In: Math
I am working with SPSS software. The researchers conducted a study to determine the following:
What is the correlation between students’ age and how many seconds they were observed washing their hands?
What is the correlation between students’ score on the “when should you wash your hands” knowledge index and the “correct handwashing” self-report scale?
For "sex" the role is (input)
For "age" the role is (input)
For "seconds of hand washing" the role is (target)
For "hand washing index" the role is (both)
For "correct handwashing method" the role is (both)
I am looking to find if each dependent variable is approximately normally distributed, but am unsure which information should be put into Explore in SPSS to calculate for normal distribution. I know that my independent variables are "age" and "sex" and one of the dependent variables is "seconds hand washing" but I am unclear as to whether I should use the other two labeled as (both) as well?
Can someone help me understand how I should go about exploring for normal distribution?
The normality of the dependent variable can be determine by histograms, Normal Q-Q plots and box plots. These plot can be obtained in spss by following these steps,
Step 1: Click Analyze > Descriptive Statistics > Explore. the screenshot is shown below,
Step 2: Select all the dependent variables and move it to the “Dependent List” box.
Step 3: Click on Plots and unselect Stem-and-leaf, select Histogram and select Normality plots with tests then click Continue. and then OK. The screenshot is shown below,
Step 4: Now, the result is obtained. In the Descriptives, the skewness and kurtosis should be tends to zero for normality of the variable. However the small deviation is acceptable in real world scenario. These deviation should be within the accptable confidence limit which can be measured by computing the z score (by dividing the measure by its standard error) and this z value should be within -1.96 and +1.96 for allowing 2.5% deviation in either side.
Step 5: The table for Test of Normality also test the normality of data points of variables which test the null hypothesis that the data are normally distributed. If the P-value is less than 0.05 then the null hypothesis can be rejected at 5% significance level.
Step 6: The Histogram shows the visual representation of normal curve.
Step 7: The Normal Q-Q plot shows the normality of the data points such that if the data points are close to the line then we can say that the data points are normally distributed. The screenshot for approximately normally distributed Normal Q-Q plot is shown below,
Step 8: The box shows the normal distribution if they are symmetrical. The screenshot for approximately normally distributed box plot is shown below,