Professional Documents
Culture Documents
Assumption of normality
Transformations
Practice problems
SW388R7
Assumption of Normality
Data Analysis &
Computers II
Slide 2
Evaluating normality
Data Analysis &
Computers II
Slide 3
Transformations
Data Analysis &
Computers II
Slide 4
Slide 5
Problem 1
Data Analysis &
Computers II
Slide 6
1. True
2. True with caution
3. False
4. Incorrect application of a statistic
SW388R7
Slide 7
Slide 8
Slide 9
Slide 10
Slide 11
Slide 12
Slide 13
The histogram
Data Analysis &
Computers II
Slide 14
20
Frequency
10
Std. Dev = 15.35
Mean = 10.7
0 N = 93.00
0.0 20.0 40.0 60.0 80.0 100.0
10.0 30.0 50.0 70.0 90.0
Slide 15
-1
normality plot.
Slide 16
Tests of Normality
a
Kolmogorov-Smirnov Shapiro-Wilk
Statistic df Sig. Statistic df Sig.
TOTAL TIME SPENT
.246 93 .000 .606 93 .000
ON THE INTERNET
a. Lilliefors Significance Correction
Problem 1 asks about the results of the test of normality. Since the sample
size is larger than 50, we use the Kolmogorov-Smirnov test. If the sample
size were 50 or less, we would use the Shapiro-Wilk statistic instead.
The null hypothesis for the test of normality states that the actual
distribution of the variable is equal to the expected distribution, i.e., the
variable is normally distributed. Since the probability associated with the
test of normality is < 0.001 is less than or equal to the level of significance
(0.01), we reject the null hypothesis and conclude that total hours spent on
the Internet is not normally distributed. (Note: we report the probability as
<0.001 instead of .000 to be clear that the probability is not really zero.)
Slide 17
Slide 18
Second, click on
the Run button to
activate the script.
SW388R7
Slide 19
Slide 20
Tests of Normality
a
Kolmogorov-Smirnov Shapiro-Wilk
Statistic df Sig. Statistic df Sig.
TOTAL TIME SPENT
.246 93 .000 .606 93 .000
ON THE INTERNET
a. Lilliefors Significance Correction
Problem 2
Data Analysis &
Computers II
Slide 21
1. True
2. True with caution
3. False
4. Incorrect application of a statistic
SW388R7
Slide 22
Descriptives
The skewness and kurtosis for the variable both exceed the rule of
thumb criteria of 1.0. The variable is not normally distributed.
Problem 3
Data Analysis &
Computers II
Slide 23
1. True
2. True with caution
3. False
4. Incorrect application of a statistic
SW388R7
Slide 24
Tests of Normality
a
Kolmogorov-Smirnov Shapiro-Wilk
Statistic df Sig. Statistic df Sig.
Logarithm of NETIME
.047 93 .200* .994 93 .951
[LG10(NETIME)]
Square Root of NETIME
.118 93 .003 .868 93 .000
[SQRT(NETIME)]
Inverse of NETIME
.288 93 .000 .495 93 .000
[1/(NETIME)]
*. This is a lower bound of the true significance.
a. Lilliefors Significance Correction
Problem 3 specifically asks about the results of the test of
normality for the logarithmic transformation. Since our sample
size is larger than 50, we use the Kolmogorov-Smirnov test.
Slide 25
Slide 26
Yes
Yes
No
Are any of the metric True
variables ordinal level?
Yes
Slide 27
Yes
Statistical evidence
No Statistical evidence No
supports normality?
for transformation False
supports normality?
Yes
No
Either variable
ordinal level? True
Yes