Week 8 - Assignment: Signature Assignment: Create a Presentation for Statistical Analysis in Research

SAGE Research Methods Video

ANOVA

Video Title: ANOVA

Originally Published: 2016

Publication Date: Sep. 30, 2016

Publishing Company: SAGE Publications, Inc.

City: Thousand Oaks, United States

ISBN: 9781506359144

DOI: https://dx.doi.org/10.4135/9781506359144

(c) SAGE Publications Inc., 2017

NARRATOR: Welcome to Practical Statistics for Nursing using SPSS. This video shows how to process the ANOVA test. You can watch the entire video, or use the time slider to navigate directly to any time point. The ANOVA test is similar to the t-test, but where is the t-test

NARRATOR [continued]: compares two groups of continuous variables to determine if one group statistically significantly outperformed the other. The ANOVA test can process three or more groups. In this example, we have three groups. The members of each group will be given an anti- hypertensive drug. The participants in Group 1 get Drug A, the participants

NARRATOR [continued]: in Group 2 get Drug B, and the participants in Group 3 get Drug C. After a month, we'll record a systolic blood pressure of each participant. Group 1 had a mean of 120.37. Group 2 had a mean of 122.37. And Group 3 had a mean of 122.70.

NARRATOR [continued]: The ANOVA test will compare the groups to each other and calculate a p- value for each pair of groups. If the p-value is less than or equal to 0.05, we would conclude that one drug statistically significantly outperformed the other. This example uses the data set, CH 0 6, Example 01, ANOVA.sav.

NARRATOR [continued]: This data set contains two variables. The first variable is group, which is a categorical variable containing three values. Group 1 gets Drug A, Group 2 gets Drug, and Group 3 gets Drug C. The second variable is systolic BP.

NARRATOR [continued]: This is a continuous variable that contains the systolic blood pressure reading of each participant. The ANOVA test will compute the mean for each group and then calculate the p-value for each pair of groups, which will tell us which groups statistically significantly outperformed which.

NARRATOR [continued]: The ANOVA test has three pretest criteria-- normality, n quota, and homogeneity of variance. We'll check for normality now. The other two will be processed when we run the ANOVA test. To check for normality, we need to order a histogram with a normal curve for systolic BP for each group.

NARRATOR [continued]: We'll begin with Group 1-- the group that got Drug A. Click "select cases." Click "if condition is satisfied," and click "if." In the dialog box, enter "group = 1." Click "continue."

NARRATOR [continued]: Click "OK." Now that only the records for Group 1 are active, we can order a histogram with normal curve. Click "Analyze, Descriptive Statistics, Frequencies." Move systolic BP to variables.

NARRATOR [continued]: Click "charts" and select histogram with normal curve. Click "continue," click "OK," and it'll process. The histogram for Group 1, Drug A, meets the normality criteria. Now we'll repeat this process for Group 2,

NARRATOR [continued]: Drug B. Click "select cases." Click "if." In the dialog box, enter "group = 2." Click "continue," and click "OK." Now that only the records for Group 2 are active,

NARRATOR [continued]: we can order a histogram with a normal curve. Click "Analyze, Descriptive Statistics, Frequencies." Notice that systolic BP is still in variables. Since the charts option hasn't been changed since our prior run, we don't need

NARRATOR [continued]: to revisit the charts menu. Click "OK," and it'll process. The histogram for Group 2, Drug B, meets their normality criteria. We'll repeat this one more time to process Group 3, Drug C. Click "select cases."

NARRATOR [continued]: Click "if." In the dialog box, enter "group = 3." Click "continue," and click

SAGE (c) SAGE Publications Inc., 2017

SAGE Research Methods Video

Page 2 of 3 ANOVA

"OK." Now that only the records for Group 3 are active, we can order the histogram with normal curve. Click "Analyze, Descriptive Statistics, Frequencies."

NARRATOR [continued]: Click "OK," and it'll process. The histogram for Group 3, Drug C, meets the normality criteria. Before we run the ANOVA test, we need to select all of the records. The simplest way to do this is to click on the filter

NARRATOR [continued]: underscore dollar sign variable, And press the "Delete" key. To run the ANOVA test, click on "Analyze, Compare Means, One way ANOVA." Move systolic BP to dependent list.

NARRATOR [continued]: And move "group" to "factor." Click "options," and click "descriptive and homogeny of variance test." Click "continue." Now click on "post-hoc." The post hoc menu allows us to select how the pairs of groups

NARRATOR [continued]: will be compared to each other. Since each group has the same number of participants, we'll opt for the two-key test. If the groups had had different ends, then we'd select the side deck test instead. Click "continue," click "OK," and it will process.

NARRATOR [continued]: We see that each group has an end of at least 30, hence the end quote is satisfied. We also see that the homogeneity of variance test returned a p-value of 0.656. Since this is greater than 0.05, this indicates that there is no statistically significant

NARRATOR [continued]: difference in the variances between the groups, hence the homogeny of variance test is satisfied. Back to the descriptive table, notice that this table contains the means for each group. These figures will be useful when it comes to documenting the results. Finally, we see the results of the ANOVA test.

NARRATOR [continued]: The p-value is 0.003. Since this is less than or equal to 0.5, this tells us that at least one group statistically significantly outperformed another. To determine which group outperformed which, we'll look at the pairwise comparisons on the multiple comparisons table.

NARRATOR [continued]: The first pair we'll assess is Drug A, with a mean of 120.37, and Drug B, with a mean of 122.37. The p-value of 0.019, is less than or equal to 0.05, indicating that Drug A statistically significantly

NARRATOR [continued]: outperformed Drug B. The next comparison is Drug A with a mean of 120.37, and Drug C, with a mean of 122.70. The p-value is 0.005. Since this is less than or equal to 0.05,

NARRATOR [continued]: this indicates that Drug A statistically significantly outperformed Drug C. The last pair of comparisons involves Drug B, with a mean of 122.37, and Drug C with a mean of 122.70. This comparison produced the p-value of 0.891.

NARRATOR [continued]: Since this is greater than 0.05, this tells us that there is no statistically significant difference between Drug B and Drug C. This concludes this video.

SAGE (c) SAGE Publications Inc., 2017

SAGE Research Methods Video

Page 3 of 3 ANOVA