Chapter 6, Introduction to Inferential Statistics Sampling & the Sampling Distribution Techniques for Probability Sampling EPSEM Sampling Techniques The Sampling Distribution Symbols and Terminology
Purpose of Inferential Statistics Learn about the characteristics of a population, based on samples. Estimation procedures - a “guess” is made, based on what is known about the sample. Hypothesis testing - validity of a hypothesis about the population is tested against sample outcomes.
Probability Sampling A sample is likely to be representative if it is selected by the EPSEM principle. Every element in the population must have an equal probability of selection for the sample. EPSEM - Equal Probability of Selection Method
Generating Simple Random Samples List of all elements or cases in the population. Develop a system for selection that guarantees that every case has an equal chance of being selected for the sample.
Systematic Sampling Only the first case is randomly selected. Thereafter every kth case is selected.
Stratified Sampling Population is divided into sublists according to a relevant trait. Sample is drawn from the sublist.
Cluster Sampling Groups of cases are selected rather than single cases. Clusters are often based on geography and the selection of clusters proceeds in stages. A less accurate representation of the population.
Characterizing a Variable Requires three types of information: The shape of its distribution. Some measure of central tendency. Some measure of dispersion.
Distributions in Inferential Statistics Sample - allows the researcher to learn about the population. Population -making inferences to the population is the purpose of inferential statistics. Sampling - because of the laws of probability, a great deal is known about this distribution.