Explore BrainMass
Share

# Autocorrelation and heteroscedasticity

This content was STOLEN from BrainMass.com - View the original, and get the already-completed solution here!

Open the Cons Trans 59 - 00.xls file. Use the BEA consumption and transfers data to investigate whether heteroscedasticity or autocorrelation is present in the model using the graphical approach (consumption as the dependent variable). Which answer best represents the degree of autocorrelation in the model? Using EXCEL or PHStat2, answer the following:

a) Neither autocorrelation nor heteroscedasticity appear to be present in the model.
b) Autocorrelation appears to be present in the model.
c) Heteroscedasticity appears to be present in the model.
d) Both autocorrelation and heteroscedasticity appear to be present in the model

Refer to the BEA consumption and transfers data from the Cons_Trans_59-00.xls file which was used in Problem 1, above. Analyze the signs of the residuals and values of the residuals to determine which best describes the pattern in the residuals

a) The signs of the residuals are randomly arranged and the values of the residuals remain constant.
b) The signs of the residuals reveal a non-random pattern and the values of the residuals remain constant.
c) The signs of the residuals reveal a non-random pattern and the values of the residuals increase as the transfers increase.
d) The signs reveal are randomly arranged and the values of the residuals increase as the transfers increase.

Use the Cons Trans 59-00.xls file, which was, used in Problems 1 & 2 and PHStat2, Excel, or other means to calculate the d statistic. The calculated d-statistic is:

a) 0.635267892
b) 1.355377418
c) 0.877545537
d) 0.355377418

The dl and du at a 0.01 level of significance in the Durbin-Watson test for autocorrelation are:

a) 1.44 & 1.54, respectively.
b) 1.48 & 1.57, respectively.
c) 1.25 & 1.34, respectively.
d) 1.24 & 1.42, respectively.

Use the results of the Durbin-Watson test in Problems 3 & 4 to determine if autocorrelation exists in the model. Test at the 0.01 level of significance. The statistical conclusion is:

a) No evidence of autocorrelation.
b) No conclusion can be drawn.
c) Autocorrelation exists in the model.
d) Not enough information to determine if autocorrelation exists.

https://brainmass.com/statistics/correlation-and-regression-analysis/434510

#### Solution Summary

Multiple choice questions on Time series.

\$2.19
Similar Posting

## Heteroskedasticity Residual Plots

I am attaching three different residual plots. I am trying to determine whether heteroskedasticity is present. I don't believe I see any pattern indicative of heteroskedasticity (nonconstant variance). I know it can be difficult to detect - do you see any indication of this?

View Full Posting Details