Lecturre 10

# Lecturre 10 - Todays Topics Econ1320 Lecture 10 Survey...

This preview shows pages 1–2. Sign up to view the full content.

1 1 Econ1320 Lecture 10 Survey Sampling Sections 7.1 Extra reading: Harrison & Tamaschke Ch 14 2 Today’s Topics b The Objective of Sampling b Some Technical Terms b Non-sampling Errors in Surveys b Sampling Errors b Alternative Sampling Designs s Random sampling without replacement s Stratified sampling s Cluster sampling b Systematic Sampling b Randomised Response Sampling 3 Background b In earlier topics we have been learning about various procedures for drawing inferences from sample data (e.g. inferences concerning μ or p ). b The formulas we have been using are generally only appropriate when the sample data collected using a particular sampling design (e.g. the formula is appropriate when the sample data has been collected using simple random sampling with replacement). In today lecture, we discuss… b Alternative methods for collecting the sample data that might be more cost effective and/or lead to smaller errors in estimation. b How to modify our formulas when we use these alternative sampling designs. n s t x 2 α ± 4 The Objective Of Sampling b is to estimate population parameters (e.g., means, proportions) using information contained in a sample. b We control the quantity of information contained in the sample by controlling s the amount of sample data collected (i.e., the number of observations) and s the sampling design used to collect it (e.g., simple random sample, cluster sample). b Which sampling design is most appropriate? b How does the choice of sampling design affect the way we use the sample data to estimate the population parameters? 5 Example 1 b A dental researcher is interested in determining the dental health of school children in a particular area. She undertakes the following procedure: 1. Uses the school records to draw up a list of all school children in the community. 2. Randomly selects children from the list. 3. Examines each selected child to determine the number of cavities. 4. Uses the collected data to estimate the population mean number of cavities. S How does she select children from her list? S How does this choice affect the way she estimates the population mean? S How does it affect the precision of the estimate? 6 Some Technical Terms b Element : an object on which a measurement is taken (e.g., a schoolchild) b Population: a collection of elements about which we wish to make an inference (e.g., all school children in the community). We must always define the population before we collect the sample. b Sampling units : non-overlapping collections of elements in the population that cover the entire population (e.g., a schoolchild; a class of schoolchildren). b Sampling frame: a list of sampling units (e.g. a list of all school children; a list of classes). b

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 10/21/2009 for the course ECON 1320 taught by Professor John during the Three '08 term at Queensland.

### Page1 / 8

Lecturre 10 - Todays Topics Econ1320 Lecture 10 Survey...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online