RCH 8303, Quantitative Data Analysis 1

Course Learning Outcomes for Unit VI Upon completion of this unit, students should be able to:

1. Perform statistical tests using software tools. 1.1 Perform analysis of variance (ANOVA) using appropriate data file and menu options.

2. Explain results of statistical tests.

2.1 Describe the selection process of the variables in the data file. 2.2 Discuss the differences between alternative hypotheses. 2.3 Elaborate on options available for missing or incomplete data. 2.4 Describe the assumptions for an ANOVA. 2.5 Contrast the differences between an ANOVA and an independent sample t-test.

3. Judge whether null hypotheses should be rejected or maintained.

3.1 Explain the differences between the null and alternative hypotheses, and perform option selection.

3.2 Perform an ANOVA option selection.

Course/Unit Learning Outcomes

Learning Activity

1.1 Unit Lesson Chapter 6 Unit VI Assignment 2

2.1, 2.2, 2.3, 2.4, 2.5 Unit Lesson Unit VI Assignment 1

3.1, 3.2 Unit Lesson Unit VI Assignment 2

Required Unit Resources Chapter 6: Simple Statistical Tests

Unit Lesson

Unit VI Plan The Unit VI assignment will be in two parts. Part 1 of your assignment requires you to complete modules of the Collaborative Institutional Training Initiative (CITI) Program Essentials of Statistical Analysis (EOSA) that relate directly to the reading in this unit. Each of the modules has a final quiz that must be completed and successfully passed to demonstrate your knowledge of basic statistics and the research process. For Part 2, you will review how to conduct an analysis of variance (ANOVA) to determine whether differences in means are statistically significant between three or more groups. These are the topics of the Unit VI CITI EOSA course.

UNIT VI STUDY GUIDE

ANOVA

RCH 8303, Quantitative Data Analysis 2

UNIT x STUDY GUIDE

Title

Analysis of Variance (ID 17625): This module describes and explains conducting analyses comparing three or more groups and testing for equality of variances. The module describes the assumptions of the ANOVA, which are the same basic assumptions of the independent-samples t-test and what to do if the data violates one or more of the assumptions. The module concludes with testing homogeneity of variances. Following Up Significant ANOVA (ID 17626): This module describes and explains conducting pairwise comparisons and planned contrast ANOVAs. The module explains what to do if the ANOVA is significant and how to determine which groups mean are different from the others.

Unit VI Lesson Unit VI builds on the Unit IV t-test with an ANOVA being used to test three or more groups. Many people think simply doing a t-test with three or four groups is an option; however, once you exceed two groups you need to use an ANOVA with more than two groups. The t-test discussed in Unit V is used to compare two means (e.g., training and no training runtimes), while Unit VI focuses on the ANOVA, which is used to compare means between more than two groups (e.g., runtimes between runners in groups A, B, and C). For this unit, we will be asking the question; Are there differences in runtimes between runners in A, B, and C? The example in the lesson will work through an ANOVA and answer this question. As noted in Unit III, once data are collected, a researcher needs to be able to describe, summarize, and, potentially, detect patterns in the data they have recorded with meaningful numerical scales such as histogram. After reviewing the data, decisions must be made regarding whether the assumptions of the test have been met. If they have, then conducting of the test can proceed. Refer to these tutorials on the two assumptions associated with these tests: Homogeneity of Variances and Testing for Normality. For an example of an ANOVA, make sure when you access R that you also load R Commander. Type in library(Rcmdr) or see Unit I for a refresher on how to gain access to R Commander. Once R and R Commander have been loaded the next step is to load the data set threeruntime that will be used (Figure 1).

RCH 8303, Quantitative Data Analysis 3

UNIT x STUDY GUIDE

Title

Figure 1 Data Set Threeruntime Successfully Uploaded

RCH 8303, Quantitative Data Analysis 4

UNIT x STUDY GUIDE

Title

Viewing the updated data set allows a user to examine the type of category information and numeric values (Figure 2). Figure 2 Visual Representation of Threeruntime Data Set

Note that in Figure 2, the variable category has three groups, and the variable runtimes contains continuous or interval information. This allows the data in runtimes to be measured by the grouping and an ANOVA to be performed.

RCH 8303, Quantitative Data Analysis 5

UNIT x STUDY GUIDE

Title

The next step is to plot the data set in groups. This will allow us the opportunity to view the data set in graphical display. Select Graphs and then Histogram (Figure 3). Figure 3 Histogram Selection Menu

RCH 8303, Quantitative Data Analysis 6

UNIT x STUDY GUIDE

Title

Since our data has three grouping variables, selecting the Plot by groups option will allow us to view the data set by groupings (Figure 4). Figure 4 Plot by Groups Selection Menu

RCH 8303, Quantitative Data Analysis 7

UNIT x STUDY GUIDE

Title

Selecting Plot by groups offers our grouping variable to select. Since we only have one, we select category and then press “OK.” This will produce the histogram of our data set (Figure 5). Figure 5 Groups Variable Selection Menu

RCH 8303, Quantitative Data Analysis 8

UNIT x STUDY GUIDE

Title

Data display of our grouping variable (Figure 6) is shown below. Figure 6 Plot by Groups Data Display

RCH 8303, Quantitative Data Analysis 9

UNIT x STUDY GUIDE

Title

Following the data plot by groups, we need to check homogeneity of variances. Please review the Homogeneity of Variances tutorial discussed earlier. For our threeruntime data set, select Statistics, Variances, and Bartlett’s test (Figure 7) Figure 7 Homogeneity of Variances selection menu

RCH 8303, Quantitative Data Analysis 10

UNIT x STUDY GUIDE

Title

Selecting “OK” will run the Bartlett’s Test (Figure 8). Figure 8 Bartlett’s Test Selection Menu

RCH 8303, Quantitative Data Analysis 11

UNIT x STUDY GUIDE

Title

Bartlett’s Test output results indicating homogeneity of variances (Figure 9) are shown below. Figure 9 Bartlett’s Test Output Results

A Bartlett’s test of the homogeneity of variance was performed on the runtime variable based on category. Since the p-value of this test was greater than .05, indicating normality, the null hypothesis would not be rejected. If a researcher wanted to include this result in a paper, the following narrative could be used:

A Bartlett’s test was performed to examine the runtime variable’s variance across the three groups. The result of the test was not significant, K2(2) = 5.67, p = .059.

If the Bartlett test was significant, departures from normality may be causing the test to report a significant value. One option is to perform the Levene test, which has been shown to be less sensitive to discrepancies to normality. Another option would be to transform the data so that if follows a normal distribution (which is outside the scope of this lesson).

RCH 8303, Quantitative Data Analysis 12

UNIT x STUDY GUIDE

Title

We are now ready to conduct the ANOVA. The menu options are shown below (Figure 10). Figure 10 ANOVA Selection Menu

Once a one-way ANOVA is selected, a new menu option is provided. First, a default name of the model is provided (AnovaModel.1). Second, a user must select the grouping variable. Third, a user selects the response variable. Since an ANOVA will only show whether there is a difference between the groups, a pairwise comparison between groups must be examined with the p-value is < .05. Thus, the Pairwise comparison of means checkbox should be activated. Finally, if a user wants to perform the Welch version of test, which assumes unequal variances, the other checkbox should be activated (Figure 11).

RCH 8303, Quantitative Data Analysis 13

UNIT x STUDY GUIDE

Title

Figure 11 ANOVA Options Selection Menu With Pairwise Comparisons

RCH 8303, Quantitative Data Analysis 14

UNIT x STUDY GUIDE

Title

Selecting “Ok” will perform the test and display results of the ANOVA (Figure 12). Figure 12 Output of ANOVA for AnovaModel.1

As indicated in Figure 12, the result of the test was significant (p < .05).

RCH 8303, Quantitative Data Analysis 15

UNIT x STUDY GUIDE

Title

As displayed below (Figure 13), the differences between the three groups are significant. Figure 13 Pairwise Comparison of Means Using Tukey’s (1949) Contrasts

In addition to simultaneous tests for the general linear hypotheses, simultaneous confidence intervals can be obtained (Figure 14). Figure 14 Pairwise Confidence Intervals Using Tukey’s Contrasts

RCH 8303, Quantitative Data Analysis 16

UNIT x STUDY GUIDE

Title

Many researchers also display the differences of means using graphical representation. Viewing the means in a linear fashion and a plot of means aids in visual representation of the data means (Figure 15), as shown below. Figure 15 Plot of Family-Wise 95% Confidence Intervals

RCH 8303, Quantitative Data Analysis 17

UNIT x STUDY GUIDE

Title

In addition, one could plot the means and confidence intervals a different way (Figure 16). Figure 16 Plot of Means

This concludes Unit V. The ANOVA used to compare more than two means (e.g., runtimes between runners in groups A, B, and C) was discussed. An ANOVA works with more than two groups. In Unit VI, we will be asking these questions: Are there differences in runtimes between runners in A, B, and C? Is there a positive or negative relationship between two variables? Unit VI starts on a different type of outcome form of testing. Units IV and V conducted tests that compared the means, and in some cases, a causation could be determined. The focus of Unit VI is Correlation, which is a methodology that tests to determine whether there is a relationship between variables.

Reference Tukey, J. W. (1949, June). Comparing individual means in the analysis of variance. Biometrics, 5(2), 99–114.

https://doi.org/10.2307/3001913

Learning Activities (Nongraded) Nongraded Learning Activities are provided to aid students in their course of study. You do not have to submit them. If you have questions, contact your instructor for further guidance and information. When studying APA formatting, pay particular attention to the sections that pertain to formatting for research and statistics. Review these sections as needed.

- Course Learning Outcomes for Unit VI
- Required Unit Resources
- Unit Lesson
- Unit VI Plan
- Unit VI Lesson
- Reference
- Learning Activities (Nongraded)