Inference in differences-in-differences with few treated groups and heteroskedasticity

Differences-in-Differences (DID) is one of the most widely used identification strategies in applied economics. However, how to draw inferences in DID models when there are few treated groups remains an open question. We show that the usual inference methods used in DID models might not perform well when there are few treated groups and errors are heteroskedastic. In particular, we show that when there is variation in the number of observations per group, inference methods designed to work when there are few treated groups tend to (under-) over-reject the null hypothesis when the treated groups are (large) small relative to the control groups. This happens because larger groups tend to have lower variance, generating heteroskedasticity in the group x time aggregate DID model. We provide evidence from Monte Carlo simulations and from placebo DID regressions with the American Community Survey (ACS) and the Current Population Survey (CPS) datasets to show that this problem is relevant even in datasets with large numbers of observations per group. We then derive an alternative inference method that provides accurate hypothesis testing in situations where there are few treated groups (or even just one) and many control groups in the presence of heteroskedasticity. Our method assumes that we can model the heteroskedasticity of a linear combination of the errors. We show that this assumption can be satisfied without imposing strong assumptions on the errors in common DID applications. With many pre-treatment periods, we show that this assumption can be relaxed. Instead, we provide an alternative inference method that relies on strict stationarity and ergodicity of the time series. Finally, we consider two recent alternatives to DID when there are many pre-treatment periods. We extend our inference methods to linear factor models when there are few treated groups. We also derive conditions under which a permutation test for the synthetic control estimator proposed by Abadie et al. (2010) is robust to heteroskedasticity and propose a modification on the test statistic that provided a better heteroskedasticity correction in our simulations.

Inference in differences-in-differences with few treated groups and heteroskedasticity

Differences-in-Differences (DID) is one of the most widely used identification strategies in applied economics. However, how to draw inferences in DID models when there are few treated groups remains an open question. We show that the usual inference methods used in DID models might not perform well when there are few treated groups and errors are heteroskedastic. In particular, we show that when there is variation in the number of observations per group, inference methods designed to work when there are few treated groups tend to (under-) over-reject the null hypothesis when the treated groups are (large) small relative to the control groups. This happens because larger groups tend to have lower variance, generating heteroskedasticity in the group x time aggregate DID model. We provide evidence from Monte Carlo simulations and from placebo DID regressions with the American Community Survey (ACS) and the Current Population Survey (CPS) datasets to show that this problem is relevant even in datasets with large numbers of observations per group. We then derive an alternative inference method that provides accurate hypothesis testing in situations where there are few treated groups (or even just one) and many control groups in the presence of heteroskedasticity. Our method assumes that we know how the heteroskedasticity is generated, which is the case when it is generated by variation in the number of observations per group. With many pre-treatment periods, we show that this assumption can be relaxed. Instead, we provide an alternative application of our method that relies on assumptions about stationarity and convergence of the moments of the time series. Finally, we consider two recent alternatives to DID when there are many pre-treatment groups. We extend our inference method to linear factor models when there are few treated groups. We also propose a permutation test for the synthetic control estimator that provided a better heteroskedasticity correction in our simulations than the test suggested by Abadie et al. (2010).

Structural and Biochemical Characterization of Peroxiredoxin Q beta from Xylella fastidiosa CATALYTIC MECHANISM and HIGH REACTIVITY

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Mechanism of infection and colonization of Rhipicephalus sanguineus eggs by Mertarhizium anisopliae as revealed by scanning eletron microscopy and histopathology

O presente trabalho teve como objetivo verificar a forma de penetração do fungo Metarhizium anisopliae em ovos do carrapato Rhipicephalus sanguineus, assim como as lesões infringidas no interior do ovo. A aderência e penetração do fungo foram estudadas por meio da microscopia eletrônica de varredura e a ação do fungo nos tecidos internos avaliada em secções histológicas convencionais. Para observação destes eventos, realizaram-se infecções experimentais em 11 grupos de ovos do R. sanguineus contendo 25 mg cada. Os ovos foram banhados durante 3 minutos, sob agitação manual, em suspensão com concentração de 10(8) conídios/mL. Nos grupos controle o banho foi realizado apenas no veículo da suspensão. Os ovos foram processados para análise histopatológica e microscopia eletrônica de varredura nos seguintes tempos após a infecção: 1 e 18h, e um, dois, três, quatro, cinco, seis, sete, nove e onze dias. Observou-se grande germinação de conídios em 67% dos ovos 18h após a inoculação e o fungo penetrou em 92,6% dos ovos 5 dias após a infecção. A extrusão do patógeno ocorreu em 87% dos ovos 7 dias após a infecção, chegando a 100% no 9º dia. Nas análises histopatológicas não foram observadas lesões dignas de nota, porem deve-se ressaltar que houve significativa redução (53,9%) na eclosão a partir dos ovos infectados.

Genetic parameter estimates for buffalo milk yield, milk quality and mozzarella production and Bayesian inference analysis of their relationships

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Bayesian inference in genetic parameter estimation of visual scores in Nellore beef-cattle

The aim of this study was to estimate the components of variance and genetic parameters for the visual scores which constitute the Morphological Evaluation System (MES), such as body structure (S), precocity (P) and musculature (M) in Nellore beef-cattle at the weaning and yearling stages, by using threshold Bayesian models. The information used for this was gleaned from visual scores of 5,407 animals evaluated at the weaning and 2,649 at the yearling stages. The genetic parameters for visual score traits were estimated through two-trait analysis, using the threshold animal model, with Bayesian statistics methodology and MTGSAM (Multiple Trait Gibbs Sampler for Animal Models) threshold software. Heritability estimates for S, P and M were 0.68, 0.65 and 0.62 (at weaning) and 0.44, 0.38 and 0.32 (at the yearling stage), respectively. Heritability estimates for S, P and M were found to be high, and so it is expected that these traits should respond favorably to direct selection. The visual scores evaluated at the weaning and yearling stages might be used in the composition of new selection indexes, as they presented sufficient genetic variability to promote genetic progress in such morphological traits.

Estimation of genetic parameters for milk yield in Murrah buffaloes by Bayesian inference

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Genetic parameters for buffalo milk yield and milk quality traits using Bayesian inference

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Genetic correlations between heifer subsequent rebreeding and age at first calving and growth traits in Nellore cattle by Bayesian inference

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

EFFICIENCY of PNEUMATIC and HORIZONTAL PERFORATED DISK METER MECHANISM IN CORN NO-TILLAGE SEEDERS IN SOIL WITH DIFFERENT MOBILIZATION REPORTS

This work objectified to evaluate the efficiency of two meter mechanism of corn seeds when submitted to different forward speed and soil management system during the non-tillage seeding. It was used a factorial design in randomized blocks. The factors whose effects were examined were related to the seeders with pneumatic and horizontal disk meter mechanisms for the distribution of the seeds, to the set tractor-seeder forward speeds (4.4; 8.0 and 9.8 km h(-1)), and to the soil management system considering the corn no-tillage seeding over minimum tillage with chisel plow and the no-tillage system for the seeding of oat culture (Avena strigosa Schreb). It was verified that the forward speed didn't influence the initial and final stands of plants but it interfered in the regularity of longitudinal distribution of plants. The smallest speed provided the largest percentile of normal spacing between plants. The pneumatic meter mechanism presented better performance than the horizontal disk perforated in the longitudinal distribution of plants. About corn productivity aspect it's indifferent the recommendation of use for pneumatic and perforated horizontal disk meter mechanism of seeds.

Mechanism of anticlastogenicity of Agaricus blazei Murill mushroom organic extracts in wild type CHO (K-1) and repair deficient (xrs5) cells by chromosome aberration and sister chromatid exchange assays

Agaricus blazei Murill is a medicinal mushroom native to Brazil. The present work assessed the clastogenic and anticlastogenic potential of organic extracts (ethanol and chloroform/methanol) from the lineage AB97/11 in chinese hamster CHO-K-1 (wild type) and CHO-xrs5 (repair deficient) cells using the chromosome aberration (CA) and sister chromatid exchange (SCE) assays. In these experimental conditions were observed: (a) anticlastogenic effect at concentrations of 0.06 and 0.09% of the EtOH extract and at the 0.03 and 0.06% concentrations of the C/MetOH extract in CHO-K-1; (b) absence of protector effect on CHO-xrs5 cells; and (c) absence of protector effect in the SCE assay. These results indicate that organic extracts of A. blazei lineage AB97/11 present bio-antimutagenic type protective activity. (C) 2003 Elsevier B.V. B.V. All rights reserved.

Mechanism and control of Genipa americana seed germination

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Interaction mechanism of poly (o-ethoxyaniline) and collagen blends

Blend films of poly (o-ethoxyaniline) (POEA) and collagen were fabricated by casting under optimized conditions and characterized by Raman scattering and UV-vis absorption spectroscopies. The UV-vis spectra showed that the addition of collagen in the aqueous solution of POEA promotes a dedoping of the POEA. This effect was also observed for the blend films as supported by Raman scattering and a mechanism for the chemical interaction between POEA-collagen is proposed. The influences of different percentage of collagen as well as the pH of stock solutions during the fabrication process of the blend films were also investigated. It was found that the preparation method plays an important role in the flexibility and freestanding properties of the films. Complementary, the surface morphology was studied by atomic force microscopy and the conductivity by dc measurements. (C) 2003 Elsevier Ltd. All rights reserved.

Iron phthalocyanine in non-aqueous medium forming layer-by-layer films: growth mechanism, molecular architecture and applications

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)