1 G89.2228 Lect 3b G89.2228 Lecture 3b Why are means and variances so useful? Recap of random variables and expectations with examples Further consideration.

Slides:



Advertisements
Similar presentations
Week11 Parameter, Statistic and Random Samples A parameter is a number that describes the population. It is a fixed number, but in practice we do not know.
Advertisements

Chapter 7 Title and Outline 1 7 Sampling Distributions and Point Estimation of Parameters 7-1 Point Estimation 7-2 Sampling Distributions and the Central.
Sampling: Final and Initial Sample Size Determination
SOLVED EXAMPLES.
Maximum likelihood Conditional distribution and likelihood Maximum likelihood estimations Information in the data and likelihood Observed and Fisher’s.
Statistical Inference Chapter 12/13. COMP 5340/6340 Statistical Inference2 Statistical Inference Given a sample of observations from a population, the.
Statistics Lecture 20. Last Day…completed 5.1 Today Parts of Section 5.3 and 5.4.
Evaluating Hypotheses
Data Basics. Data Matrix Many datasets can be represented as a data matrix. Rows corresponding to entities Columns represents attributes. N: size of the.
Continuous Random Variables and Probability Distributions
Lecture 7 1 Statistics Statistics: 1. Model 2. Estimation 3. Hypothesis test.
A) Transformation method (for continuous distributions) U(0,1) : uniform distribution f(x) : arbitrary distribution f(x) dx = U(0,1)(u) du When inverse.
Maximum likelihood (ML)
Random Variable and Probability Distribution
Econ 482 Lecture 1 I. Administration: Introduction Syllabus Thursday, Jan 16 th, “Lab” class is from 5-6pm in Savery 117 II. Material: Start of Statistical.
Review of Probability.
Random Sampling, Point Estimation and Maximum Likelihood.
Random Variables Section 3.1 A Random Variable: is a function on the outcomes of an experiment; i.e. a function on outcomes in S. For discrete random variables,
Variability The goal for variability is to obtain a measure of how spread out the scores are in a distribution. A measure of variability usually accompanies.
Functions of Random Variables. Methods for determining the distribution of functions of Random Variables 1.Distribution function method 2.Moment generating.
Variance and Covariance
1 Lecture 4. 2 Random Variables (Discrete) Real-valued functions defined on a sample space are random vars. determined by outcome of experiment, we can.
G Lect 21 G Lecture 2 Regression as paths and covariance structure Alternative “saturated” path models Using matrix notation to write linear.
CPSC 531: Probability Review1 CPSC 531:Probability & Statistics: Review II Instructor: Anirban Mahanti Office: ICT 745
1 G Lect 8b G Lecture 8b Correlation: quantifying linear association between random variables Example: Okazaki’s inferences from a survey.
Lecture 15: Statistics and Their Distributions, Central Limit Theorem
Continuous Distributions The Uniform distribution from a to b.
1 G Lect 4a G Lecture 4a f(X) of special interest: Normal Distribution Are These Random Variables Normally Distributed? Probability Statements.
Statistical Applications Binominal and Poisson’s Probability distributions E ( x ) =  =  xf ( x )
Chapter 7 Sampling and Sampling Distributions ©. Simple Random Sample simple random sample Suppose that we want to select a sample of n objects from a.
1 G Lect 2M Examples of Correlation Random variables and manipulated variables Thinking about joint distributions Thinking about marginal distributions:
: Chapter 3: Maximum-Likelihood and Baysian Parameter Estimation 1 Montri Karnjanadecha ac.th/~montri.
1 G Lect 2w Review of expectations Conditional distributions Regression line Marginal and conditional distributions G Multiple Regression.
Consistency An estimator is a consistent estimator of θ, if , i.e., if
Chapter 7 Point Estimation of Parameters. Learning Objectives Explain the general concepts of estimating Explain important properties of point estimators.
Expectation. Let X denote a discrete random variable with probability function p(x) (probability density function f(x) if X is continuous) then the expected.
Confidence Interval & Unbiased Estimator Review and Foreword.
Estimators and estimates: An estimator is a mathematical formula. An estimate is a number obtained by applying this formula to a set of sample data. 1.
Review of Probability. Important Topics 1 Random Variables and Probability Distributions 2 Expected Values, Mean, and Variance 3 Two Random Variables.
Brief Review Probability and Statistics. Probability distributions Continuous distributions.
Point Estimation of Parameters and Sampling Distributions Outlines:  Sampling Distributions and the central limit theorem  Point estimation  Methods.
Statistical Estimation Vasileios Hatzivassiloglou University of Texas at Dallas.
CHAPTER 9 Inference: Estimation The essential nature of inferential statistics, as verses descriptive statistics is one of knowledge. In descriptive statistics,
BASIC STATISTICAL CONCEPTS Statistical Moments & Probability Density Functions Ocean is not “stationary” “Stationary” - statistical properties remain constant.
Continuous Random Variables and Probability Distributions
Describing Samples Based on Chapter 3 of Gotelli & Ellison (2004) and Chapter 4 of D. Heath (1995). An Introduction to Experimental Design and Statistics.
Variability Introduction to Statistics Chapter 4 Jan 22, 2009 Class #4.
Lecture 1: Basic Statistical Tools. A random variable (RV) = outcome (realization) not a set value, but rather drawn from some probability distribution.
Statistics Sampling Distributions and Point Estimation of Parameters Contents, figures, and exercises come from the textbook: Applied Statistics and Probability.
Week 31 The Likelihood Function - Introduction Recall: a statistical model for some data is a set of distributions, one of which corresponds to the true.
Week 21 Order Statistics The order statistics of a set of random variables X 1, X 2,…, X n are the same random variables arranged in increasing order.
G. Cowan Lectures on Statistical Data Analysis Lecture 9 page 1 Statistical Data Analysis: Lecture 9 1Probability, Bayes’ theorem 2Random variables and.
Engineering Probability and Statistics - SE-205 -Chap 3 By S. O. Duffuaa.
R. Kass/W03 P416 Lecture 5 l Suppose we are trying to measure the true value of some quantity (x T ). u We make repeated measurements of this quantity.
Evaluating Hypotheses. Outline Empirically evaluating the accuracy of hypotheses is fundamental to machine learning – How well does this estimate its.
1 Ka-fu Wong University of Hong Kong A Brief Review of Probability, Statistics, and Regression for Forecasting.
Week 21 Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
Random Variables By: 1.
Evaluating Hypotheses. Outline Empirically evaluating the accuracy of hypotheses is fundamental to machine learning – How well does this estimate accuracy.
Sampling and Sampling Distributions
MECH 373 Instrumentation and Measurements
Variance and Covariance
Probability 9/22.
Probability and Estimation
Sample Mean Distributions
Parameter, Statistic and Random Samples
Probability and Estimation
Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
Applied Statistics and Probability for Engineers
Presentation transcript:

1 G Lect 3b G Lecture 3b Why are means and variances so useful? Recap of random variables and expectations with examples Further consideration of random variables Expected mean and variance of averages Estimates of population variance Bias of Variance Estimator

2 G Lect 3b Why are Means and Variances so useful? The commonly observed NORMAL distribution is indexed by two parameters  and  2, the mean and variance  is the index of location, and  2 is the index of spread. We can estimate the relative frequency of values given  and  

3 G Lect 3b An example: learning about distributions Suppose we were planning to study performance variables that are known to be affected by anxiety. Is the distribution of performance scores obtained in the month following the WTC attack systematically different from previous studies? Suppose we plan to measure performance with a measure that goes from 1 to 10, but published studies used a measure that ranged from 0 to 5. How are the means and variances affected by this difference in range?

4 G Lect 3b Expectations Recap A Random Variable is a real-valued function defined on a sample space. f(X) is a function that describes the likelihood of each value of X »Density function for continuous X »Probability mass function for discrete X Suppose that g(X) is any arbitrary function of values of X. E(g(X)) is the expectation of g(X), the average value of g(X) in the population » For continuous variables: »For discrete variables:

5 G Lect 3b Recap: First Moment (the Mean  x ) E(X)=  x is the first moment, the mean For k an arbitrary fixed constant: »E(X+k) = E(X)+k =  x +k »E(k*X) = k*E(X) = k*  x Let Y be a second random variable (perhaps related to X, perhaps not): »E(X+Y) = E(X)+E(Y) =  x +  y »E(X-Y) = E(X)-E(Y) =  x -  y

6 G Lect 3b Example We can relate the 1-10 scale to the 0-5 scale with a simple linear function. »Let X be on the 0-5 scale. »G(X) is on the 1-10 scale G(X) = (9/5)X + 1 If E(X), the mean of X, is  X then E[G(X)], the mean of G(X), is »E[G(X)] = (9/5)  X + 1

7 G Lect 3b Recap: Second Moment (the Variance V(X)) Let k be a fixed constant » Let Y be another random variable independent of X, then: »

8 G Lect 3b Example If X is on the 0-5 scale. »G(X) is on the 1-10 scale G(X) = (9/5)X + 1 If V(X), the variance of X, is    X then V[G(X)], the variance of G(X), is »V[G(X)] = (9/5) 2    X The standard deviation is the square root of the variance »The standard deviation of G(X) is simply (9/5) the standard deviation of X.

9 G Lect 3b Notes on Random Variables Statisticians consider all instances of X to be random variables E.G., A sample of 10 women measured on CESD gives 10 random variables »independent if sampled randomly »identically distributed if from same population hence, same f(X) i.i.d. is shorthand for “independent, identically distributed” Note that data analysts use the term “variable” to refer to one kind of measure. If the sample has n subjects, the variable describes the set of n random variables in the statistician’s sense.

10 G Lect 3b Random Variables Need Not Be Independent Three outcomes measured on a single subject are three random variables »They are not likely to be independent, nor to have the same f(X) »We would then consider the multivariate joint density, f(X 1,X 2,X 3 ) Random variables can be nonindependent in other ways »Unit of analysis issue »E.g., randomly selected employees within randomly selected supervisor’s teams If supervisor level is ignored, employees are not sampled randomly (rather in “clusters”) Within a team, the employees may be considered independent »Average team score may be assumed to be independent over supervisors, however

11 G Lect 3b Example: Sample of Size 10 The values at the right have a variance of 3.8, (standard deviation of 1.9). The mean of the sample is 6.2. What can we say about the population from which the numbers are sampled? What can we say about the sample statistics themselves?

12 G Lect 3b Studying sample statistics using expectation operators Let be the sample average of n random variables that are independently sampled from the same distribution (i.i.d). (The expected mean of each X is the same, as is the expected variance). Because the expectation of the sample mean is equal to the parameter it is estimating, we say it is unbiased.

13 G Lect 3b Expected variance of the sample mean The expected variance of the sample mean goes down directly with increased sample size, n.

14 G Lect 3b Bias of a Variance Estimator If variance is defined as the average squared deviation from the mean, consider the estimate, On the average, will this function of the data give an unbiased estimate? »The answer is NO! »The conceptual reason is that the sample mean is itself variable »The expected value of the above sample estimate is   [(n-1)/n]

15 G Lect 3b Bias of a Variance Estimator 2 First, let’s derive an alternative definition of variance: Next, let’s do the same for our biased variance estimator:

16 G Lect 3b Bias of a Variance Estimator 3 To determine bias, we determine the expected value: The first term is:

17 G Lect 3b Bias of a Variance Estimator 4 The second term is: Hence, To make it unbiased,