The data in Appendix 5.A (see Lai and Xing (2008), p. 71) denote logreturns on six stocks, monthly observations from August 2000 to October 2005, where PFE=Pfizer, INTEL=Intel, CITI=Citigroup, AXP=American Express, XOM=

Exxon-Mobil, GM=General Motors. In addition, the data include log-returns for 3TB=3-month treasury bill rate and the SP500.

(a) Graph the t-plots for all the log-returns series and evaluate the presence of any chance regularity patterns associated with heterogeneity.

(b) Use a second-order polynomial t, t2, for t = 1, 2, . . . , n, to detrend the data series that exhibit any mean heterogeneity and use the t-plots of the detrended data to evaluate the presence of any chance regularity patterns associated with dependence.

(c) Use two lags (xt−1, xt−2) to dememorize all the detrended data series and use the t-plot of the detrended and dememorized data to evaluate the presence of any departures from the Normality assumption.

(d) For the detrended and dememorized data: (i) plot their histograms, as well as (ii)

their P–P plots, to evaluate your assessment in (c).

(e) In light of your answers in (a)–(d), speculate on the possible departures from assuming that a NIID vector process {Xt, t∈N} underlies the above data.