Empirical Policy Function Benchmarks for Evaluation and Estimation of Dynamic Models,”

SSRN

Santiago Bazdresch, Jay Kahn, Toni Whited

Research output: Other contribution

Abstract

We describe a set of model dependent statistical benchmarks that can be used to estimate and evaluate dynamic models of firms' investment and financing. The benchmarks characterize the empirical counterparts of the models' policy functions. These empirical policy functions (EPFs) are intuitively related to the corresponding model, their features can be estimated very easily and robustly, and they describe economically important aspects of firms' dynamic behavior. We calculate the benchmarks for a traditional trade-off model using Compustat data and use them to estimate some of its parameters. We present two Monte Carlo exercises. One shows that both moments-based and EPF-based estimation have low average bias and variance. The other shows that EPF based tests are dramatically better at detecting misspecification than analogous tests from moments based estimation.
Original languageEnglish
StatePublished - Jul 30 2014

Fingerprint

Evaluation
Benchmark
Policy function
Trade-offs
Exercise
Firm investment
Firm dynamics
Misspecification
Financing

Bibliographical note

Type: Manuscript

Cite this

Empirical Policy Function Benchmarks for Evaluation and Estimation of Dynamic Models,” : SSRN. / Bazdresch, Santiago; Kahn, Jay; Whited, Toni.

2014, .

Research output: Other contribution

@misc{6f155666a1bd470ab410a94ec275017d,
title = "Empirical Policy Function Benchmarks for Evaluation and Estimation of Dynamic Models,”: SSRN",
abstract = "We describe a set of model dependent statistical benchmarks that can be used to estimate and evaluate dynamic models of firms' investment and financing. The benchmarks characterize the empirical counterparts of the models' policy functions. These empirical policy functions (EPFs) are intuitively related to the corresponding model, their features can be estimated very easily and robustly, and they describe economically important aspects of firms' dynamic behavior. We calculate the benchmarks for a traditional trade-off model using Compustat data and use them to estimate some of its parameters. We present two Monte Carlo exercises. One shows that both moments-based and EPF-based estimation have low average bias and variance. The other shows that EPF based tests are dramatically better at detecting misspecification than analogous tests from moments based estimation.",
author = "Santiago Bazdresch and Jay Kahn and Toni Whited",
note = "Type: Manuscript",
year = "2014",
month = "7",
day = "30",
language = "English",
type = "Other",

}

TY - GEN

T1 - Empirical Policy Function Benchmarks for Evaluation and Estimation of Dynamic Models,”

T2 - SSRN

AU - Bazdresch, Santiago

AU - Kahn, Jay

AU - Whited, Toni

N1 - Type: Manuscript

PY - 2014/7/30

Y1 - 2014/7/30

N2 - We describe a set of model dependent statistical benchmarks that can be used to estimate and evaluate dynamic models of firms' investment and financing. The benchmarks characterize the empirical counterparts of the models' policy functions. These empirical policy functions (EPFs) are intuitively related to the corresponding model, their features can be estimated very easily and robustly, and they describe economically important aspects of firms' dynamic behavior. We calculate the benchmarks for a traditional trade-off model using Compustat data and use them to estimate some of its parameters. We present two Monte Carlo exercises. One shows that both moments-based and EPF-based estimation have low average bias and variance. The other shows that EPF based tests are dramatically better at detecting misspecification than analogous tests from moments based estimation.

AB - We describe a set of model dependent statistical benchmarks that can be used to estimate and evaluate dynamic models of firms' investment and financing. The benchmarks characterize the empirical counterparts of the models' policy functions. These empirical policy functions (EPFs) are intuitively related to the corresponding model, their features can be estimated very easily and robustly, and they describe economically important aspects of firms' dynamic behavior. We calculate the benchmarks for a traditional trade-off model using Compustat data and use them to estimate some of its parameters. We present two Monte Carlo exercises. One shows that both moments-based and EPF-based estimation have low average bias and variance. The other shows that EPF based tests are dramatically better at detecting misspecification than analogous tests from moments based estimation.

M3 - Other contribution

ER -