B. Le Baron, Some relations between volatility and serial correlations in stock returns, J. Business 65 (1992) 199--219.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....that are inputted into the specification tests are themselves motivated by the type of economic and financial behavior one is trying to study. For example, distributions of statistics gleaned off of trading strategies are bootstrapped under the null model being tested in Brock, Lakonishok, LeBaron (1992), and Levich and Thomas (1993) This approach to specification testing is described in Section four below. 2 1.1 Theoretic and statistical models The theme of argument above contains the subtheme that a closer analytical study between theoretic models and the statistical models that are ....

....features of returns at the high to medium frequencies which include the daily frequency. A recent surge of interest has developed around bootstrap based specification tests or goodness of fit tests of parameterizations of the Efficient Market Hypothesis. See, for example, Brock, Lakonishok, LeBaron (1992), hereafter referred to as BLL, Levich and Thomas (1993) Antoniewicz (1992) 1993) and Vaga (1994) We shall only give a brief discussion here which is based upon BLL. BLL explore operationalizing the idea that various fundamentalist or technical trading rules have evolved over the decades ....

[Article contains additional citation context not shown here]

LeBaron, B. (1992), Some relations between volatility and serial correlations in stock returns," Journal of Business 65, 199-219.

....100 000. again u t = t , this latter expression becomes equal to 2 (1 P q i=1 2 i ) i.e. the well known formula for the variance of an MA(q) process. Depending on the signs of the i (i =1; q) the model can capture an inverse relationship between autocorrelation and volatility (cf. LeBaron, 1992). Using estimated parameters (see Section 5, below) a time series of length T = 100 000 is generated. From the generated series the unknown expected values are estimated as sample averages, and used in (6) 7) In Figure 2 the lag one autocorrelation coecient, 1 = 1 = 0 , is graphed against 0 ....

....than for negative shocks. For the conditional variance the impact of negative shocks is greater. The asymmetric and positive responses in volatility to past shocks is in line with, e.g. Nelson (1991) To study the previously found inverse relationship between autocorrelation and volatility (LeBaron, 1992), consider Figure 2 which is based on estimated versions of (6) 7) to obtain the autocorrelation coecient at lag one, 1 = 1 = 0 . Variation in h 2 t is obtained by varying the constant term 0 (E(h 2 t ) is increasing from 0.47 to 7.31) Figure 2 is based on a generated series of length T ....

LeBaron, B. (1992), \Some relations between volatility and serial correaltions in stock market returns", Journal of Business, 65, 199-219.

....sets of variables, making it an exogenous or ARX model. We use first differences of the logarithm of the level of the Dow Jones Industrials Index as a measure of relative stock returns, r t . Furthermore, volume movements are connected to stock return movements in interesting ways (Karpov, 1987; LeBaron, 1992a; Gallant et al. : 1993) One of these features is that volume is related to stock price volatility, sometimes approximated by the absolute magnitude of daily price movements. Furthermore, volume tends to be higher in rising markets. For these reasons we chose several lagged returns and volume ....

....taking the raw volume from Fig. 1 (b) the overall shift in level over the two decades is responsible for an autocorrelation of 0.95. ffl Three lags each of the relative returns, r t Gamma1;2;3 . Their one day autocorrelation is small (0. 135) and disappears for two or more lags, as discussed in LeBaron (1992). ffl Two estimates of their volatilities, with three lags each: Absolute value of the relative returns,jr t Gamma1;2;3 j. Their autocorrelation coefficients are dropping off very slowly, and have values for the first 10 lags around 0.16, computed after subtracting the mean of jr t j. 7 ....

LeBaron, B. 1992. Some relations between volatility and serial correlations in stock market returns. Journal of Business 65, 199--219.

....other sets of variables, making it an exogenous or XAR model. We use first differences of the logarithm of the level of the Dow Jones Industrials Index as a measure of stock returns, r t . Furthermore, volume movements are connected to stock return movements in interesting ways (Karpov, 1987; LeBaron, 1992a; Gallant et al. : 1993) One of these features is that volume is related to stock price volatility, sometimes approximated by the absolute magnitude of daily price movements. Furthermore, volume tends to be higher in rising markets. For these reasons we chose several lagged returns and volume ....

....three lags of the past volume prices (normalized levels, not differenced, see Fig. 1 c) they have a 0.66 one day autocorrelation. Furthermore, we used three lags each of the differences of the Dow Jones Industrial Index (having small 1 day autocorrelation of 0. 135, and none for two or more lags, LeBaron (1992)) as well as of two estimates of their volatilities: absolute values of the returns (small autocorrelation of 0.16) and the logarithm of the exponentially smoothed squared returns (with autocorrelation of 0.975 primarily due to the smoothing) III. Empirical Results A. Learning Curves and ....

LeBaron, B. 1992. Some relations between volatility and serial correlations in stock market returns. Journal of Business 92.

No context found.

B. Le Baron, Some relations between volatility and serial correlations in stock returns, J. Business 65 (1992) 199--219.

No context found.

Blake LeBaron. Some relations between volatility and serial correlations in stock market returns. Technical Report 9002, Social Systems Research Institute, University of Wisconsin, Madison, February 1990.

No context found.

LeBaron B., 1992b, Some relations between volatility and serial correlations in stock market returns, Journal of Business, 65(2), 199--219.

No context found.

LeBaron B. (1990), Some Relations Between Volatility and Serial Correlation in Stock Market Returns, Social Systems Research Institute, University of Wisconsin.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC