This preview shows pages 1–18. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Click to edit Master subtitle style Applied Probability Methods for Engineers Slide Set 2 Click to edit Master subtitle style Chapter 6 Descriptive Statistics Data and Samples n When we want information about a phenomenon or characteristic, often cannot have complete information n We collect as much data as is practical from the entire set of possibilities, or population n Given a random variable X, we obtain a sample of observations of the phenomenon, x1, x2, , xn n We analyze sample data and use this analysis to make inferences about the population n To ensure as accurate a representation of the population as possible, we need to ensure that we take a random sample Data Presentation n Bar chart Machine Breakdowns Data Presentation n Pareto chart Histograms n Used to show frequency of occurrences (or distribution) of numerical data n Similar to a probability mass function (pmf) n A pmf is a histogram for a population (or entire sample space) Histograms Positive skewness (right skewed) Negative skewness (left skewed) Histograms Bimodal distribution Outliers Sample Statistics n Sample mean of a data set is arithmetic average n Sample median is the middle value (if n even, average value & n/2R and & n/2& n Sample mode is the most commonly occurring value n Sample variance 1 / n i i x x n = = ( 29 ( 29 2 2 2 2 2 1 1 2 1 1 1 1 1 n n n n i i i i i i i i x x n x x x nx s n n n = = = = = = = Sample Statistics Boxplots n Used to represent quartiles of data and provides a picture of the distribution Coefficient of Variation n Measures relative variability n CV = s/x for sample data n Allows comparing different random variables on equal footing n For a distribution with known parameters, CV = / n Binomial CV = n Poisson CV = n Exponential CV = 1 n Gamma CV = ( 29 1 / p np 1/ 1/ k Click to edit Master subtitle style Chapter 7 Statistical Estimation and Sampling Distributions Parameters and Statistics n A parameter is a true, fixed value that, in statistical analysis is usually unknown n May be the true mean or true variance 2 of a probability distribution n The true value of a parameter is estimated from sample data n A statistic is a property of sample data taken from a population n A point estimate of some unknown parameter is a statistic that provides a best guess at the parameter value Parameters and Statistics Point Estimates n A point estimate is unbiased if n The bias of a biased estimate is n Suppose we dont know the probability of success p in a sequence of Bernoulli trials n If there are n trials, we use the point estimate for p n The number of successes, X ~ B(n, p), so that E(X) = np, implying n Therefore is an unbiased estimator of p ( 29 E = ( 29 E  / p X n = ( 29 ( 29 / E p E X n p = = p Point estimates n If X1, , Xn are sample observations from a distribution with mean , consider the sample mean n Observe that n This shows that = X is an unbiased estimator of...
View Full
Document
 Spring '07
 JosephGeunes

Click to edit the document details