Selecting Input Distribution - DoMS, IIT Madras选择输入分布的延迟性肌肉酸痛，马德拉斯分校.pptVIP

* Probability plots The Q-Q plot will amplify the differences between the tails of the model distribution and the sample distribution. Whereas, the P-P plot will amplify the differences at the middle portion of the model and sample distribution. * Probability plots: Dataset * Probability plots: Dataset * Probability plots: Dataset * Probability plots: Dataset * Probability plots: Dataset * Probability plots: Dataset * Goodness-of-fit tests A goodness-of-fit test is a statistical hypothesis test that is used to assess formally whether the observations X1, X2, X3…Xn are an independent sample from a particular distribution with function F^. H0: The Xi’s are IID random variables with distribution function F^. Two famous tests: Chi-square test Kolmogorov - Smirnov test * Chi-square test Applicable for both: continuous as well as discrete distributions. Method of calculating chi-square test statistic: Divide the entire range of fitted distribution into k adjacent intervals -- [a0 ,a1), [a1,a2),…[ak-1,ak), where it could that a0 = -∞ in which case the first interval is (-∞,a1) and/or ak = ∞. Nj = # of Xi’s in the jth interval [aj-1,aj), j= 1,2…n. Next, we compute the expected proportion of Xi’s that would fall in the jth interval if we were sampling from fitted distribution * Chi-square test Finally the test statistic is calculated as: * Chi-square test This calculated value of the test statistic is compared with the tabulated value of chi-square distribution with k-1 df at 1-α level of significance. Selecting Input Distribution * Introduction The data on the input random variables of interest can be used in following ways: The data values themselves are used directly in the simulation. This is called trace-driven simulation. The data values could be used to define an empirical distribution function in some way. Standard techniques of statistical inferences are used to “fit” a theoretical distribution form to the data and perform hypothesis te