this limitation. p. 1
Where the paper says it

70 in the most leveraged papers. This paper treats that concentration, rather than aggregate variation, as the regularity condition for Gaussian inference and develops a finite-sample exact alternative.

A key element is a nuisance-annihilating contrast—a linear combination of treatment and fixed-effect dummies that eliminates the fixed effects without affecting the outcome. p. 0
Where the paper says it

This paper builds an exact test from the design alone. A nuisance-annihilating contrast is a linear combination of the treatment and fixed-effect dummies that eliminates the fixed effects without touching the outcome; sign-flipping these contrasts is then an exact symmetry of the null distribution at every sample size, under arbitrary heteroskedasticity.

By sign-flipping these contrasts, an exact symmetry of the null distribution is achieved across all sample sizes, even under arbitrary heteroskedasticity. p. 0
Where the paper says it

This paper builds an exact test from the design alone. A nuisance-annihilating contrast is a linear combination of the treatment and fixed-effect dummies that eliminates the fixed effects without touching the outcome; sign-flipping these contrasts is then an exact symmetry of the null distribution at every sample size, under arbitrary heteroskedasticity.

The core theoretical foundation lies in the two-way case, where observations form a bipartite multigraph. p. 2

Where the paper says it

The substance of the paper is the two-way case (Section 4), and its main point needs no new vocabulary to state. In worker–firm, firm–time, or student–teacher designs, the observations form a bipartite multigraph, and the linear combinations that annihilate the two-way fixed effects turn out to be exactly the cycles of that graph: alternating ±1 contrasts around closed walks, including “digons” formed by parallel edges (repeated matches).

The identifying treatment effect and the exact inference contrasts are precisely represented by the cycles within this graph structure. p. 2
Where the paper says it

In worker–firm, firm–time, or student–teacher designs, the observations form a bipartite multigraph, and the linear combinations that annihilate the two-way fixed effects turn out to be exactly the cycles of that graph: alternating ±1 contrasts around closed walks, including “digons” formed by parallel edges (repeated matches). So the mobility that identifies the treatment effect and the contrasts that make exact inference possible are the same object, and the entire within variation lives in that cycle space: formally, Vn = ∥ΠZ x∥ 2 , the squared norm of the projection of the treatment onto the cycle space (Proposition 4.

Specifically, the within variation (V n) is formally defined as the squared norm of the projection of the treatment onto this cycle space (| pi Z x | squared, Proposition 4.1).

The exactness of Theorem 3. p. 2

Where the paper says it

Everything that follows is a consequence of this fact: which cycles to use is a packing problem, the capture ratio κC introduced below is the observable price of exactness, and that price runs into a granularity floor set by how many independent signs the chosen cycles carry. The exactness of Theorem 3.

3 is independent of leverage and holds even when lambda n vanishes. p. 2
Where the paper says it

The exactness of Theorem 3. 3 does not depend on leverage: it holds whether or not λn vanishes.

The trade-off, however, is in power, which can be assessed from the design itself via the capture ratio (kappa C) and a standard-error premium (kappa-1/2 C) relative to an oracle test. p. 0
Where the paper says it

In two-way designs — worker-firm, firm-time — these contrasts are exactly the cycles of the bipartite mobility graph, so the movement that identifies the treatment effect is what makes exact inference possible. Exactness costs power: relative to an oracle test, a chosen set of cycles has an observable capture ratio κC ∈ [0, 1] and standard-error premium κ −1/2 C , and a packing algorithm resolves the capture-granularity trade-off.

The exactness is guaranteed under Assumption 2 (Blockwise symmetric errors), which requires that contrasts exactly annihilate fixed effects and that each contrast support is a union of blocks. p. 7
Where the paper says it

, εBK are mutually independent; (ii) each εBk is centrally symmetric, εBk d= −εBk ; and (iii) each contrast support Sc is a union of blocks. No moment or identical-distribution condition appears in Assumption 2: variances may differ arbitrarily across blocks and need not exist.

Theorem 3.3 guarantees that the fraction of patterns scoring at least as extreme as the observed one constitutes a valid p-value at every sample size, without asymptotics or estimated nuisance parameters, regardless of design concentration. p. 8
Where the paper says it

■ In words: compare the observed pattern of contrast signs against every possible sign pattern consistent with the null (or a random sample of them), using any test statistic at all. The fraction of patterns that score at least as extreme as the one actually observed is a valid p-value at every sample size, with no asymptotics, no estimated nuisance parameters, and no restriction on how concentrated the design is.

The paper introduces diagnostics like lambda n (maximum leverage) and H n (Herfindahl index) to determine when Gaussian approximations are no longer valid. p. 5

Where the paper says it

5 (Diagnostics). Both λn and the Herfindahl index Hn := P i (xe 2 i /Vn) 2 , with effective sample size Neff := 1/Hn, are observable from the design and should be reported alongside saturated FE estimates; Young (2022) computes λn-type shares across published

The exact test's power is compared against conventional tests under various error structures, showing that for concentrated designs, the exact test can match or exceed calibrated conventional tests in terms of size while maintaining validity under heteroskedasticity.

The paper quantifies the capture–granularity trade-off: coarser supports offer better capture but finer supports yield better granularity. p. 2

Where the paper says it

3(c) formalizes this capture– granularity trade-off : enlarging the flip group restricts its orbit span and weakly lowers the capture ceiling. Cycle packing supplies interpretable, granular supports.

Cycle packing algorithms are introduced to select edge-disjoint cycle families that maximize kappa C, providing an interpretable method for navigating this trade-off. p. 2
Where the paper says it

3(c) formalizes this capture– granularity trade-off : enlarging the flip group restricts its orbit span and weakly lowers the capture ceiling. Cycle packing supplies interpretable, granular supports.

The binding constraint in this optimization is identified as the splitting problem of a biconnected block, which necessitates partitioning the block into supports to maximize capture subject to a balance constraint. p. 2
Where the paper says it

In the diffuse benchmark, κC is Pitman efficiency relative to the infeasible oracle Gaussian test, so κ −1/2 C is the asymptotic standard-error price (Theorem 3. Capture rises when supports merge and reaches κC = 1 with one projection contrast per biconnected block (Proposition 5.

For binary treatments, Proposition 5. p. 1

Where the paper says it

In words, λn is the maximum leverage of the residualized treatment: the largest share of the identifying variation Vn carried by any single observation. When that share does not vanish, the ordinary t-test loses its foundation, and Proposition 2.

4 establishes a granularity floor: the number of usable independent signs cannot exceed the size of the smaller treatment group. p. 2
Where the paper says it

So the mobility that identifies the treatment effect and the contrasts that make exact inference possible are the same object, and the entire within variation lives in that cycle space: formally, Vn = ∥ΠZ x∥ 2 , the squared norm of the projection of the treatment onto the cycle space (Proposition 4. Everything that follows is a consequence of this fact: which cycles to use is a packing problem, the capture ratio κC introduced below is the observable price of exactness, and that price runs into a granularity floor set by how many independent signs the chosen cycles carry.

Optimal weighting for heteroskedasticity is provided in Theorem 3. p. 2
Where the paper says it

sign flips when errors are independent and symmetric, with arbitrary heteroskedasticity, yielding exact finite-sample inference (Theorem 3. In one-way designs this specializes to familiar sign-change and cluster-flip procedures (Canay et al.

9(c), where E n/V omega represents the Pitman asymptotic relative efficiency, and kappa het C = E n/V omega equals kappa C under homoskedasticity. p. 2
Where the paper says it

Its observable capture ratio is κC = 1 Vn X j≤C ΠZAj x 2 ∈ [0, 1], which becomes P c (v ′ cx) 2/Vn for edge-disjoint ±1 cycles. In the diffuse benchmark, κC is Pitman efficiency relative to the infeasible oracle Gaussian test, so κ −1/2 C is the asymptotic standard-error price (Theorem 3.

The new contributions include the concentration boundary and a fixed-critical-value impossibility result (Proposition 2. p. 3

Where the paper says it

Sign-flipping itself is classical (Lehmann & Romano, 2005; Hemerik & Goeman, 2018). The contributions are the concentration boundary and fixed-critical-value impossibility result (Proposition 2.

3), design-based nuisance annihilation with exact heteroskedastic inference (Theorem 3. p. 3
Where the paper says it

The contributions are the concentration boundary and fixed-critical-value impossibility result (Proposition 2. 3); design-based nuisance annihilation with exact heteroskedastic inference (Theorem 3.

3), cycle-space characterization (Proposition 4. p. 3
Where the paper says it

3); design-based nuisance annihilation with exact heteroskedastic inference (Theorem 3. 3); the cycle-space characterization (Proposition 4.

1), observable Pitman efficiency kappa C (Theorem 3. p. 2
Where the paper says it

Its observable capture ratio is κC = 1 Vn X j≤C ΠZAj x 2 ∈ [0, 1], which becomes P c (v ′ cx) 2/Vn for edge-disjoint ±1 cycles. In the diffuse benchmark, κC is Pitman efficiency relative to the infeasible oracle Gaussian test, so κ −1/2 C is the asymptotic standard-error price (Theorem 3.

9), and a structure-exploiting packing algorithm for an NP-hard problem based on the contraction principle of Proposition 4. p. 3
Where the paper says it

1); observable Pitman efficiency κC (Theorem 3. 9); and a structure-exploiting packing algorithm for a generally NP-hard problem, built on the contraction principle of Proposition 4.

6. The central finding is that the same movement that identifies the treatment effect is what makes exact inference possible. Numerical results confirm that structured packing recovers roughly twice the identifying variation compared to naive packing, and empirical capture ratios suggest full capture is achievable but concentrated, with the splitting problem being the binding constraint on realistic designs.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Exact inference in fixed-effect regressions with many groups can be performed exactly without relying on asymptotic normality conditions like Lindeberg-type, as nuisance-annihilating contrast is a linear combination of the treatment and fixed-effect dummies that eliminates the fixed effects without touching the outcome.

  2. The system can perform exact inference under arbitrary heteroskedasticity by using nuisance-annihilating contrasts where disjointly supported contrasts are invariant to independent sign flips when errors are independent and symmetric, with arbitrary heteroskedasticity, yielding exact finite-sample inference (Theorem 3.3).

  3. The AI system can determine the optimal test strategy based on design alone by calculating the observable price of exactness, which is the capture ratio kappa C or κC = 1 for block-projection tests. This allows practitioners to select a test that balances capture and granularity rather than relying on abstract asymptotic benchmarks.

  4. The system can implement a cycle packing algorithm to construct support systems that are structurally fine, such as edge-disjoint firm-pair four-cycles with optimal nested pairing, which provides interpretable, granular supports for inference.

  5. The AI can perform a pre-flight check for binary treatments by calculating the binary-treatment granularity floor, ensuring that no rejection is possible at any level unless the necessary sample size conditions are met, providing a data-driven constraint on test feasibility.

Abstract

In fixed-effect regressions with many groups, a handful of observations can carry most of the identifying variation left after fixed effects are removed. Conventional t-tests can then reject a true null more than half the time. This paper specializes the exact t-test of Pouliot to such designs. Contrasts chosen from the design eliminate the nuisance coefficients exactly; sign flips give finite-sample valid tests under independent symmetric errors, or compatible independent symmetric error blocks, allowing arbitrary heteroskedasticity. In two-way designs, the annihilating space is the cycle space of the bipartite observation graph and contains all within variation. This makes the choice of contrasts a graph problem. The observable capture ratio κ C in[0,1] measures retained identifying variation and, under diffuse homoskedastic conditions, gives the efficiency relative to an oracle test. Structured packing trades capture against the number and balance of usable signs. The matched-weight test is also asymptotically valid without symmetry when independent centered contrast scores satisfy a fourth-moment negligibility condition. In the Grunfeld investment regression, where one observation carries 73.9% of the realized squared score, 32 contrasts capture κ C=0.627 and give a symmetry-based exact 95% confidence interval of [0.150, 0.450].

Sources

Related papers