Hansen-Hurwitz estimator
(→The Hansen-Hurwitz estimator: links added) |
|||
| Line 1: | Line 1: | ||
| − | {{ | + | {{Ficontent}} |
| − | + | ||
| − | + | ||
| − | + | ||
The Hansen-Hurwitz estimator gives the framework for all [[Sampling with unequal selection probabilities|unequal probability sampling]] with replacement (Hansen and Hurwitz, 1943<ref> Hansen MM and WN Hurwitz. 1943. On the theory of sampling from finite populations. Annals of Mathematical Statistics 14:333-362. </ref>). “With replacement” means that the [[selection probability|selection probabilities]] are the same for all draws; if selected elements would not be replaced (put back to the [[population]]), the selection probabilities would change after each draw for the remaining elements. | The Hansen-Hurwitz estimator gives the framework for all [[Sampling with unequal selection probabilities|unequal probability sampling]] with replacement (Hansen and Hurwitz, 1943<ref> Hansen MM and WN Hurwitz. 1943. On the theory of sampling from finite populations. Annals of Mathematical Statistics 14:333-362. </ref>). “With replacement” means that the [[selection probability|selection probabilities]] are the same for all draws; if selected elements would not be replaced (put back to the [[population]]), the selection probabilities would change after each draw for the remaining elements. | ||
| Line 8: | Line 5: | ||
Then the Hansen-Hurwitz estimator of the population total is | Then the Hansen-Hurwitz estimator of the population total is | ||
| − | |||
:<math>\hat \tau = \frac {1}{n} \sum_{i=1}^n \frac {y_i}{p_i}</math> | :<math>\hat \tau = \frac {1}{n} \sum_{i=1}^n \frac {y_i}{p_i}</math> | ||
| − | + | Here, each observation <math>y_i</math> is weighted by the inverse of its selection probability <math>p_i</math> | |
| − | Here, each observation <math>y_i</math> is weighted by the inverse of its selection probability <math>p_i</math> | + | |
| − | + | ||
The parametric [[variance]] of the total is | The parametric [[variance]] of the total is | ||
| − | |||
:<math>var (\hat \tau) = \frac {1}{n} \sum_{i=1}^N p_i \left (\frac {y_i}{p_i} - \tau \right )^2</math> | :<math>var (\hat \tau) = \frac {1}{n} \sum_{i=1}^N p_i \left (\frac {y_i}{p_i} - \tau \right )^2</math> | ||
| − | |||
which is [[bias|unbiasedly]] estimated from a sample size ''n'' from | which is [[bias|unbiasedly]] estimated from a sample size ''n'' from | ||
| − | |||
:<math>v\hat ar (\hat \tau) = \frac {1}{n} \frac {\sum_{i=1}^n \left (\frac {y_i}{p_i} - \tau \right )^2}{n-1}</math> | :<math>v\hat ar (\hat \tau) = \frac {1}{n} \frac {\sum_{i=1}^n \left (\frac {y_i}{p_i} - \tau \right )^2}{n-1}</math> | ||
| − | |||
Latest revision as of 13:20, 26 October 2013
The Hansen-Hurwitz estimator gives the framework for all unequal probability sampling with replacement (Hansen and Hurwitz, 1943[1]). “With replacement” means that the selection probabilities are the same for all draws; if selected elements would not be replaced (put back to the population), the selection probabilities would change after each draw for the remaining elements.
Suppose that a sample of size n is drawn with replacement and that on each draw the probability of selecting the i-th unit of the population is \(p_i\).
Then the Hansen-Hurwitz estimator of the population total is
\[\hat \tau = \frac {1}{n} \sum_{i=1}^n \frac {y_i}{p_i}\]
Here, each observation \(y_i\) is weighted by the inverse of its selection probability \(p_i\)
The parametric variance of the total is
\[var (\hat \tau) = \frac {1}{n} \sum_{i=1}^N p_i \left (\frac {y_i}{p_i} - \tau \right )^2\]
which is unbiasedly estimated from a sample size n from
\[v\hat ar (\hat \tau) = \frac {1}{n} \frac {\sum_{i=1}^n \left (\frac {y_i}{p_i} - \tau \right )^2}{n-1}\]
Hansen-Hurwitz estimator examples: 4 application examples
[edit] References
- ↑ Hansen MM and WN Hurwitz. 1943. On the theory of sampling from finite populations. Annals of Mathematical Statistics 14:333-362.
