Chapter 5 Joint Probability Distributions and Random Samples  5.1 - Jointly Distributed Random Variables.2 - Expected Values, Covariance, and Correlation.3.

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

Statistical Estimation and Sampling Distributions
Sampling: Final and Initial Sample Size Determination
Estimation  Samples are collected to estimate characteristics of the population of particular interest. Parameter – numerical characteristic of the population.
Statistics review of basic probability and statistics.
Chapter 5 Discrete Random Variables and Probability Distributions
3.3 Toward Statistical Inference. What is statistical inference? Statistical inference is using a fact about a sample to estimate the truth about the.
Chapter 4 Discrete Random Variables and Probability Distributions
1 MF-852 Financial Econometrics Lecture 4 Probability Distributions and Intro. to Hypothesis Tests Roy J. Epstein Fall 2003.
Sampling Distributions
Review.
Chapter 6 Continuous Random Variables and Probability Distributions
Data Basics. Data Matrix Many datasets can be represented as a data matrix. Rows corresponding to entities Columns represents attributes. N: size of the.
SAMPLING DISTRIBUTIONS. SAMPLING VARIABILITY
Continuous Random Variables and Probability Distributions
Review of Probability and Statistics
Today Today: Chapter 8, start Chapter 9 Assignment: Recommended Questions: 9.1, 9.8, 9.20, 9.23, 9.25.
Normal and Sampling Distributions A normal distribution is uniquely determined by its mean, , and variance,  2 The random variable Z = (X-  /  is.
Prof. SankarReview of Random Process1 Probability Sample Space (S) –Collection of all possible outcomes of a random experiment Sample Point –Each outcome.
One Sample  M ean μ, Variance σ 2, Proportion π Two Samples  M eans, Variances, Proportions μ1 vs. μ2 σ12 vs. σ22 π1 vs. π Multiple.
Binomial and Related Distributions 學生 : 黃柏舜 學號 : 授課老師 : 蔡章仁.
Section 15.8 The Binomial Distribution. A binomial distribution is a discrete distribution defined by two parameters: The number of trials, n The probability.
1 If we can reduce our desire, then all worries that bother us will disappear.
ENGR 610 Applied Statistics Fall Week 3 Marshall University CITE Jack Smith.
Bernoulli Trials Two Possible Outcomes –Success, with probability p –Failure, with probability q = 1  p Trials are independent.
CHAPTER Discrete Models  G eneral distributions  C lassical: Binomial, Poisson, etc Continuous Models  G eneral distributions 
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.
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.
Math b (Discrete) Random Variables, Binomial Distribution.
Chapter 1 Overview and Descriptive Statistics 1111.1 - Populations, Samples and Processes 1111.2 - Pictorial and Tabular Methods in Descriptive.
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.
Confidence Interval & Unbiased Estimator Review and Foreword.
Chapter 3 Discrete Random Variables and Probability Distributions  Random Variables.2 - Probability Distributions for Discrete Random Variables.3.
Review of Probability. Important Topics 1 Random Variables and Probability Distributions 2 Expected Values, Mean, and Variance 3 Two Random Variables.
Review Normal Distributions –Draw a picture. –Convert to standard normal (if necessary) –Use the binomial tables to look up the value. –In the case of.
Probability Distributions, Discrete Random Variables
Point Estimation of Parameters and Sampling Distributions Outlines:  Sampling Distributions and the central limit theorem  Point estimation  Methods.
Chapter 5 Joint Probability Distributions and Random Samples  Jointly Distributed Random Variables.2 - Expected Values, Covariance, and Correlation.3.
Continuous Random Variables and Probability Distributions
Chapter 5 Sampling Distributions. Introduction Distribution of a Sample Statistic: The probability distribution of a sample statistic obtained from a.
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.
Sums of Random Variables and Long-Term Averages Sums of R.V. ‘s S n = X 1 + X X n of course.
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.
Sampling Distributions Chapter 18. Sampling Distributions A parameter is a number that describes the population. In statistical practice, the value of.
Chapter 6: Sampling Distributions
Chapter 5 Joint Probability Distributions and Random Samples
Chapter 3 Discrete Random Variables and Probability Distributions
Supplemental Lecture Notes
STAT 311 Chapter 1 - Overview and Descriptive Statistics
STAT 312 Chapter 7 - Statistical Intervals Based on a Single Sample
STAT 311 REVIEW (Quick & Dirty)
Chapter 6: Sampling Distributions
Chapter 5 Joint Probability Distributions and Random Samples
Discrete random variable X Examples: shoe size, dosage (mg), # cells,…
Sample Mean Distributions
Chapter 3 Discrete Random Variables and Probability Distributions
Parameter, Statistic and Random Samples
Chapter 4 Continuous Random Variables and Probability Distributions
t distribution Suppose Z ~ N(0,1) independent of X ~ χ2(n). Then,
Chapter 3 Discrete Random Variables and Probability Distributions
Random Sampling Population Random sample: Statistics Point estimate
ASV Chapters 1 - Sample Spaces and Probabilities
Sampling Distributions and the Central Limit Theorem
Discrete random variable X Examples: shoe size, dosage (mg), # cells,…
Econometric Models The most basic econometric model consists of a relationship between two variables which is disturbed by a random error. We need to use.
Chapter 3 Discrete Random Variables and Probability Distributions
CHAPTER 6 Statistical Inference & Hypothesis Testing
Chapter 3 Discrete Random Variables and Probability Distributions
1/2555 สมศักดิ์ ศิวดำรงพงศ์
Presentation transcript:

Chapter 5 Joint Probability Distributions and Random Samples  Jointly Distributed Random Variables.2 - Expected Values, Covariance, and Correlation.3 - Statistics and Their Distributions.4 - The Distribution of the Sample Mean.5 - The Distribution of a Linear Combination

X Density X = Age of women in U.S. at first birth Population Distribution of X Suppose X ~ N( μ, σ ), then… … etc…. μ = 25.4 σ = 1.5  x1x1 x  x  x3x3 x  x4x4 x2x2 x  x5x5 x Each of these individual ages x is a particular value of the random variable X. Most are in the neighborhood of μ, but there are occasional outliers in the tails of the distribution.

X = Age of women in U.S. at first birth Sample, n = 400 X Density Sample, n = 400 Sample, n = 400 Sample, n = 400 … etc…. Sample, n = 400 Population Distribution of X σ = 1.5 Suppose X ~ N( μ, σ ), then… μ = 25.4 Each of these sample mean values is a “point estimate” of the population mean μ… How are these values distributed?

X Density μ =μ = σ = 1.5 Density μ =μ = Suppose X ~ N( μ, σ ), then… X = Age of women in U.S. at first birth Sampling Distribution of for any sample size n. … etc…. Population Distribution of X μ = 25.4 How are these values distributed? Each of these sample mean values is a “point estimate” of the population mean μ… The vast majority of sample means are extremely close to μ, i.e., extremely small variability. “standard error”

Suppose X ~ N( μ, σ ), then… X Density μ =μ = σ = 2.4 Density μ =μ = X = Age of women in U.S. at first birth Sampling Distribution of for any sample size n. … etc…. Population Distribution of X μ = 25.4 “standard error” Each of these sample mean values is a “point estimate” of the population mean μ… The vast majority of sample means are extremely close to μ, i.e., extremely small variability.  for large sample size n. 

X ~ Anything with finite μ and σ Suppose X  N( μ, σ ), then… Suppose X ~ N( μ, σ ), then… X Density μ =μ = σ = 2.4 Density μ =μ = X = Age of women in U.S. at first birth Sampling Distribution of for any sample size n. … etc…. Population Distribution of X for large sample size n. μ = 25.4 “standard error” The vast majority of sample means are extremely close to μ, i.e., extremely small variability. Each of these sample mean values is a “point estimate” of the population mean μ… 

Density  “standard error”

Density    “standard error”  Probability that a single house selected at random costs less than $300K = ? Example: X = Cost of new house ($K) = Cumulative area under density curve for X up to = Z-score

Density    “standard error”  Probability that a single house selected at random costs less than $300K = ? Example: X = Cost of new house ($K) 300 = Z-score

Density    “standard error”  Probability that the sample mean of n = 36 houses selected at random is less than $300K = ? Example: X = Cost of new house ($K) 300 $12.5K = Cumulative area under density curve for up to 300. Probability that a single house selected at random costs less than $300K = ? = Z-score

Density    “standard error”  Probability that the sample mean of n = 36 houses selected at random is less than $300K = ? Example: X = Cost of new house ($K) 300 $12.5K Probability that a single house selected at random costs less than $300K = ? = Z-score = Z-score

 Density  “standard error”    approximately  mild skew large 

Density  “standard error”    approximately  continuous or discrete, large as n  ,   ~ CENTRAL LIMIT THEOREM ~ 

Density  “standard error”    approximately   continuous or discrete, large as n  ,   ~ CENTRAL LIMIT THEOREM ~ Example: X = Cost of new house ($K)

Density  “standard error” Density   Example: X = Cost of new house ($K) 300 $12.5K Probability that the sample mean of n = 36 houses selected at random is less than $300K = ? Probability that a single house selected at random costs less than $300K = ? = Z-score = Cumulative area under density curve for X up to 300.

16

17 xf(x)f(x)

= = =

19

20

21 possibly log-normal… each based on 1000 samples but remember Cauchy and 1/x 2, both of which had nonexistent  … CLT may not work! heavily skewed tail More on CLT…

More on CLT… X Density  X = Age of women in U.S. at first birth Population Distribution of X Random Variable If this first individual has been randomly chosen, and the value of X measured, then the result is a fixed number x 1, with no random variability… and likewise for x 2, x 3, etc. DATA! X ~ Dist ( μ, σ )

More…  X = Age of women in U.S. at first birth Population Distribution of X X Density Random Variable If this first individual has been randomly chosen, and the value of X measured, then the result is a fixed number x 1, with no random variability… and likewise for x 2, x 3, etc. DATA! However, if this is not the case, then this first “value” of X is unknown, thus can be considered as a random variable X 1 itself… and likewise for X 2, X 3, etc. The collection {X 1, X 2, X 3, …, X n } of “independent, identically-distributed” (i.i.d.) random variables is said to be a random sample. X ~ Dist ( μ, σ )

More… X = Age of women in U.S. at first birth Population Distribution of X X Density Random Variable X ~ Dist ( μ, σ ) Sample, size n Density etc…… Claim: Proof: Sampling Distribution of for any n

More… X = Age of women in U.S. at first birth Population Distribution of X X Density Random Variable X ~ Dist ( μ, σ ) Density etc…… Claim: Proof: Sampling Distribution of for any n

M o r e o n C L T … R e c a l l … Normal Approximation to the Binomial Distribution 26 continuousdiscrete P(Success) =  P(Failure) = 1 –  Discrete random variable X = # Successes (0, 1, 2,…, n) in a random sample of size n Suppose a certain outcome exists in a population, with constant probability . We will randomly select a random sample of n individuals, so that the binary “Success vs. Failure” outcome of any individual is independent of the binary outcome of any other individual, i.e., n Bernoulli trials (e.g., coin tosses). Then X is said to follow a Binomial distribution, written X ~ Bin(n,  ), with “probability function” f(x) =, x = 0, 1, 2, …, n.

Normal Approximation to the Binomial Distribution 27 continuousdiscrete P(Success) =  P(Failure) = 1 –  Discrete random variable X = # Successes (0, 1, 2,…, n) in a random sample of size n Suppose a certain outcome exists in a population, with constant probability . We will randomly select a random sample of n individuals, so that the binary “Success vs. Failure” outcome of any individual is independent of the binary outcome of any other individual, i.e., n Bernoulli trials (e.g., coin tosses). Then X is said to follow a Binomial distribution, written X ~ Bin(n,  ), with “probability function” f(x) =, x = 0, 1, 2, …, n. CLT See Prob 5.3/7

Normal Approximation to the Binomial Distribution 28 continuousdiscrete P(Success) =  P(Failure) = 1 –  Discrete random variable X = # Successes (0, 1, 2,…, n) in a random sample of size n Suppose a certain outcome exists in a population, with constant probability . We will randomly select a random sample of n individuals, so that the binary “Success vs. Failure” outcome of any individual is independent of the binary outcome of any other individual, i.e., n Bernoulli trials (e.g., coin tosses). Then X is said to follow a Binomial distribution, written X ~ Bin(n,  ), with “probability function” f(x) =, x = 0, 1, 2, …, n. CLT ??

29 PARAMETER ESTIMATOR (Not to be confused with an “estimate”) SAMPLING DISTRIBUTION (or approximation)  = “true” population mean of a numerical random variable X, where  = “true” population probability of Success, where “Success vs. Failure” are the only possible binary outcomes. In general….  In general….  want “nice” properties

30 PARAMETER ESTIMATOR (Not to be confused with an “estimate”) SAMPLING DISTRIBUTION (or approximation) want “nice” properties In general….  In general….  (see page 253)

31 PARAMETER ESTIMATOR (Not to be confused with an “estimate”) SAMPLING DISTRIBUTION (or approximation) want “nice” properties In general….  In general….  Recall: Rearrange terms:

32 PARAMETER ESTIMATOR (Not to be confused with an “estimate”) SAMPLING DISTRIBUTION (or approximation) want “nice” properties In general….  In general….  Recall: Ideally, we would like to minimize MSE, but this is often difficult in practice. However, if Bias = 0, then MSE = Variance, so it is desirable to seek Minimum Variance Unbiased Estimators (MVUE)…