Page 323 - Fundamentals of Probability and Statistics for Engineers
P. 323

306                    Fundamentals of Probability and Statistics for Engineers

             In this approximation, sample mean X   is at  the center  of the interval for
           which the width is a function of the sample and the sample size.
             Example 9.21. Problem: in a random sample of 500 persons in the city of Los
           Angeles it was found that 372 did not approve of US energy policy. Determine
           a  95%  confidence  interval  for  p,  the  actual  proportion  of  the  Los  Angeles
           population registering disapproval.
             Answer: in this example, n ˆ  500,   ˆ  0.05, and the observed sample mean is
           x ˆ  372/500 ˆ  0.74.  Table  A.3  gives u 0:025 ˆ 1:96.  Substituting these values
           into Equation (9.153) then yields

                 P…0:74   0:04 < p < 0:74 ‡ 0:04†ˆ P…0:70 < p < 0:78†ˆ 0:95:




           REFERENCES

           Anderson, R.L., and Bancroft, T.A., 1952, Statistical Theory in Research, McGraw-Hill,
            New York.
           Benedict, T.R., and Soong, T.T., 1967, ‘‘The Joint Estimation of Signal and Noise from

            the Sum Envelope’’, IEEE Trans. Information Theory, IT-13 447–454.
           Fisher, R.A., 1922, ‘‘On  the Mathematical Foundation of Theoretical Statistics’’, Phil.

            Trans. Roy. Soc. London, Ser. A 222 309–368.
           Gerlough,  D.L.,  1955,  ‘‘The  Use  of  Poisson  Distribution  in  Traffic’’,  in  Poisson and
            Traffic, The Eno Foundation for Highway Traffic Control, Saugatuk, CT.
           Mood, A.M., 1950, Introduction to the Theory of Statistics, McGraw-Hill, New York.
           Neyman, J., 1935, ‘‘Su un Teorema Concernente le Cosiddeti Statistiche Sufficienti’’,

            Giorn. Inst. Ital. Atturi. 6 320–334.
           Pearson,  K.,  1894,  ‘‘Contributions  to  the  Mathematical  Theory  of  Evolution’’,  Phil.
            Trans. Roy. Soc. London, Ser. A 185 71–78.

           Soong, T.T., 1969, ‘‘An Extension of the Moment Method in Statistical Estimation’’,

            SIAM J. Appl. Math. 17 560–568.
           Wilks, S.S., 1962, Mathematical Statistics, John Wiley & Sons Inc., New York.


           FURTHER READING AND COMMENTS
           The Crame ´r–Rao inequality is named after two well-known statisticians, H. Crame ´rand
           C.R. Rao, who independently established this result in the following references. How-
           ever, this inequality was first stated by Fisher in 1922 (see the Reference section). In fact,
           much of the foundation of parameter estimation and statistical inference in general, such
           as concepts of consistency, efficiency, and sufficiency, was laid down by Fisher in a series
           of publications, given below.
           Crame ´r,  H.,  1946,  Mathematical Methods of Statistics,  Princeton  University  Press,
            Princeton, NJ.
           Fisher, R.A., 1924, ‘‘On a Distribution Yielding the Error Functions of Several Well-
            known Statistics’’, Proc. Int. Math. Congress, Vol. II, Toronto, 805–813.








                                                                            TLFeBOOK
   318   319   320   321   322   323   324   325   326   327   328