Indirect Inference Research Articles

How Much Price Stickiness in Hong Kong? —Evidence from Small Open Economy DSGE and Indirect Inference

How Much Price Stickiness in Hong Kong? —Evidence from Small Open Economy DSGE and Indirect Inference

The Influence of Food Names with Different Levels of Concreteness on Evaluations of Food Deliciousness and Healthiness.

Recently, many restaurateurs in the food and beverage industry started using vague and abstract names to label their dishes. However, the influence of the concreteness of food names on consumers' evaluations of food remains unclear. Therefore, the present study investigated people's perceptions of food names with different levels of concreteness and their evaluations of food deliciousness and healthiness through two experiments. Experiment 1 investigated the likelihood of names with different levels of concreteness being perceived as foods or dishes through subjective guessing tasks. In line with the hypothesis of mental imagery consistency, the results revealed that individuals were more inclined to perceive high-concreteness names as actual food or dishes than low-concrete names. Experiment 2 further explored the impact of food names with different levels of concreteness on consumers' perceptions and evaluations of food in terms of the direct sensory (deliciousness) and indirect inference (healthiness) dimension. The results showed that in terms of deliciousness, consistent with the feelings-as-information theory, high-concreteness food names were rated significantly higher than low-concreteness ones. In terms of healthiness, consistent with the incongruence theory, low-concreteness food names were rated significantly higher than high-concreteness ones. These results indicated that high-concreteness names were more likely to be perceived as foods or dishes. Moreover, they also had advantages in the direct sensory dimension (deliciousness) but were perceived as less healthy in the indirect inference dimension (healthiness). The present findings provide new evidence for studies related to food naming and the evaluation of deliciousness and healthiness and offer suggestions and strategies for the food and beverage industry in naming foods and dishes.

Undisclosed facts in Friedrich Wegener's links with Nazism.

Friedrich Wegener was the author of a comprehensive description of a disease that was named Wegener's granulomatosis. In 2010, its name was changed to granulomatosis with polyangiitis (GPA), the reason being that Wegener's links to Nazism were revealed. The research was conducted between May 2021 and August 2023 and was based on the historical method (understood as defining the subject of research, critical analysis of collected historical source materials, and historiographical synthesis) using the methods of direct and indirect inference ascribed to the historical method. Wegener and his wife were members of numerous Nazi organizations. He was rewarded for his stance by the German Reich. Together with his family, he lived in very comfortable conditions for the standards of the time, unattainable for the average person. He described himself as a frontline combatant in the Nazi invasion of Poland. Friedrich Wegener's links with Nazism were more extensive than has hitherto been known. The links involved his professional and private life. They testify to his membership in numerous Nazi organizations, as well as his active involvement in the activities of various institutions and communities of the German Reich and his overt expression of support for Hitler. Wegener's numerous accolades from the German Reich providing him with professional, material and personal benefits were proof of his links with the Nazi movement. Wegener's association with Nazism helped him to advance his career, and to attain a high social status and quality of life, both before the outbreak and during the Second World War.

What does housing collateral mean for Hong Kong economy? From the perspective of modelling and policy implication

This paper studies the housing sector of Hong Kong and the role of collateral constraint in modelling Hong Kong economy, through the lens of a small open economy DSGE model with a currency board exchange rate commitment. By estimating and evaluating the model by Indirect Inference over the sample period of 1994Q1–2018Q3, it is found that the collateral model can match data behaviour. Comparing with the tests generated from the model without collateral, collateral model can match the housing price data better, while the model without collateral fits the general price better. Since collateral constraint acts like an additional transmission channel, it enhances the impact from shocks and housing price is highly determined by housing demand. We further investigate LTV policy, finding it could be applied as macroprudential policy, especially when addressing the problem caused by increase in the US interest rate and the burst in the domestic housing demand, but the government should watch closely to the crowding out effect from export to housing demand and housing investment.

News or animal spirits? Consumer confidence and economic activity: Redux

SummaryBarsky and Sims (2012, AER) demonstrated, via indirect inference, that confidence innovations can be viewed as noisy signals about medium‐term economic growth. They highlighted that the connection between confidence and subsequent activity, such as consumption and output, is primarily driven by news shocks about the future. We expand upon their research by incorporating the Great Recession and ZLB episodes, during which animal spirits have a greater potential to influence economic activity. Nevertheless, we confirm the main finding of Barsky and Sims (2012) that this relationship is predominantly driven by news about the future rather than animal spirits.

Bayesian estimation of large-scale simulation models with Gaussian process regression surrogates

Large scale, computationally expensive simulation models pose a particular challenge when it comes to estimating their parameters from empirical data. Most simulation models do not possess closed-form expressions for their likelihood function, requiring the use of simulation-based inference, such as simulated method of moments, indirect inference, likelihood-free inference or approximate Bayesian computation. However, given the high computational requirements of large-scale models, it is often difficult to run these estimation methods, as they require more simulated runs that can feasibly be carried out. The aim is to address the problem by providing a full Bayesian estimation framework where the true but intractable likelihood function of the simulation model is replaced by one generated by a surrogate model trained on the limited simulated data. This is provided by a Linear Model of Coregionalization, where each latent variable is a sparse variational Gaussian process, chosen for its desirable convergence and consistency properties. The effectiveness of the approach is tested using both a simulated Bayesian computing analysis on a known data generating process, and an empirical application in which the free parameters of a computationally demanding agent-based model are estimated on US macroeconomic data.

Ambiguity Aversion and Heterogeneity in Households’ Beliefs

UK households that wish for lower inflation and lower nominal interest rates have higher expected inflation. We interpret the evidence through the lens of a New Keynesian model where ambiguity-averse households differ in wealth, skill, labor market participation, and the receipt of government transfers and are subject to Knightian uncertainty. Households act based on beliefs that are negatively affected by their wishes, the more so the greater the amount of uncertainty. Using indirect inference, we find substantial output costs due to uncertainty. Monetary policy uncertainty contributes little to the costs because households generally dislike monetary expansions. (JEL D12, D81, D83, E12, E31, E43, E52)

TinyMSI: A cost-effective handheld device for non-contact diabetic wound monitoring

Devices characterizing diabetic foot ulcers and other wounds currently fall into two categories. Expensive clinically-oriented devices that use mature technologies such as X-ray CT and hyperspectral imaging or low-cost solutions that leverage deep learning to infer wound characterization from conventional smartphone camera images or simple surrogate markers. Mature medical-grade devices are too expensive for primary care and assisted living facilities. Low-cost solutions rely too much on indirect statistical inference to be clinically suitable. Therefore, we propose a device that leverages mature, clinically suitable optical technologies to provide a solution for these facilities. Recognizing that individual combinations of 1–2 bands of active illumination are used individually to capture pulsation, vascular, and oxygenation images. We combine all these bands into a single multispectral lighting source to create a multi-functional, reliable device for wound assessment. We selected these bands to leverage CMOS cameras near orthogonality between the RGB channels and leverage that CMOS cameras can also sense near IR light if a filter is not present, reducing overall system complexity and needed bands. For each function, the necessary lights are turned on, and the captured raw video is then fed to the corresponding sequence of image processing steps. No deep learning models are used, so large training datasets are not required. Our device is also small, lightweight, and handheld.

Research Status of Haplotype Assembly Technology

Haplotype, also called haploid genotype, refers to the combination of a series of variant loci located on the same chromosome. Most of the current assembly algorithms ignore the heterozygous SNP variant sites on the chromosome and assemble a pseudohaplotype sequence. Due to the importance of haplotypes for the treatment of diseases, the mining of pathogenic genes and other medical organisms, haplotype analysis methods have become particularly important. At present, the indirect haplotype inference technology mainly includes two types: the alignment-based haplotyping algorithm and the assembly-based haplotyping method. This paper briefly summarizes the current typical haplotype indirect regression technology, and also looks forward to the future of haplotype typing technology.

Adjusted Indirect Treatment Comparison of Progression-Free Survival with D-Rd and VRd Based on MAIA and SWOG S0777 Individual Patient-Level Data.

Daratumumab plus lenalidomide and dexamethasone (D-Rd) and bortezomib plus lenalidomide and dexamethasone (VRd) are commonly used treatment combinations for transplant-ineligible (TIE) patients with newly diagnosed multiple myeloma (NDMM). D-Rd and VRd demonstrated superior efficacy relative to lenalidomide and dexamethasone (Rd) in the MAIA and SWOG S0777 trials, respectively, but have not been compared directly in a head-to-head trial. Naïve comparisons of efficacy across the two trials may be biased because MAIA enrolled only TIE patients (median age 73years), whereas SWOG S0777 enrolled both TIE patients and transplant-eligible patients who chose to defer/refuse frontline stem cell transplantation (median age 63years). The present study compared progression-free survival (PFS) in TIE patients with NDMM treated with D-Rd versus VRd based on an adjusted indirect treatment comparison (ITC) that leveraged individual patient-level data from MAIA and SWOG S0777. Harmonized inclusion/exclusion criteria (including age ≥ 65years as a proxy for transplant ineligibility) and propensity-score weighting were used to balance the trial populations on measured baseline characteristics. After differences in trial populations were adjusted for, an anchored ITC was performed wherein within-trial PFS hazard ratios (HRs) for D-Rd versus Rd and VRd versus Rd were estimated and used to make indirect inference about PFS for D-Rd versus VRd. PFS HRs were 0.52 (95% confidence interval [CI] 0.41-0.67) for D-Rd versus Rd based on MAIA data, 0.88 (95%CI 0.63-1.23) for VRd versus Rd based on SWOG S0777 data, and 0.59 (95%CI 0.39-0.90) for the Rd-anchored ITC of D-Rd versus VRd. Sensitivity and subgroup analyses produced results consistent with the primary results. This anchored ITC demonstrated a greater PFS benefit for D-Rd versus VRd in TIE patients with NDMM. In the absence of head-to-head trials comparing D-Rd and VRd, the present trial may help inform treatment selection in this patient population.

Earnings, labor market dynamics, and inequality in Sweden

AbstractIn this paper, we develop a comprehensive model of earnings and labor market dynamics, where employment and job change are endogenous. The model is estimated by applying the method of indirect inference on Swedish register data, and then used to carry out some policy experiments. There are three key conclusions from these experiments. First, employment shocks early in life can, to a larger extent, be mitigated before retirement compared with employment shocks occurring later. Second, we find that idiosyncratic productivity shocks, unobserved heterogeneity, and education contribute substantially to life‐cycle earnings inequality. Finally, we find that transitory shocks to employment risk have negative effects on earnings and employment in the short run but may increase labor market fluidity in the medium run.

Characterizing Ice Nucleating Particles Over the Southern Ocean Using Simultaneous Aircraft and Ship Observations

AbstractSupercooled liquid clouds are ubiquitous over the Southern Ocean (SO), even to temperatures below −20°C, and comprise a large fraction of the marine boundary layer (MBL) clouds. Earth system models and reanalysis products have struggled to reproduce the observed cloud phase distribution and occurrence of cloud ice in the region. Recent simulations found the microphysical representation of ice nucleation and growth has a large impact on these properties, however, measurements of SO ice nucleating particles (INPs) to validate simulations are sparse. This study presents measurements of INPs from simultaneous aircraft and ship campaigns conducted over the SO in austral summer 2018, which include the first in situ observations in and above cloud in the region. Our results confirm recent observations that INP concentrations are uniformly lower than measurements made in the late 1960s. While INP concentrations below and above cloud are similar, higher ice nucleation efficiency above cloud supports model simulations that the dominant INP composition varies with height. Model parameterizations based solely on aerosol properties capture the mean relationship between INP concentration and temperature but not the observed variability, which is likely related to the only modest correlations observed between INPs and environmental or aerosol metrics. Including wind speed in addition to activation temperature in a marine INP parameterization reduces bias but does not explain the large range of observed INP concentrations. Direct and indirect inference of marine INP size suggests MBL INPs, at least during Austral summer, are dominated by particles with diameters smaller than 500 nm.

Effective signal reconstruction from multiple ranked lists via convex optimization

The ranking of objects is widely used to rate their relative quality or relevance across multiple assessments. Beyond classical rank aggregation, it is of interest to estimate the usually unobservable latent signals that inform a consensus ranking. Under the only assumption of independent assessments, which can be incomplete, we introduce indirect inference via convex optimization in combination with computationally efficient Poisson Bootstrap. Two different objective functions are suggested, one linear and the other quadratic. The mathematical formulation of the signal estimation problem is based on pairwise comparisons of all objects with respect to their rank positions. Sets of constraints represent the order relations. The transitivity property of rank scales allows us to reduce substantially the number of constraints associated with the full set of object comparisons. The key idea is to globally reduce the errors induced by the rankers until optimal latent signals can be obtained. Its main advantage is low computational costs, even when handling n<<p\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$n < < p$$\\end{document} data problems. Exploratory tools can be developed based on the bootstrap signal estimates and standard errors. Simulation evidence, a comparison with the state-of-the-art rank centrality method, and two applications, one in higher education evaluation and the other in molecular cancer research, are presented.

Indirect Inference&amp;amp;#8212;A Methodological Essay on Its Role and Applications

Indirect Inference&amp;amp;#8212;A Methodological Essay on Its Role and Applications

The impacts of wild boars (Sus scrofa) on fish community and on instream physical habitat of two small streams in a protected area in Brazil

Abstract Despite the wild boar’s alarming invasive status, little is known about its impacts on aquatic environments. We assessed whether there were changes in the physical habitat of Neotropical streams and their ichthyofaunas after the record of wild boar populations in a conservation unit in Southeastern Brazil. We characterized the physical habitat and the fish community of two streams five times between 2009 and 2022. We found differences after the wild boar invasion. The amount of fine sediment inside the streams and exposed soil increased, while the bank angle decreased. There were also modifications regarding the fish fauna, including the local disappearance of two species and the constant decline of others. Although the sampling design does not allow for the establishment of a cause-effect relationship, these changes appear to be related to alterations in the physical habitats due to the wild boar’ behavior of forming large puddles in the stream beds. This is the first long-term study to make indirect inference of a possible effect of wild boar invasion on fish community level on streams. We highlight the urgent need for similar studies in aquatic environments, especially in tropical regions, where the abundance and distribution of wild boars are increasing.

Wage Rigidity and Employment Outcomes: Evidence from Administrative Data

This paper examines the relationship between downward nominal wage rigidity and employment outcomes using linked employer-employee data. Wage rigidity prevents 27.1 percent of counterfactual wage cuts, with a standard deviation of 19.2 percent across establishments. An establishment with the sample-average level of wage rigidity is predicted to have a 3.3 percentage point higher layoff rate, a 7.4 percentage point lower quit rate, and a 2.0 percentage point lower hire rate. Estimating a structural model by indirect inference implies that the cost of a nominal wage cut is 33 percent of an average worker’s annual compensation. (JEL E24, J23, J31, J63, M51)

Comparative Analysis of Hospital Outcomes for Thrombotic Thrombocytopenic Purpura between 2018 and 20120: A National Inpatient Sample Database Study

Background: Thrombotic Thrombocytopenic Purpura (TTP) is a rare, life-threatening hematological emergency with a mortality rate of up to 20%. While plasma exchange and immunosuppression have long been the “pillars” of therapy, since 2019, a novel targeted therapy, caplacizumab, has become available. This study aims to analyze hospital outcomes before and after 2019 to assess the potential impact of this therapeutic advancement. Methods: A retrospective analysis of the United States (US) National Inpatient Sample (NIS) database was conducted using International Classification of Diseases (ICD-10) codes to identify TTP patients in 2018 and 2020. The data were analyzed using STATA version MP14.2. Fischer's exact test, student's t-test, and multivariate regression analysis were used to compare proportions and continuous variables and calculate the adjusted odds ratio. The database, however, did not consistently specify which patients received specific therapeutics like rituximab and caplacizumab and which patients did not. Results: The study included 1120 TTP hospitalization in 2018 and 975 in 2020. The majority of patients were African Americans (52.1% in 2018, 46.4% in 2020) and females (67.9% in 2018, 68.7% in 2020); 1.6% had COVID-19 infection in 2020, with a mean Charlson comorbidity Index (CCI) of 1.28 in 2018 vs. 1.34 in 2020. The multivariate analysis after controlling age, sex, CCI, and primary payer, revealed no significant change in the rates of stroke (AOR: 0.94, 95% CI: 0.64-1.40, P = 0.77), myocardial infarction (AOR: 1.01, 95% CI: 0.70-1.46, P = 0.95), acute kidney injury (AOR: 0.91, 95% CI: 0.72-1.14, P = 0.398), acute bleeding (AOR: 0.74, 95% CI: 0.51-1.09, P = 0.13), packed red blood cell transfusion (AOR: 0.95, 95% CI: 0.74-1.23, P = 0.71), and platelet transfusion (AOR: 1.20, 95% CI: 0.88-1.62, P = 0.25) in 2020 compared to 2018. Additionally, there were no significant changes in the mortality rate (AOR: 0.83, 95% CI: 0.52-1.33, P = 0.43) and mean length of hospital stay (12 vs. 11 days) in 2020. However, a significant increase in mean hospital cost ($189,749.9 vs. $267,835 US dollars, P&amp;lt;0.001), adjusted for inflation, was observed in 2020. A subgroup analysis was conducted for 50 patients who received caplacizumab in 2020, revealing higher average hospital costs ($465,665 vs. $241,665) and an increased rate of intracranial bleeding (10% vs. 1.6%) compared to patients whose caplacizumab usage was unknown. Mortality was observed in none of the known caplacizumab-treated samples, while 6.5% mortality was recorded among those without known caplacizumab use. Conclusion: Compared to 2018, 2020 hospitalizations had a substantial increase in costs without a significant change in patient outcomes. This probability is related to the COVID-19 pandemic and the advent of caplacizumab use in the US. We were unable to sort out the impact of other costly therapeutics like rituximab. However, it would be given less frequently. Further study is needed to explore this indirect inference from the NIS database analysis and the attendant cost-benefit implications in the management of TTP and its impact on patient outcomes.

Indirect inference approach for parameter estimation of non linear manoeuvring models of a ROV based on model basin trials

ABSTRACT In this work, indirect inference (II) techniques are applied to estimate the parameters of a non-linear manoeuvring model of a remotely operated vehicle (ROV). In the application of this method, a set of auxiliary statistics is established in the optimisation process in order to improve the efficiency of the estimated parameters. For the parameter estimation, data from different tests are available, which were carried out with a ROV in the facilities of the Centro de Experiencias Hidrodinámicas del Pardo INTA/CEHIPAR, Madrid. The model obtained is validated by means of graphical and statistical methods with the acquired data and the statistical properties of the estimated parameters are evaluated by means of a Monte Carlo study.

Indirect Inference and Small Sample Bias — Some Recent Results

Macroeconomic researchers use a variety of estimators to parameterise their models empirically. One such is FIML; another is indirect inference (II). One form of indirect inference is ‘informal’ whereby data features are ‘targeted’ by the model — i.e. parameters are chosen so that model-simulated features replicate the data features closely. Monte Carlo experiments show that in the small samples prevalent in macro data, both FIML informal II produce high bias, while formal II, in which the joint probability of the data- generated auxiliary model is maximised under the model simulated distribution, produces low bias. They also show that FII gets this low bias from its high power in rejecting misspecified models, which comes in turn from the fact that this distribution is restricted by the model-specified parameters, so sharply distinguishing it from rival misspecified models.

Testing competing world trade models against the facts of world trade

We carry out an indirect inference test of two versions of a computable general equilibrium (CGE) model of world trade. One of these, the ‘classical’ model, is well-known as the Heckscher-Ohlin-Samuelson model of world trade, in which countries trade homogeneous products in world markets and produce according to their comparative advantage as determined by their resource endowments. The other, the ‘gravity’ model, assumes products are differentiated by geographical origin, so that trade is determined largely by demand and relative prices differing according to distance; trade in turn affects productivity through technology transfer. These two CGE models of world trade behave in very different ways and predict quite different effects for trade policy, underlining the importance of discovering which best fits the facts of international trade. Our findings here are that the classical model fits these facts fairly well in general, while the gravity model is largely strongly rejected by them.