Search Results
Working Paper
Test Questions, Economic Outcomes, and Inequality
Standard achievement scales aggregate test questions without considering their relationship to economic outcomes. This paper uses question-level data to improve the measurement of achievement in two ways. First, the paper constructs alternative achievement scales by relating individual questions directly to school completion and labor market outcomes. Second, the paper leverages the question data to construct multiple such scales in order to correct for biases stemming from measurement error. These new achievement scales rank students differently than standard scales and typically yield ...
Working Paper
Likelihood Evaluation of Models with Occasionally Binding Constraints
Applied researchers interested in estimating key parameters of DSGE models face an array of choices regarding numerical solution and estimation methods. We focus on the likelihood evaluation of models with occasionally binding constraints. We document how solution approximation errors and likelihood misspecification, related to the treatment of measurement errors, can interact and compound each other.
Working Paper
Estimating Macroeconomic News and Surprise Shocks
The importance of understanding the economic effects of TFP news and surprise shocks is widely recognized in the literature. This paper examines the ability of the state-of-the-art VAR approach in Kurmann and Sims (2021) to identify responses to TFP news shocks and possibly surprise shocks in theory and practice. When applied to data generated from conventional New Keynesian DSGE models with shock processes that match key TFP moments, this estimator tends to be strongly biased, both in the presence of TFP measurement error and in its absence. This bias worsens in realistically small samples, ...
Working Paper
The Limited Macroeconomic Effects of Unemployment Benefit Extensions
By how much does an extension of unemployment benefits affect macroeconomic outcomes such as unemployment? Answering this question is challenging because U.S. law extends benefits for states experiencing high unemployment. We use data revisions to decompose the variation in the duration of benefits into the part coming from actual differences in economic conditions and the part coming from measurement error in the real-time data used to determine benefit extensions. Using only the variation coming from measurement error, we find that benefit extensions have a limited influence on state-level ...
Working Paper
Wealth, Pensions, Debt, and Savings: Considerations for a Panel Survey
Several U.S. panel surveys measure household wealth. At the same time, many important questions about household wealth accumulation remain somewhat unresolved. We consider whether measurement error on the existing suite of longitudinal surveys hinders their usefulness for addressing these questions. We review the features of wealth data that make it difficult to collect and assess which assets and debts households are more likely to report accurately. We suggest several considerations in choosing between improving existing surveys and starting a new one.
Working Paper
Estimating Macroeconomic News and Surprise Shocks
The importance of understanding the economic effects of TFP news and surprise shocks is widely recognized in the literature. A common VAR approach is to identify responses to TFP news shocks by maximizing the variance share of TFP over a long horizon. Under suitable conditions, this approach also implies an estimate of the surprise shock. We find that these TFP max share estimators tend to be strongly biased when applied to data generated from DSGE models with shock processes that match the TFP moments in the data, both in the presence of TFP measurement error and in its absence. ...
Working Paper
Missing Variation in the Great Moderation: Lack of Signal Error and OLS Regression
This paper studies measurement errors that subtract signal from true variables of interest, labeled lack of signal errors (LoSE). The effect on OLS regression of LoSE is opposite the conventional wisdom about classical measurement errors, with LoSE in the dependent variable, not the explanatory variables, causing attenuation bias under some conditions. The paper provides evidence of LoSE in US GDP growth during the period known as the Great Moderation (roughly the mid-1980s to the mid-2000s), illustrating attenuation bias in regressions of GDP growth on asset prices. These biases may have ...