Point Estimators, Interval Estimation

Point Estimators, Interval Estimation - Chapter 7.1...

Info icon This preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
Chapter 7.1 Properties of Point Estimators Let the random sample , , . . . , be a set of random variables that are independently and identically distributed. 1 X 2 X n X Population characteristics are summarized by parameters – the true values are typically unknown. For example, the population mean is denoted by μ . An estimation rule can be specified for a parameter of interest. This estimation rule is called a point estimator . For example, a point estimator for the population mean is: μ = = n 1 i i X n 1 X An estimator is a random variable that is a function of the sample information. An estimator has a probability distribution called the sampling distribution. Econ 325 – Chapter 7 1
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
An applied study works with a data set. The numeric observations are: , , . . . , . 1 x 2 x n x The estimation rule given by the estimator X can be used to calculate a point estimate of the population mean μ : = = n 1 i i x n 1 x ¾ An important distinction is made between an estimator and an estimate. A point estimator is a random variable. A point estimate is a numeric outcome. Different samples of data will have different numeric observations and, therefore, will result in different point estimates of the population parameter. Econ 325 – Chapter 7 2
Image of page 2
Properties of Point Estimators Denote (the Greek letter theta) as a population parameter to be estimated (as a special case this may be the population mean ). θ μ Let θ ˆ (theta-hat) be a point estimator of θ . θ ˆ is a function of the sample information: ) X , , X , X ( f ˆ n 2 1 K = θ This estimator is a random variable with a sampling distribution. θ ˆ is said to be an unbiased estimator of θ if: θ = θ ) ˆ ( E The bias of an estimator θ ˆ is defined as: θ θ = θ ) ˆ ( E ) ˆ ( Bias It follows that the bias of an unbiased estimator is zero. Econ 325 – Chapter 7 3
Image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Example: Let , , be a random sample from a population with mean 1 X 2 X 3 X μ . That is, μ = = = ) X ( E ) X ( E ) X ( E 3 2 1 Consider two alternative point estimators of μ : ) X X X ( 3 1 X 3 2 1 + + = and ) X X 4 X ( 6 1 X 3 2 1 W + + = The second estimator is a weighted average of the sample information. To compare these estimators consider: μ = ) μ = + + = 3 ( 3 1 )] X ( E ) X ( E ) X ( E [ 3 1 ) X ( E 3 2 1 and μ = ) μ + μ + μ = + + = 4 ( 6 1 )] X ( E ) X ( E 4 ) X ( E [ 6 1 ) X ( E 3 2 1 W Therefore, both estimators are unbiased estimators of the population mean μ . Econ 325 – Chapter 7 4
Image of page 4