Anurag Banerjee
Durham University, Economics, Faculty Member
Worldwide, India has the highest number of people defecating in the open. In an attempt to reduce number of open defecation, a supply side initiative is underway. In 2014-2015, Government of India, constructed 8 million toilets. However,... more
Worldwide, India has the highest number of people defecating in the open. In an attempt to reduce number of open defecation, a supply side initiative is underway. In 2014-2015, Government of India, constructed 8 million toilets. However, an important aspect for this supply-side initiative to become successful is to create demand for toilets. In this paper we look at household demand for toilets, and study the factors leading to open defecation. Using Demographic and Health Survey data we create a wealth index, and use it to rank household preference for toilets vis-a-vis 20 other different consumer durables. Our results suggest, among lists of household items that any individual want to have, toilets get a lower preference – ranked 12, out of 21. Additionally, we examine preference structure for using toilets among residents from various federal states in India. We find residents of NorthEastern states are more likely to use toilets. We further investigate factors leading to toilet ...
Research Interests:
Although the ratio of higher educated lifetime earnings relative to primary-educated lifetime earnings (skill premium) is higher in poor than rich countries, poor countries have a substantially lower fraction of individuals with higher... more
Although the ratio of higher educated lifetime earnings relative to primary-educated lifetime earnings (skill premium) is higher in poor than rich countries, poor countries have a substantially lower fraction of individuals with higher education (skilled individuals). Why? In a sample of 52 countries, we document that the unemployment rate of the skilled net of that of the unskilled decreases with a country’s level of development. We argue that the cost of opening and operating a business is a first order determinant of these unemployment rates and can reconcile a lower skill acquisition in front of a higher skill premium in poor compared to rich countries. To formalize our argument, we write and quantify a matching model of endogenous occupational choice and skill acquisition. A country’s business cost, schooling cost and skill-productivity profile determine its fraction of skilled individuals, skill premium and unemployment rates by skill level. We infer a higher business cost for...
Research Interests:
Research Interests:
This paper proposes a random-coefficient autoregressive model that can accomodate the pricing of assets under standard present-value relations, both according to fundamentals and in the presence of bubbles. The distribution of the random... more
This paper proposes a random-coefficient autoregressive model that can accomodate the pricing of assets under standard present-value relations, both according to fundamentals and in the presence of bubbles. The distribution of the random coefficient is parameterized in a local-asymptotics framework as a moderate deviation from a stochastic unit root. An application to inference regarding the dynamics of U.S. house prices shows the pertinence of the model.
Research Interests:
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We... more
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We establish its asymptotic properties and evaluate its performance in finite samples. Our working model also allows us to formalise the concept of a long run functional equilibrium relationship analogous to the well known cointegration concept within a constant coefficient setting
Research Interests:
We propose a near explosive random coefficient autoregressive model (NERC) to obtain predictive probabilities of the apparition and devolution of bubbles. The distribution of the autoregressive coefficient of this model is allowed to be... more
We propose a near explosive random coefficient autoregressive model (NERC) to obtain predictive probabilities of the apparition and devolution of bubbles. The distribution of the autoregressive coefficient of this model is allowed to be centred at an O(T−α) distance of unity, with α ∈ (0, 1). When the expectation of the autoregressive coefficient lies on the explosive side of unity, the NERC helps to model the temporary explosiveness of time series and obtain related predictive probabilities. We study the asymptotic properties of the NERC and provide a procedure for inference on the parameters. In empirical illustrations, we estimate predictive probabilities of bubbles or flash crashes in financial asset prices.
Research Interests:
Research Interests:
Research Interests:
Adhesive capsulitis is a common cause of stiff shoulder and may result in pain and restriction of movement. The study aimed to investigate the role of hydrodilatation of the glenohumeral joint in the management of adhesive capsulitis.... more
Adhesive capsulitis is a common cause of stiff shoulder and may result in pain and restriction of movement. The study aimed to investigate the role of hydrodilatation of the glenohumeral joint in the management of adhesive capsulitis. Patients referred from the shoulder clinic underwent hydrodilatation under ultrasound guidance. Of 209 referred for hydrodilatation, 163 underwent the procedure and attended follow-up physiotherapy. Outcome measures were available for 118 patients (58 men and 60 women). Mean age of the study group was 52.6 years. There was a statistically significant improvement in both Oxford Shoulder Score (OSS) and Disability Arm Shoulder Hand Scores (Quick DASH) in the first 4 weeks after the procedure, which was maintained but not improved to the end of the study period. Patients presenting with pain, those who had a history of steroid injections and older patients all had worse functional scores at presentation. Diabetes (both Type I and II), previous physiothera...
Research Interests:
Research Interests:
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We... more
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We establish its asymptotic properties and evaluate its performance in finite samples. Our working model also allows us to formalise the concept of a long run functional equilibrium relationship analogous to the well known cointegration concept within a constant coefficient setting
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract: Economic and econometric models are used as simple metaphors for the real economic process. There are several reasons to study economic models - to justify some economic theory, to get a mathematical model of the economy but... more
Abstract: Economic and econometric models are used as simple metaphors for the real economic process. There are several reasons to study economic models - to justify some economic theory, to get a mathematical model of the economy but mostly they are used to study a particular feature or features of the real economy. When we are interested in estimating or inferring only a particular feature of the economy, anything else in the model or the estimation process is only important, as so far as it might influence the study of the desired feature. This thesis contains my study of sensitivity analysis of econometric models, within such framework.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In India, the popular perception is economic reforms have benefited the rich more than the poor leading to an unequal income distribution, as in Quah's twin peaks hypothesis. In this article we test this hypothesis by studying the... more
In India, the popular perception is economic reforms have benefited the rich more than the poor leading to an unequal income distribution, as in Quah's twin peaks hypothesis. In this article we test this hypothesis by studying the spatial dynamics of income distribution. Using district-level per-capita income we find that the income distribution has not changed. The perception about economic
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
ABSTRACT We consider a passive 1/N naive diversification strategy which is long in the equally weighted portfolio of stocks feasible for trading and short in the risk-free asset. We then examine the profi
tability, exposures to risk... more
ABSTRACT We consider a passive 1/N naive diversification strategy which is long in the equally weighted portfolio of stocks feasible for trading and short in the risk-free asset. We then examine the profi
tability, exposures to risk factors, idiosyncratic variance as well as the relation between the momentum and the 1/N naive diversifi
cation strategies. The set of sample stocks that we use to construct the equally weighted portfolio is the same as that for constructing the momentum strategies. We fi
nd that both strategies generate an average pro
t of 1% per month. The differences in raw and risk-adjusted pro
ts between these two strategies are statistically and economically insignifi
cant. These two strategies are independent of each other. The idiosyncratic variance of the momentum strategies is 20 times higher than that of the naive diversifi
cation strategy. The findings are consistent over the period between 1926 and 2005 and various sub-sample periods including the periods examined in Jegadeesh and Titman (1993 and 2001) and in our simulations where we randomly select 10 years for 100 times. The results also hold when we conduct tests in sub-samples where we divide the sample, each month, into two groups of large and small size stocks.
ABSTRACT We analyze the bias in the standard error caused by the correlated variance-covariance error matrix from using the Fama-McBeth method with panel data. We propose a three step Generalized Fama-McBeth method to model the correlated... more
ABSTRACT We analyze the bias in the standard error caused by the correlated variance-covariance error matrix from using the Fama-McBeth method with panel data. We propose a three step Generalized Fama-McBeth method to model the correlated errors. In the first step we estimate the betas using cross-sectional regressions. Next, the betas are fitted with a a stationary ARMA process. We then test the drift parameter of the ARMA process of the betas. We show that this is equivalent to testing for the beta being equal to zero. We also model a stochastic entry/exit process for firms in a dataset which helps estimate and test the betas with this method for a more general class of error process. This approach is much simpler and easier to implement than the methods commonly used to correct for the OLS standard errors for large data sets.
Research Interests:
The paper uses local linear regression to estimate the ``direct'' Average Derivative \delta = E(D[m(x)]), where m(x) is the regression function. The estimate of \delta is the weighted average of local slope estimates. We prove... more
The paper uses local linear regression to estimate the ``direct'' Average Derivative \delta = E(D[m(x)]), where m(x) is the regression function. The estimate of \delta is the weighted average of local slope estimates. We prove the asymptotic normality of the estimate under conditions which are different from the conditions used by Heardle-Stoker (H-S) (1989). Using Monte-Carlo simulation experiments we give some small sample results comparing our estimator with the H-S estimator under our conditions for asymptotic normality.
Research Interests:
It is well known that the Durbin-Watson and several other tests for first-order autocorrelation have limiting power of either zero or one in a linear regression model without an intercept, and tend to a constant lying strictly between... more
It is well known that the Durbin-Watson and several other tests for first-order autocorrelation have limiting power of either zero or one in a linear regression model without an intercept, and tend to a constant lying strictly between these values when an intercept term is ...
Research Interests:
We formally define a concept of functional cointegration linking the dynamics of two time series via a functional coefficient. This is achieved through the use of a concept of summability as an alternative to I(1)’ness which is no longer... more
We formally define a concept of functional cointegration linking the dynamics of two time series via a functional coefficient. This is achieved through the use of a concept of summability as an alternative to I(1)’ness which is no longer suitable under nonlinear dynamics. We subsequently introduce a nonparametric approach for estimating the unknown functional coefficients. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We establish its consistency properties and evaluate its performance in finite samples. We subsequently illustrate its usefulness through an application that explores linkages between stock prices and dividends via a sentiment indicator.
Research Interests:
Research Interests:
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We... more
We introduce a new nonparametric approach for estimating a simple varying coeffcient model with a unit root nonstationarity. Our method is based on a piecewise local least squares principle and is computationally simple to implement. We establish its asymptotic properties and evaluate its performance in finite samples. Our working model also allows us to formalise the concept of a long run functional equilibrium relationship analogous to the well known cointegration concept within a constant coefficient setting