Estimating the Probability of Informed Trading

Using a new empirical model, I estimate the probability of trades being generated by privately informed traders. Inference is drawn on a trade‐by‐trade basis using data samples from the New York Stock Exchange (NYSE). The modeling setup facilitates in‐depth analysis of the estimated probability of informed trading at the intraday level and for stocks with different levels of trading activity. The most important empirical results are: (a) the intradaily pattern of the inferred probability of informed trading is highly correlated with the intradaily pattern of observed quoted spreads, (b) differences in the magnitude of quoted spreads across volume categories are not exclusively related to differences in the level of informed trading, and (c) private information is incorporated faster in the quotes for high‐volume stocks than in the quotes for low‐volume stocks.     

Regime shifts in the Danish term structure of interest rates

Within a bivariate VAR model allowing for two-state Markov regime switching we test and evaluate the Expectations Theory (ET) of the term structure using Danish 1- and 3-months interest rates covering the period 1976–1997. A regime-shift approach is used in order to account for the change in monetary policy and the 1992–93 exchange rate crises that occured during this period. The basic findings are that these episodes did change the term structure, and, although we do find departures from the ET, several of the implications of the theory are consistent with the data, especially in the later part of the sample. First version received: June 1997/Final version received: March 1998     

A New Approach to Predicting Recessions

This paper presents a new approach to recession prediction. The methodology relies on the shape of the yield curve alone and does not incorporate macroeconomic information or other explanatory variables. This makes the modelling framework less data intensive and more intuitive than other models that have the same goal. The workhorses of the approach are (i) data transformation of observed yields with the purpose of normalizing the yield spread, and (ii) a three-state regime-switching version of the Nelson–Siegel parametric model of the yield curves' shape and location. In an out-of-sample exercise the model predicts all US NBER recessions from 1973 to 2004 at least eight months in advance of their occurrences.     

Effectiveness comparison and incremental cost-per-responder analysis of calcipotriene 0.005%/betamethasone dipropionate 0.064% foam vs. halobetasol 0.01%/tazarotene 0.045% lotion for plaque psoriasis: a matching-adjusted indirect comparative analysis

Abstract

Background: The fixed-dose combination foam formulation of calcipotriene 0.005% plus betamethasone dipropionate 0.064% (Cal/BD) has demonstrated efficacy and a favorable safety profile for the treatment of plaque psoriasis. Recently, a topical lotion of the combination of halobetasol 0.01% plus tazarotene 0.045% (HP/TAZ) was approved for treating adult plaque psoriasis. Currently, no head-to-head studies have compared Cal/BD foam with HP/TAZ lotion.

Objective: Compare the effectiveness and drug incremental cost per responder (ICPR) of Cal/BD foam vs. HP/TAZ lotion in moderate-to-severe plaque psoriasis.

Methods: An anchor-based, matching-adjusted indirect comparison was conducted for PGA treatment success (Physician’s Global Assessment of “clear” or “almost clear,” [PGA 0/1] with at least a 2-point improvement) using individual patient data from 3 randomized clinical studies of Cal/BD foam and published data from 2 randomized, Phase 3 clinical studies of HP/TAZ lotion. The number needed to treat and ICPR were also calculated.

Results: After reweighting of patients in the Cal/BD foam studies to match summary baseline characteristics of the HP/TAZ lotion study patients and anchoring to vehicle effect, 4?weeks of Cal/BD foam produced a significantly greater rate of treatment success than 8?weeks of HP/TAZ lotion treatment (51.4 vs. 30.7%; treatment difference = 20.7%, p?<?.001). The number needed to treat with Cal/BD foam was also less than HP/TAZ lotion (1.9 vs. 3.3). Using US wholesale acquisition costs and equal weekly consumption rates, the incremental cost per PGA 0/1 responder relative to vehicle for Cal/BD foam was $3,988 and was 37% lower compared with HP/TAZ lotion ($6,294).

Conclusions: The indirect comparison analyses showed that Cal/BD foam was associated with a greater rate of treatment success, lower ICPR, and quicker treatment response than HP/TAZ lotion in adult patients with moderate-to-severe plaque psoriasis.     

Estimation of the effective bid-ask spread on high frequency Danish bond data

In this paper the effective bid-ask spread is estimated using 12 high frequency Danish bond samples. A clear-cut MA(1)-model for the mean of the return series, and a GARCH(1,1)-model for the variance, are found. Basically, Roll's model is used, but three different methods of calculating the first-order autocovariance are suggested. Each of these in turn produces three possible ways of estimating the effective bid-ask spread. First, Roll's original autocovariance estimate is used. Second, the autocovariance is calculating using the parameters of an estimated MA(1) model. Third, the autocovariance is obtained from the parameters of a joint MA(1)-GARCH(1,1) model. By means of bootstrapping the standard error of the bid-ask spread estimates are found. It is shown that the gain in efficiency, measured by the relative difference in the standard error of the estimates, is 29% when going from method one to method two, but only 1% when going from method two to method three. These results indicate that the extra gain in efficiency obtained by taking account of the MA(1) structure of the data is noteworthy, but the gain when incorporating the GARCH-effects is negligible.     

Inferring the private information content of trades: a regime‐switching approach

This paper presents an empirical model for inferring the private information content of trades at the transaction level. The trade‐indicator model of Glosten and Harris ( 1988 ) is extended to a two‐state regime‐switching setting, and the model is estimated using tick‐by‐tick data from the New York Stock Exchange (NYSE). The specialist is found to react in accordance with the proposed model. Bid–ask quotes set after the execution of a trade reflect the conjectured information content of that particular trade. Based on the estimated model four empirical results emerge: (a) the suggested regime‐switching model fit data well; (b) the reverse J‐shaped pattern of intra‐daily quoted spreads is shown to agree with the clustering of costs incurred by the specialist through trading with better‐informed agents; (c) on average 9% of all trades are found to reveal private: information to the specialist; (d) results regarding the trading volume of informed traders support the stealth trading hypothesis suggested by Barclay and Warner ( 1993 ). Copyright © 2003 John Wiley & Sons, Ltd.     

A Rotated Dynamic Nelson‐Siegel Model

I show how to rotate the factor structure of the well‐known Dynamic Nelson‐Siegel yield‐curve model to enable direct parametrization of the short rate process. This makes it easy to calculate model‐implied term premia and to integrate macroeconomic variables into the model in a Taylor‐rule‐type fashion.