Description Usage Arguments Details Value References
Estimates the model of Madhavan, Richardson, and Roomans (1997)
1 2 | estimate_mrr(price_diff, price, indicator, indicator_lag, midquote,
midquote_lag, spread_quoted)
|
price_diff |
a numeric vector containing the series of first price differences. |
price |
a numeric vector containing the price series. |
indicator |
an integer vector containing the trade direction with a buy as 1 and a sell as -1. |
indicator_lag |
an integer vector containing the first lag of the indicator series. |
midquote |
a numeric vector with the midquote price series. |
midquote_lag |
a numeric vector containing the first lag of the midquote series. |
spread_quoted |
a numeric vector containing the quoted spread series. |
The function estimates for given data the trade indicator model of
Madhavan,
Richardson, and Roomans (1997). For estimation a GMM approach is used similar to
the one desribed in the paper of the three authors. For application the gmm
-
package is used with a Bartlett-kernel, a heteroscedastic and autocorrelation
consistent variance-covariance matrix with a Newey West bandwith. For details
it is referred to the gmm
-function.
A data.frame with the following values:
the number of observation used in estimation.
the adverse selection component.
the standard deviation of the adverse selection component.
the t-value of the adverse selection component.
the p-value of the adverse selection component.
the transitory cost component.
the standard deviation of the transitory cost component.
the t-value of the transitory cost component.
the p-value of the transitory cost component.
the indicator first order autocorrelation.
the standard deviation of the indicator autocorrelation.
the t-value of the indicator autocorrelation.
the p-value of the indicator autocorrelation.
the coefficient of determination.
the adjusted coefficient of determination.
the value of the F-statistic.
the p-value of the F-statistic.
the start value for theta in the numerical optimization.
the start value for phi in the numerical optimization.
the start value for rho in the numerical optimization.
the estimated standard deviation of the epsilon error term (order flow innovations).
the estimated standard deviation of the eta error term (stochastic rounding errors).
the effective spread estimated from the model using the formula 2(θ+φ).
the standard deviation of the effective spread, calculated via the delta method.
the empirical effective spread, calculated directly from the data by the arithmetic mean of the series q_t(p_t-m_t), where q_t is the trade direction, p_t the transaction price, and m_t the price midquote series.
the standard deviation of the empirical effective spread calculated as the standard deviation of the series q_t(p_t-m_t).
the standard error of the estimated empirical effective spread using the formula SE=STD/√ n.
the median of the empirical effective spread calculated as the median of the series q_t(p_t-m_t).
the mean quoted spread using the input quoted spread series.
the standard deviation of the quoted spread using the input quoted spread series.
the standard error of the quoted spread estimate using the formula SE=STD/√ n.
the median of the quoted spread series.
Madhavan, Richardson & Roomans (1997), "Why Do Security Prices Change? A Transaction-Level Analysis of NYSE Stocks," Review of Financial Studies, Vol. 10, No. 4, pp. 1035-1064.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.