Showing papers by "Tarun Ramadorai published in 2017"
Posted Content•
TL;DR: This article proposed to change the default P-value threshold for statistical significance for claims of new discoveries from 0.05 to 0.005, which is the threshold used in this paper.
Abstract: We propose to change the default P-value threshold for statistical significance for claims of new discoveries from 0.05 to 0.005.
1,415 citations
TL;DR: This article investigated the sources of variation in the "ARM share" of ARMs issued, relative to total mortgage issuance, and uncovered strong evidence in favour of current cost minimization as the proximate driver of household mortgage choice.
Abstract: The form of the interest rate on newly issued mortgages, namely whether they are adjustable-rate mortgages (ARMs) or fixed-rate mortgages (FRMs), varies considerably both across countries and over time. We attempt to uncover the sources of this variation in the "ARM share" of ARMs issued, relative to total mortgage issuance. Our emphasis is on drawing inferences about how household mortgage choice is affected by households' reactions to movements in interest rates. We complement newly assembled panel data from nine countries on the ARM share and mortgage interest rates with a panel instrumental variables approach in which we test exclusion restrictions that are implied by alternative explanations for variation in the ARM share. We uncover strong evidence in favour of current cost minimization as the proximate driver of household mortgage choice.
34 citations
Posted Content•
TL;DR: The authors proposed to change the default P-value threshold for statistical significance for claims of new discoveries from 0.05 to 0.005, which is the threshold used in this paper.
Abstract: We propose to change the default P-value threshold for statistical significance for claims of new discoveries from 0.05 to 0.005.
14 citations
Posted Content•
TL;DR: In this article, a simple equilibrium model of credit provision in which to evaluate the impacts of statistical technology on the fairness of outcomes across categories such as race and gender was proposed. But the model was not applied to US mortgages.
Abstract: Recent innovations in statistical technology, including in evaluating creditworthiness, have sparked concerns about impacts on the fairness of outcomes across categories such as race and gender. We build a simple equilibrium model of credit provision in which to evaluate such impacts. We find that as statistical technology changes, the effects on disparity depend on a combination of the changes in the functional form used to evaluate creditworthiness using underlying borrower characteristics and the cross-category distribution of these characteristics. Employing detailed data on US mortgages and applications, we predict default using a number of popular machine learning techniques, and embed these techniques in our equilibrium model to analyze both extensive margin (exclusion) and intensive margin (rates) impacts on disparity. We propose a basic measure of cross-category disparity, and find that the machine learning models perform worse on this measure than logit models, especially on the intensive margin. We discuss the implications of our findings for mortgage policy.
9 citations
Posted Content•
01 Jan 2017
TL;DR: In this article, the authors used the most recent wave of the All India Debt and Investment Survey data to explain several important features of Indian household balance sheets and found that Indian households tend to hold a high fraction of non-financial assets with particularly high relative weights in real estate and gold, hold negligible retirement assets and rely on non-institutional debt as their primary source of debt.
Abstract: Using the most recent wave of the All India Debt and Investment Survey data, we describe and attempt to explain several important features of Indian household balance sheets. When compared with data on households in a range of developed and emerging economies, Indian households, on average, tend to hold a high fraction of non-financial assets with particularly high relative weights in real estate and gold, hold negligible retirement assets, and rely on non-institutional debt as their primary source of debt. These propensities are also evident along the life cycle, as well as at almost all points in the wealth distribution, and correlated with location (rural versus urban), education, and family composition. Controlling for demographics, substantial state-level variation remains in asset and debt holdings which is related to state-level factors including historical inflation volatility, the share of the population in public sector employment, and the density of bank branch networks. We discuss the potential implications of these results for policy.
1 citations