Econometrica 2023年第1期

?

?

——更多動態(tài)，請持續(xù)關(guān)注gzh：理想主義的百年孤獨(dú)

?

?

1.Invidious Comparisons: Ranking and Selection as Compound Decisions

令人反感的比較:作為復(fù)合決策的排名和選擇

Jiaying Gu, Roger Koenker

There is an innate human tendency, one might call it the “l(fā)eague table mentality,” to construct rankings. Schools, hospitals, sports teams, movies, and myriad other objects are ranked even though their inherent multi‐dimensionality would suggest that—at best—only partial orderings were possible. We consider a large class of elementary ranking problems in which we observe noisy, scalar measurements of merit for?n?objects of potentially heterogeneous precision and are asked to select a group of the objects that are “most meritorious.” The problem is naturally formulated in the compound decision framework of Robbins's (1956) empirical Bayes theory, but it also exhibits close connections to the recent literature on multiple testing. The nonparametric maximum likelihood estimator for mixture models (Kiefer and Wolfowitz (1956)) is employed to construct optimal ranking and selection rules. Performance of the rules is evaluated in simulations and an application to ranking U.S. kidney dialysis centers.

人類有一種天生的傾向，人們可以稱之為“排名心態(tài)”，來構(gòu)建排名。學(xué)校、醫(yī)院、運(yùn)動隊(duì)、電影和無數(shù)其他物體被排序，盡管它們固有的多維度表明——最多只能進(jìn)行部分排序——是可能的。我們考慮了一類很大的基本排序問題，在這些問題中，我們觀察到n個具有潛在異質(zhì)性精度的對象的噪聲、標(biāo)量值的優(yōu)點(diǎn)測量，并被要求選擇一組”最有價值”的對象。這個問題在Robbins(1956)的經(jīng)驗(yàn)貝葉斯理論的復(fù)合決策框架中很自然地得到了闡述，但它也與最近關(guān)于多重檢驗(yàn)的文獻(xiàn)表現(xiàn)出了密切的聯(lián)系。混合模型的非參數(shù)極大似然估計(jì)(Kiefer and Wolfowitz, 1956)被用來構(gòu)造最優(yōu)排序和選擇規(guī)則。這些規(guī)則的表現(xiàn)在模擬和美國腎臟透析中心排名的應(yīng)用程序中進(jìn)行評估。

?

?

2.Misallocation and Capital Market Integration: Evidence From India

錯配與資本市場一體化:來自印度的證據(jù)

https://doi.org/10.3982/ECTA19039

Natalie Bau, Adrien Matray

We show that foreign capital liberalization reduces capital misallocation and increases aggregate productivity for affected industries in India. The staggered liberalization of access to foreign capital across disaggregated industries allows us to identify changes in firms' input wedges, overcoming major challenges in the measurement of the effects of changing misallocation. Liberalization increases capital overall. For domestic firms with initially high marginal revenue products of capital (MRPK), liberalization increases revenues by 23%, physical capital by 53%, wage bills by 28%, and reduces MRPK by 33% relative to low MRPK firms. The effects of liberalization are largest in areas with less developed local banking sectors, indicating that inefficiencies in that sector may cause misallocation. Finally, we propose an assumption under which a novel method exploiting natural experiments can be used to bound the effect of changes in misallocation on treated industries' aggregate productivity. These industries' Solow residual increases by 3–16%.

我們表明，外國資本自由化減少了資本錯配，并提高了印度受影響行業(yè)的總生產(chǎn)率。在各個細(xì)分行業(yè)逐步放開外資準(zhǔn)入，使我們能夠發(fā)現(xiàn)企業(yè)投入楔的變化，克服了在衡量不斷變化的錯配影響方面的重大挑戰(zhàn)。自由化總體上增加了資本。相對于資本邊際收益產(chǎn)品(MRPK)較低的國內(nèi)企業(yè)，自由化使其收入增加23%，實(shí)物資本增加53%，工資支出增加28%，MRPK降低33%。自由化的影響在當(dāng)?shù)劂y行部門較不發(fā)達(dá)的地區(qū)最大，這表明該部門的低效率可能導(dǎo)致分配不當(dāng)。最后，我們提出了一個假設(shè)，在這個假設(shè)下，一種利用自然實(shí)驗(yàn)的新方法可以用來約束錯配變化對處理過的行業(yè)總生產(chǎn)率的影響。這些行業(yè)的索洛剩余增加了3-16%。

?

?

3.Nonparametric Estimates of Demand in the California Health Insurance Exchange

加州健康保險交易所需求的非參數(shù)估計(jì)

https://doi.org/10.3982/ECTA17215

Pietro Tebaldi, Alexander Torgovitsky, Hanbin Yang

We develop a new nonparametric approach for discrete choice and use it to analyze the demand for health insurance in the California Affordable Care Act marketplace. The model allows for endogenous prices and instrumental variables, while avoiding parametric functional form assumptions about the unobserved components of utility. We use the approach to estimate bounds on the effects of changing premiums or subsidies on coverage choices, consumer surplus, and government spending on subsidies. We find that a $10 decrease in monthly premium subsidies would cause a decline of between 1.8% and 6.7% in the proportion of subsidized adults with coverage. The reduction in total annual consumer surplus would be between $62 and $74 million, while the savings in yearly subsidy outlays would be between $207 and $602 million. We estimate the demand impacts of linking subsidies to age, finding that shifting subsidies from older to younger buyers would increase average consumer surplus, with potentially large impacts on enrollment. We also estimate the consumer surplus impact of removing the highly‐subsidized plans in the Silver metal tier, where we find that a nonparametric model is consistent with a wide range of possibilities. We find that comparable mixed logit models tend to yield price sensitivity estimates toward the lower end of the nonparametric bounds, while producing consumer surplus impacts that can be both higher and lower than the nonparametric bounds depending on the specification of random coefficients.

我們?yōu)殡x散選擇開發(fā)了一種新的非參數(shù)方法，并用它來分析加州平價醫(yī)療法案市場對健康保險的需求。該模型允許內(nèi)生價格和工具變量，同時避免了關(guān)于效用未觀察到的成分的參數(shù)函數(shù)形式假設(shè)。我們使用該方法來估計(jì)改變保費(fèi)或補(bǔ)貼對保險范圍選擇、消費(fèi)者剩余和政府補(bǔ)貼支出的影響界限。我們發(fā)現(xiàn)，每月保費(fèi)補(bǔ)貼減少10美元，將導(dǎo)致獲得補(bǔ)貼的成年人比例下降1.8%至6.7%。全年消費(fèi)者剩余總額將減少6400萬元至7400萬元，而每年的補(bǔ)貼支出將節(jié)省2.07億元至6.02億元。我們估計(jì)了將補(bǔ)貼與年齡掛鉤的需求影響，發(fā)現(xiàn)將補(bǔ)貼從年齡較大的買家轉(zhuǎn)移到年齡較小的買家將增加平均消費(fèi)者剩余，這可能對入學(xué)率產(chǎn)生巨大影響。我們還估計(jì)了在銀金屬層取消高補(bǔ)貼計(jì)劃對消費(fèi)者剩余的影響，在那里我們發(fā)現(xiàn)非參數(shù)模型與廣泛的可能性是一致的。我們發(fā)現(xiàn)，可比較的混合logit模型傾向于產(chǎn)生價格敏感性估計(jì)，接近非參數(shù)邊界的下端，同時產(chǎn)生的消費(fèi)者剩余影響可能高于或低于非參數(shù)邊界，這取決于隨機(jī)系數(shù)的規(guī)范。

?

?

4.Nexus Tax Laws and Economies of Density in E-Commerce: A Study of Amazon's Fulfillment Center Network

電子商務(wù)中的Nexus稅法與密度經(jīng)濟(jì):亞馬遜配送中心網(wǎng)絡(luò)研究

https://doi.org/10.3982/ECTA15265
p. 147-190

Jean‐Fran?ois Houde, Peter Newberry, Katja Seim

We quantify the distortionary effects of nexus tax laws on Amazon's distribution network investments between 1999 and 2018. We highlight the role of two features of the expansion of Amazon's network: densification of the network of distribution facilities and vertical integration into package sortation. Densification results in a reduction in the cost of shipping orders, but comes at the expense of higher facility operating costs in more expensive areas and lower scale economies of processing shipments. Nexus laws furthermore generate additional sales tax liabilities as the network grows. Combining data on household spending across online and offline retailers with detailed data on Amazon's distribution network, we quantify these trade‐offs through a static model of demand and a dynamic model of investment. Our results suggest that Amazon's expansion led to significant shipping cost savings and facilitated the realization of aggregate economies of scale. We find that abolishing nexus tax laws in favor of a non‐discriminatory tax policy would induce the company to decentralize its network, lowering its shipping costs. Non‐discriminatory taxation would also entail lower revenue, however, as tax‐inclusive prices would rise, resulting in a fall in profit overall. This drop and the decline in consumer welfare from higher taxes together fall short of the increases in tax revenue and rival profit, suggesting that the abolishment of nexus laws would lead to an increase in total welfare.

我們量化了1999年至2018年期間nexus稅法對亞馬遜分銷網(wǎng)絡(luò)投資的扭曲影響。我們強(qiáng)調(diào)了亞馬遜網(wǎng)絡(luò)擴(kuò)張的兩個特點(diǎn)的作用:配送設(shè)施網(wǎng)絡(luò)的密集化和包裝分類的垂直整合。致密化的結(jié)果是降低了運(yùn)輸訂單的成本，但代價是在更昂貴的地區(qū)增加了設(shè)施運(yùn)營成本，并降低了加工運(yùn)輸?shù)囊?guī)模經(jīng)濟(jì)。隨著網(wǎng)絡(luò)的增長，Nexus法律還產(chǎn)生了額外的銷售稅負(fù)債。我們將線上和線下零售商的家庭支出數(shù)據(jù)與亞馬遜分銷網(wǎng)絡(luò)的詳細(xì)數(shù)據(jù)相結(jié)合，通過靜態(tài)需求模型和動態(tài)投資模型來量化這些權(quán)衡。我們的研究結(jié)果表明，亞馬遜的擴(kuò)張帶來了顯著的運(yùn)輸成本節(jié)約，并促進(jìn)了總體規(guī)模經(jīng)濟(jì)的實(shí)現(xiàn)。我們發(fā)現(xiàn)，廢除nexus稅法，支持非歧視性稅收政策，將誘使該公司分散其網(wǎng)絡(luò)，降低其運(yùn)輸成本。然而，由于含稅價格將上升，非歧視性稅收也將導(dǎo)致收入減少，從而導(dǎo)致整體利潤下降。這種下降和更高稅收帶來的消費(fèi)者福利下降加在一起，沒有達(dá)到稅收收入和競爭對手利潤的增長，這表明廢除關(guān)系法將導(dǎo)致總福利的增加。

?

?

5.Graphon games: A statistical framework for network games and interventions

Graphon games:網(wǎng)絡(luò)游戲和干預(yù)的統(tǒng)計(jì)框架

https://doi.org/10.3982/ECTA17564
Francesca Parise, Asuman Ozdaglar

In this paper, we present a unifying framework for analyzing equilibria and designing interventions for large network games sampled from a stochastic network formation process represented by a graphon. To this end, we introduce a new class of infinite population games, termed?graphon games, in which a continuum of heterogeneous agents interact according to a graphon, and we show that equilibria of graphon games can be used to approximate equilibria of large network games sampled from the graphon. This suggests a new approach for design of interventions and parameter inference based on the limiting infinite population graphon game. We show that, under some regularity assumptions, such approach enables the design of asymptotically optimal interventions via the solution of an optimization problem with much lower dimension than the one based on the entire network structure. We illustrate our framework on a synthetic data set and show that the graphon intervention can be computed efficiently and based solely on aggregated relational data.

在本文中，我們提出了一個統(tǒng)一的框架，用于分析大型網(wǎng)絡(luò)博弈的均衡和設(shè)計(jì)干預(yù)措施，這些措施來自一個以石墨子為代表的隨機(jī)網(wǎng)絡(luò)形成過程。為此，我們引入了一類新的無限群體博弈，稱為graphon博弈，在這種博弈中，一個連續(xù)的異質(zhì)代理根據(jù)一個graphon相互作用，我們證明了graphon博弈的均衡可以用來近似從graphon采樣的大型網(wǎng)絡(luò)博弈的均衡。這為基于極限無限群體玻色子博弈的干預(yù)設(shè)計(jì)和參數(shù)推斷提供了一種新的方法。我們表明，在某些規(guī)則性假設(shè)下，這種方法能夠通過解決比基于整個網(wǎng)絡(luò)結(jié)構(gòu)的優(yōu)化問題低得多的維數(shù)來設(shè)計(jì)漸近最優(yōu)干預(yù)。我們在一個合成數(shù)據(jù)集上演示了我們的框架，并展示了graphon干預(yù)可以高效地計(jì)算，并且僅基于聚合的關(guān)系數(shù)據(jù)。

?

?

6.The Race Between Preferences and Technology

偏好和技術(shù)之間的競爭

https://doi.org/10.3982/ECTA18580
Joachim Hubmer

This paper argues that a unified analysis of consumption and production is required to understand the long‐run behavior of the U.S. labor share. First, using household data on the universe of consumer spending, I document that higher‐income households spend relatively more on labor‐intensive goods and services as a share of their total consumption. Interpreted as nonhomothetic preferences, this fact implies that economic growth increases the aggregate labor share through an income effect. Second, using disaggregated data on factor shares and capital intensities, I document that equipment‐intensive goods experienced relatively larger declines in their labor shares. Based on this finding, I estimate that capital and labor are gross substitutes, and that investment‐specific technical change reduces the labor share. Given the estimated elasticities, a parsimonious neoclassical model quantitatively matches the observed low‐frequency movements in the aggregate labor share since the 1950s, both its relative stability until about 1980 and its decline thereafter.

本文認(rèn)為，為了理解美國勞動收入占比的長期行為，需要對消費(fèi)和生產(chǎn)進(jìn)行統(tǒng)一的分析。首先，利用家庭消費(fèi)支出數(shù)據(jù)，我發(fā)現(xiàn)收入較高的家庭在勞動密集型商品和服務(wù)上的支出占總消費(fèi)的比例相對較高。這一事實(shí)被解釋為非同態(tài)偏好，意味著經(jīng)濟(jì)增長通過收入效應(yīng)提高了總勞動收入占比。其次，利用要素份額和資本密集度的分類數(shù)據(jù)，我證明了設(shè)備密集型商品的勞動份額經(jīng)歷了相對較大的下降?；谶@一發(fā)現(xiàn)，我估計(jì)資本和勞動力是總量替代品，特定于投資的技術(shù)變革降低了勞動占比?？紤]到估計(jì)的彈性，一個簡約的新古典模型定量地匹配了自20世紀(jì)50年代以來觀察到的總勞動收入占比的低頻運(yùn)動，包括1980年前后的相對穩(wěn)定和此后的下降。

?

?

7.Counterfactual Sensitivity and Robustness

反事實(shí)敏感性和穩(wěn)健性

https://doi.org/10.3982/ECTA17232

Timothy Christensen, Benjamin Connault

We propose a framework for analyzing the sensitivity of counterfactuals to parametric assumptions about the distribution of latent variables in structural models. In particular, we derive bounds on counterfactuals as the distribution of latent variables spans nonparametric neighborhoods of a given parametric specification while other “structural” features of the model are maintained. Our approach recasts the infinite‐dimensional problem of optimizing the counterfactual with respect to the distribution of latent variables (subject to model constraints) as a finite‐dimensional convex program. We also develop an MPEC version of our method to further simplify computation in models with endogenous parameters (e.g., value functions) defined by equilibrium constraints. We propose plug‐in estimators of the bounds and two methods for inference. We also show that our bounds converge to the sharp nonparametric bounds on counterfactuals as the neighborhood size becomes large. To illustrate the broad applicability of our procedure, we present empirical applications to matching models with transferable utility and dynamic discrete choice models.

我們提出了一個框架，用于分析反事實(shí)對結(jié)構(gòu)模型中潛在變量分布的參數(shù)假設(shè)的敏感性。特別是，當(dāng)潛在變量的分布跨越給定參數(shù)規(guī)范的非參數(shù)鄰域時，我們推導(dǎo)出反事實(shí)的邊界，而模型的其他“結(jié)構(gòu)”特征保持不變。我們的方法將無限維的反事實(shí)問題(針對潛在變量的分布(受制于模型約束)進(jìn)行優(yōu)化)重新塑造為有限維的凸程序。我們還開發(fā)了我們的方法的MPEC版本，以進(jìn)一步簡化由平衡約束定義的內(nèi)生參數(shù)(例如，值函數(shù))模型中的計(jì)算。我們提出了邊界的插入估計(jì)器和兩種推斷方法。我們還表明，當(dāng)鄰域大小變大時，我們的邊界收斂到反事實(shí)上的尖銳非參數(shù)邊界。為了說明我們的程序的廣泛適用性，我們提出了與可轉(zhuǎn)移效用和動態(tài)離散選擇模型匹配的實(shí)證應(yīng)用。

?

?

8.Inference for Large-Scale Linear Systems with Known Coefficients

已知系數(shù)的大規(guī)模線性系統(tǒng)的推理

https://doi.org/10.3982/ECTA18979

Zheng Fang, Andres Santos, Azeem M. Shaikh, Alexander Torgovitsky

This paper considers the problem of testing whether there exists a non‐negative solution to a possibly under‐determined system of linear equations with known coefficients. This hypothesis testing problem arises naturally in a number of settings, including random coefficient, treatment effect, and discrete choice models, as well as a class of linear programming problems. As a first contribution, we obtain a novel geometric characterization of the null hypothesis in terms of identified parameters satisfying an infinite set of inequality restrictions. Using this characterization, we devise a test that requires solving only linear programs for its implementation, and thus remains computationally feasible in the high‐dimensional applications that motivate our analysis. The asymptotic size of the proposed test is shown to equal at most the nominal level uniformly over a large class of distributions that permits the number of linear equations to grow with the sample size.

本文討論了一個已知系數(shù)的線性方程組是否存在非負(fù)解的檢驗(yàn)問題。這個假設(shè)檢驗(yàn)問題自然出現(xiàn)在許多設(shè)置中，包括隨機(jī)系數(shù)、處理效果和離散選擇模型，以及一類線性規(guī)劃問題。作為第一個貢獻(xiàn)，我們獲得了零假設(shè)在滿足無限不等式限制集的已識別參數(shù)方面的一個新的幾何特征。利用這一特性，我們設(shè)計(jì)了一種測試，它只需要求解線性程序即可實(shí)現(xiàn)，從而在激發(fā)我們分析的高維應(yīng)用程序中保持計(jì)算上的可行性。所提出的檢驗(yàn)的漸近大小表明，在允許線性方程的數(shù)量隨樣本量增長的大類別分布上，最多等于名義水平。