823 SUBJECT INDEX A Acceptance sampling, 170 Actual odds against, 153 Actual odds in favor, 153 Addition rule complementary events and, 160–161 defining, 158 disjoint events and, 159–160 formal, 158–159 intuitive, 159 notation for, 158–159 summary of, 167 Adjusted coefficient of determination, 554–555 Airport data speeds, 757 Alcohol and tobacco in movies, 752 a, 256 Alternative hypothesis, 518 contingency tables, 591 defining, 377 goodness-of-fit and, 578 original claim for, 377–378 Aluminum cans, 759 Analysis of data, 6 potential pitfalls, 7–9 Analysis of variance (ANOVA) history of, 616 interaction in, 627 one-way, 612–626 two-way, 626–636 Area between boundaries, 250 known, 254–256 with nonstandard normal distribution, 260–262 probability and, 247, 250–253 z scores and, 249, 250–253 Arsenic in rice, 751 Aspirin, 383 Assignable variation, 704, 707 Attributes, control charts for, 713 Audiometry, 748 Autism, 576–577 Average, 88, 518 Axis, nonzero vertical, 67–68 B b1 slope, 529, 530 Balanced design, 628 Bar codes, 183 Bar graphs, 64 Bayes’ theorem, 175–177 Bear measurements, 751 Benford’s law, 582–584 Bell-shaped distribution, 246 b, 384 Bias in internet surveys, 314, 317 in missing data, 23 publication, 7 survivorship, 5 Biased estimators, 107, 115, 279–280 Big data, 14, 18, 20–22 applications of, 21 Bimodal, 91 Binomial probabilities, 731 Binomial probability distribution, 218–226 defining, 219 finding, 220–224 formula, 220–221 normal distribution approximation of, 303–304 notation, 219, 303 rationale for, 225–226 software/calculator results, 226 Births, 747, 760 Bivariate normal distribution, 510 Blinding, 28 Blocks, 31–32 Body data, 746 Body temperatures, 724, 726–730, 747 Bonferroni multiple comparison test critical values in, 620 one-way ANOVA, 620 P-values in, 620 Bootstrap resampling for claims testing, 395–396, 410, 426 for constructing confidence intervals, 318, 335, 350 in holistic statistics, 728 in hypothesis testing, 384 for matched pairs, 474, 495 randomization vs., 490 software/calculator results, 360, 496–497 for two-samples inferences, 447, 460, 474, 490, 492–494, 496 Bootstrap sample for confidence interval, 356, 357 defining, 356 means and, 358–359 proportions and, 357–358 requirements, 355 standard deviation and, 359 Box, George E. P., 613 Boxplots, 121–130 constructing, 127–128 defining, 127 for mean, 619 modified, 130–131 skeletal, 130 skewness in, 128 software/calculator results, 132–133 Bribery, 708 C Callbacks, repeated, 207 Cancer, 681 Candies data set, 758 Car chases, 78 Car crash tests, 610–611 Car data set, 757 Car seats, 582 Case-control study, 30–31 Categorical data, 15–16 in frequency distributions, 47–48 Causation correlation and, 7, 73, 517–518 interpretation with, 517 Censored data, 103 Census, 4 Centerline, 704 Central Limit Theorem, 283–288 applications of, 286–288 defining, 284 fuzzy, 287 sample mean and, 285 sampling distribution and, 285 universal truths and, 284 Chebyshev’s theorem, 113 Chi-square distribution, 345–347, 735 critical values in, 346 degrees of freedom in, 346 formula, 345 properties of, 417–419 Chi-square test of homogeneity, 595–596 Chocolate chip cookies, 758 Cigarette contents, 751 Claimed distribution disagreement with, 579–582 in goodness-of-fit, 579–582 Claims testing with abnormal populations, 421 bootstrap resampling for, 395–396, 410, 426 confidence interval for, 395, 405, 409, 420 critical values for, 392, 405, 409 critical values in, 418 degrees of freedom in, 417 equivalent methods, 417 exact methods, 397–398 important properties of, 406 for non-normal population, 409–410 normal approximation method, 391–396 notation, 405, 416 about population means, 404–416, 429–430
RkJQdWJsaXNoZXIy NjM5ODQ=