The Ljung-Box test is a test for serial correlation that tests if the autocorrelation coefficients for a given number of lags are jointly not significantly different from zero. The statistic for this test is where T is the sample size, m is the number of lags and is the estimated autocorrelation coefficient. The null hypothesis for this test is that the coefficients are all jointly zero and has a distribution. The alternative hypothesis is that at least one of the coefficients is not equal to zero and implies the presence of serial correlation.

We can estimate the Ljung-Box statistic in Eviews by creating a correlogram for the series rlsp500. In the below table included with the correlogram we are given the Ljung-Box statistic for each*…show more content…*

| 6 0.076 0.073 12.277 0.056 *|. | *|. | 7 -0.081 -0.091 14.441 0.044 .|. | .|. | 8 0.042 0.048 15.025 0.059 *|. | .|. | 9 -0.089 -0.058 17.622 0.040 .|. | .|. | 10 0.007 -0.041 17.639 0.061 .|. | .|. | 11 -0.031 -0.025 17.959 0.083 .|. | *|. | 12 -0.062 -0.069 19.242 0.083

B) The stylized feature of volatility clustering in financial data cannot be explained using linear models and estimation methods such as OLS. This is because one of the underlying assumptions of OLS is that is a constant and is the basis for measuring volatility. A GARCH(1,1) model is able to model this feature because it estimates a model for , which allows the variance to change over time.

C) To test for ARCH effects in the return series, we would start by estimating the return equation using least squares. We would then square the residuals from the return equation and regress the squared residuals on its lags. The R2 from this regression can be used to construct the test statistic, where T is the number of observations and the degrees of freedom, q, is the number of lagged squared residuals in the test equation. The null hypothesis for this test is that all the coefficients on the lagged squared residuals are equal to zero. The alternative hypothesis is that at least one of the coefficients*…show more content…*

-4.710556

Durbin-Watson stat 2.099147

Since we are talking about asset returns, a standard GARCH model may not be the best choice as we would expect there to be asymmetry in the volatility (Brooks 2008, p. 404). The EGARCH model would allow negative shocks to have a larger effect on the conditional variance than positive ones. As we can see in the below Eviews output, it is the case that negative shocks have a larger effect because the coefficient C(4) is negative. Because we are estimating the log of the conditional variance, unlike the standard GARCH model, it can be more difficult to interpret the exact meaning of all the parameters.

Dependent Variable: RLSP500

Method: ML - ARCH (Marquardt) - Normal distribution

Date: 07/29/12 Time: 20:08

Sample (adjusted): 1/10/2005 1/31/2011

Included observations: 317 after adjustments

Convergence achieved after 35 iterations

Presample variance: backcast (parameter = 0.7)

LOG(GARCH) = C(2) + C(3)*ABS(RESID(-1)/@SQRT(GARCH(-1))) + C(4) *RESID(-1)/@SQRT(GARCH(-1)) + C(5)*LOG(GARCH(-1))

Variable Coefficient Std. Error z-Statistic

We can estimate the Ljung-Box statistic in Eviews by creating a correlogram for the series rlsp500. In the below table included with the correlogram we are given the Ljung-Box statistic for each

| 6 0.076 0.073 12.277 0.056 *|. | *|. | 7 -0.081 -0.091 14.441 0.044 .|. | .|. | 8 0.042 0.048 15.025 0.059 *|. | .|. | 9 -0.089 -0.058 17.622 0.040 .|. | .|. | 10 0.007 -0.041 17.639 0.061 .|. | .|. | 11 -0.031 -0.025 17.959 0.083 .|. | *|. | 12 -0.062 -0.069 19.242 0.083

B) The stylized feature of volatility clustering in financial data cannot be explained using linear models and estimation methods such as OLS. This is because one of the underlying assumptions of OLS is that is a constant and is the basis for measuring volatility. A GARCH(1,1) model is able to model this feature because it estimates a model for , which allows the variance to change over time.

C) To test for ARCH effects in the return series, we would start by estimating the return equation using least squares. We would then square the residuals from the return equation and regress the squared residuals on its lags. The R2 from this regression can be used to construct the test statistic, where T is the number of observations and the degrees of freedom, q, is the number of lagged squared residuals in the test equation. The null hypothesis for this test is that all the coefficients on the lagged squared residuals are equal to zero. The alternative hypothesis is that at least one of the coefficients

-4.710556

Durbin-Watson stat 2.099147

Since we are talking about asset returns, a standard GARCH model may not be the best choice as we would expect there to be asymmetry in the volatility (Brooks 2008, p. 404). The EGARCH model would allow negative shocks to have a larger effect on the conditional variance than positive ones. As we can see in the below Eviews output, it is the case that negative shocks have a larger effect because the coefficient C(4) is negative. Because we are estimating the log of the conditional variance, unlike the standard GARCH model, it can be more difficult to interpret the exact meaning of all the parameters.

Dependent Variable: RLSP500

Method: ML - ARCH (Marquardt) - Normal distribution

Date: 07/29/12 Time: 20:08

Sample (adjusted): 1/10/2005 1/31/2011

Included observations: 317 after adjustments

Convergence achieved after 35 iterations

Presample variance: backcast (parameter = 0.7)

LOG(GARCH) = C(2) + C(3)*ABS(RESID(-1)/@SQRT(GARCH(-1))) + C(4) *RESID(-1)/@SQRT(GARCH(-1)) + C(5)*LOG(GARCH(-1))

Variable Coefficient Std. Error z-Statistic

Related

- Satisfactory Essays
## Statistics Assignment: Grades Sav Data File

- 635 Words
- 2 Pages
- 2 Works Cited

The closer the data aims to making a straight line, the higher the correlation between the two variables, or the stronger the relationship(MSTE,n.d) The scatter plot above does not have a straight line formation, so that showing that there is not a strong relationship between the two variables of GPA and final. An example of a null hypothesis for the variables used in this data collection would be, “Does GPA predicts final exam scores? An alternative hypothesis would be that GPA scores do determine the exam scores.

- 635 Words
- 2 Pages
- 2 Works Cited

Satisfactory Essays - Good Essays
## The Value Of Central Tendency

- 827 Words
- 2 Pages

Central tendency is the extent to which data values conjoin around a specific value or central value (Levine, Stephan, Krehbiel, & Berenson, 2008). The mean is a balance point in a set of data (Levine, et al., 2008). In order to calculate the mean, you must add together all the values and then divide that sum by the amount of values present in the data set (Levine, et al., 2008). One extreme value can alter the mean greatly, when this happens the mean my not be the best measure of central tendency (Levine, et al., 2008). The median is another measure of central tendency that measures the half waypoint in a data set (Levine, et al., 2008).

- 827 Words
- 2 Pages

Good Essays - Good Essays
## Path Selection Method

- 933 Words
- 2 Pages

The proposed method is a combination of the non-optimal and optimal solutions. At first, the design space is reduced by using heuristic approach. Next, the best solution form the reduced search space is extracted. The pseudo-code of the proposed algorithm is shown in Figure 1. Function SelectPaths(U, NSPC) 1:Find the correlations between the paths 2: Prune the paths 3: Generate correlation Matrix 4: Sort the items in the Matrix 5: Prune the Matrix 6: Write ILP formulation 7:Solve ILP Figure 1- The pseudo-code of the proposed selection method In the first step, the correlation between each two paths of the U, is calculated.

- 933 Words
- 2 Pages

Good Essays - Satisfactory Essays
## Chi Square Test Of Attributes Essay

- 1835 Words
- 4 Pages

7) Table 51 Here we are testing independence between two Attributes: A: Satisfaction of bonus and incentives B: Types of bank Hypothesis: H0 : Satisfaction of bonus and incentives is independent of types of bank. H1: Satisfaction of bonus and incentives is not independent of types of bank. Result: P-value of χ_cal^2≅ 0.00000. Conclusion: As P-value less than α we reject H0. Hence, Satisfaction of bonus and incentives is not independent of types of bank.

- 1835 Words
- 4 Pages

Satisfactory Essays - Good Essays
## Correlation And Regression Analysis

- 911 Words
- 2 Pages

Please identify (1) what they are, (2) where to find them on SPSS, and (3) how you know if you have met each of the assumptions. Correlation: Linearity- Assumption that there is a linear relationship between you predictor variable and the outcome variable that you are testing. You are able to check for this in SPSS by generating scatterplots and inserting the line of best fit. If you have a consistent alignment of points in a linear fashion going along with the line of best fit you meet the assumption. If your points are all over and not in a linear fashion, linearity is not met.

- 911 Words
- 2 Pages

Good Essays - Best Essays
## Financial Market: Volatility Models

- 1800 Words
- 4 Pages

As financial variables are characterized for non linear dependence, the ARCH model captures that dependence because it allows for heteroskedasticity, precisely, it depends only on the latest lag. However, when the sample is considerably large, the ARCH model has not the ability to capture that dependence because it will need so many lags that the estimation turns too much complex. Instead, later on, Bollerslev (1986) introduced the GARCH model. The main advantage is that it is able to capture the memory of the volatility, that parameter is the beta allowing for large samples. The main issue is that is defined with symmetric response in volatility, in other words, it is only taking into account the magnitude of the shocks, rather than the sign, meaning that for the same magnitude, negative and positive shocks will have the same effect.

- 1800 Words
- 4 Pages

Best Essays - Satisfactory Essays
## Cost Accounting

- 1501 Words
- 4 Pages

Bookmark not defined. Manufacturing Overhead Cost: Error! Bookmark not defined. Budgets Error! Bookmark not defined.

- 1501 Words
- 4 Pages

Satisfactory Essays - Satisfactory Essays
## A Description Of The FE-IV Model

- 759 Words
- 2 Pages

Another reason for choosing the FE model12 is that it can solve the endogeneity problem through using the FE-IV model; the variable GDP per capita-used as a proxy of income-could be an endogenous variable. An endogenous variables are variables that correlated with the error term (ε௧ ), while the variables that uncorrelated with the error term are called exogenous variables. The description of these terms explains that an endogenous variable is determined within the model itself while an exogenous variable is determined outside the model. To understand the endogeneity, we will use the classic regression equations that show the relationship between prices and wages: Price = ߚ0 + ߚ1Wage + ε௧ ………………………… (11) Wage = ߚ0 + ߚ1Price + u௧ ……………………... (12) From equation (11) and (12) we can see that prices can affect wages and also wages can affect prices, in this case we can say that both wages and prices are interdependent variables and to run our regression we can‟t use the OLS technique because using OLS will give us biased estimates because of endogeneity13. From equation (11), the variable Wage is an endogenous variable and to solve the endogeneity we need an instrument that correlated with Wage but not correlated with the error term.

- 759 Words
- 2 Pages

Satisfactory Essays - Better Essays
## Hypothesis And Alternative Hypothesis

- 1363 Words
- 3 Pages

On the other hand null hypothesis is a statement of equality between sets of given variables and an equal sign is being used between the variables. Null hypothesis is a no effect or a no difference hypothesis. Whereas alternative hypothesis describes the population parameters that the sample data if the predicted relationship prevails, on the other hand null hypothesis describes the same if the predicted relationship does not prevail. Another difference between null hypothesis and alternative hypothesis is that, alternative hypothesis refers to sample while null hypothesis refers to a population and hence alternative hypothesis can be tested directly

- 1363 Words
- 3 Pages

Better Essays - Good Essays
## Descriptive Statistics: Raw Data

- 756 Words
- 2 Pages

Tabachnick and Fidell (1996) suggest the value of skewness and kurtosis is equal to zero if the distribution of a variable is normal. Chou and Bentler (1995) emphases the absolute values of univariate skewness indices greater than 3 can be described as extremely skewed. Meanwhile, a threshold value of kurtosis greater than 10 can be considered problematic and value greater than 20 can be considered as having serious problems (Hoyle, 1995; Kline, 1998).

- 756 Words
- 2 Pages

Good Essays