Variance Estimation and Precision
- Example 1: Balanced and Unbalanced Two-Way Mixed Models
This example is based on a data set from Milliken and Johnson (1992, table 23.1). A company wanted to replace the machines used to make a certain component in one of its factories. Three different brands of machines were available, so the management designed an experiment to evaluate the productivity of the machines when operated by the company’s own personnel. Six employees were randomly selected to participate in the experiment, each of whom was to operate each machine three different times. The data recorded were overall scores, which took into account the number and quality of components produced. - Example 2: Variance Component Estimation for a Four-Way Mixed Factorial Design
- Example 3: Variance Component Estimation for a Hierarchically Nested Random Design
- Example 4: Estimating the Population Intraclass Correlation in Variance Estimation and Precision
- Example 5: Analyzing a Nested Mixed Model
The data for this example were taken from Milliken and Johnson, figure 30.2. A comfort experiment was conducted to study the effects of temperature and gender on a person’s comfort. Researchers were interested only in three temperature settings: 65, 70, and 75 degrees Fahrenheit. Each temperature setting was randomly assigned to three of nine available environmental chambers. Eighteen males and eighteen females were randomly assigned to chambers so that two males and two females were assigned to each of the nine chambers. After the people were subjected to the environmental condition for three hours, their comfort was measured.
Copyright © 2021. Cloud Software Group, Inc. All Rights Reserved.