Test for checking normal distribution in SPSS

To test for checking normal distribution present in a data, you need to follow below steps:

1. Open SPSS 17.0

2. Click on file -> open -> Data

3. Open the data file “1991 U.S. General Social Survey “ by selecting through the path C:\Program Files\SPSSInc\Statistics17\Samples\English

4. Remember, in Variable View Tab, in Measure column, Scale indicates that the variable is parametric, where as Ordinal or Nominal means the data is nonparametric.

5. After opening the data file, click on Analyze -> Descriptive statistic -> Explore

6. Select Number of brother -> click on Plots -> select normality plots with test -> Continue – > OK

7. Since the variable selected contains parametric data, therefore in the output window we will check “Shapiro-Wilk” in Test of normality table. If the Sig. Value is < 0.05 then the data is not normal. Hence in this case, our variable is not normal.

Now let us check the normal distribution in non-parametric data variable (Childs)

Repeat the steps 5 & 6, but in step 6, select variable child / number of children (Ordinal in Measure column) instead of number of brother.

This time we will check the output result through “Kolmogorov-Smirnov” in Test of normality table because our data is non – parametric. If the Sig. Value is < 0.05 then the data is not normal. Hence in this case as well, our variable is not normal.

For Further details please read below link:

http://books.google.com.pk/books?id=B3Vx5XwJv64C&pg=PA137&dq=testing+for+checking+normal+distribution+in+spss&hl=en&sa=X&ei=nYt3VL6SEcLhywO524LICg&ved=0CB8Q6AEwAQ