Page 87 - Intermediate Statistics for Dummies
P. 87

07_045206 ch03.qxd  2/1/07  9:47 AM  Page 66
                                66
                                         Part I: Data Analysis and Model-Building Basics
                                                               Power in manufacturing
                                                                                 average weight shifts to, say, 2.5 ounces.
                                            The power of a test plays a role in the manufac-
                                                                                 Statisticians can work backwards in calculat-
                                            turing process. Manufacturers often have very
                                            strict specifications regarding the size, weight,
                                                                                 ing the power and find the sample size they
                                                                                 need to know to stop the process.
                                            and/or quality of their products. During the man-
                                            ufacturing process, manufacturers want to be
                                                                                 Medical scientists also think about power when
                                            able to detect deviations from these specifica-
                                                                                 they set up their studies (called clinical trials).
                                            tions, even small ones, so they must think about
                                                                                 Suppose they’re checking to see whether an
                                            how much of a difference from Ho they want
                                                                                 antidepressant adversely affects blood pressure
                                            to detect, and then figure out the sample size
                                                                                 (as a side effect of taking the drug). Scientists
                                            they need in order to detect that difference
                                                                                 need to be able to detect small differences in
                                            when it appears. For example, if the candy bar is
                                                                                 blood pressure, because for some patients, any
                                            supposed to weight 2.0 ounces, the manufac-
                                                                                 change in blood pressure is important to note.
                                            turer may want to blow the whistle if the actual
   82   83   84   85   86   87   88   89   90   91   92