Data Analysis Tests

Data Analysis
Descriptive Statistics Inferential Statistics
Descriptive statistics are brief descriptive With inferential statistics, you take data
coefficients that summarize a given data from samples and make generalizations
set, which can be either a representation about a population. This means taking a
of the entire population or a sample of a statistic from your sample data (for
population. Descriptive statistics are example the sample mean) and using it
broken down into measures of central to say something about a population
tendency and measures of variability parameter (i.e. the population mean).
(spread). Hypothesis tests.
Data presented by frequency It provide measures of how well data
histograms, mean, median, mode, range, support your hypothesis and if your data
variance & standard deviation. are generalizable beyond what was
tested (significance tests)
 Data Analysis Tests

• There are two types of statistical tests or methodologies that are used
to analyse data:
• Parametric Tests
• Non-Parametric Tests
 Data Analysis Tests
Parametric tests Non-parametric test
The parametric test make certain assumptions about Non-parametric test are also known is
a data set; namely – that the data are drawn from a distribution-free test is considered less powerful
population with a specific or normal distribution. It is as it uses less information in its calculation and
further assumed in parametric test that the variables makes fewer assumption about the data set.
in the population are measured based on an interval
scale.
In summary:
In summary: Non-Parametric tests are used:
Parametric tests are used:  When the data is not normally distribution
 When the data has a normal distribution  When the study is better represented by the
 When the study is better represented by the median
mean  When the measurement scale is nominal or
 When the measurement scale is interval or ratio. ordinal.
 Interval /ratio when data is not normally
distributed.
 Criteria For Choosing Tests
• If the mean more accurately
represents the center of the
distribution of data, and your sample
size is large enough, use a parametric
test.
• If the median more accurately
represents the center of the
distribution of data, use a
nonparametric test even if you have a
large sample size.
 Normality Tests
1. Shapiro-Wilk Test
2. Kolmogorov-Smirnov-Test

• Both tests are used to test the null hypothesis that a set of data comes from a
Normal distribution or not.
• The Shapiro-Wilk test is more appropriate method for small sample sizes (<50
samples) although it can also be handling on larger sample size while
Kolmogorov–Smirnov test is used for n ≥50.
 How to apply Normality Test Using SPSS:
Step:2 Click Analyze > Descriptive Statistics > Explore... on the top menu, as shown below:

Step:1 Data Entry

 SPSS

Step4 :Transfer variable that needs to be tested for normality

Step 3: You will be presented with the Explore into the Dependent List: box by either drag-and-dropping or
dialogue box, as shown below: using the SPSS Arrow Right Button button. In this example,
we transfer the Time variable into the Dependent List: box.
You will then be presented with the following screen:
 SPSS
Step 5: You need to add your independent variable to
the Factor List: box by either drag-and-dropping or
using the SPSS Arrow Right Button button. In this
Step 6: Click on the SPSS Statistics Button button.
example, we transfer the Course variable into the You will be presented with the Explore: Statistics
Factor List: box. You will be presented with the dialogue box, as shown below:
following screen:

Leave the above options unchanged and

Click on the SPSS Statistics click on the SPSS Continue Button .
 SPSS
Step 7: Click on the SPSS Plots Button button.
Change the options so that you are presented
with the following screen:

• Step 8:Click on the Continue

button.
• Step 9: Click on the OK button.
 Graphical presentation
Normal /Skewed Presentation
 Parametric tests Non-parametric test
Independent (unpaired) Two-sample t-test Kruskal-Wallis test
Paired t-test Spearman’s rank correlation
Analysis of variance (ANOVA) Wilcoxon signedrank test
Pearson coefficient of correlation Wilcoxon ranksum test
Parametric test:
1. t- test A t-test is a type of inferential statistic used to for the purpose
of hypothesis testing in statistics.

There are three main types of t-test:

i .One sample t-test A One sample t-test tests the mean of a single group
against a known mean.
ii. Dependent/Paired sample t-test A Paired sample t-test compares means from the same
group at different times (pre and post values).
iii. Independent/unpaired Samples t- An Independent Samples t-test compares the means for
test two groups.
 i. one sample t- test
Comparing One Group
T-Test Type: Description Example:
i .One sample A One sample t-test tests the Researcher interested in whether resting pulse rate of long
mean of a single group distance runners differs from others athletes in general
t-test against a known mean. population (60 beats/minute).

Randomly sample 8 long distance runners resting pulse rate:

45,42,64,54,58,49,48,56
mean =416/8=52
resting pulse rate of long distance runners 52 beats/minute

Assumptions of One Sample Test

The data are continuous.
The data follow the Normal distribution.
The sample is a simple random sample from the population.

If assumption not fulfilled then Sign Test (Non-parametric test)

 ii. Paired t- test
Comparing Two Means (Same Population)

T-test type: Description Example

ii. Paired sample t- A Paired sample t-test compares means Hamstring stretching effect to improve hip
from the same group at different times SLR.
test (pre and post values). take values on the same person using
goniometer before stretch (pre value) and
after training complete (post value),

Assumptions of Paired Sample T Test

The data are continuous.
The data follow Normal distribution.
The sample of pairs is a simple random sample from its population.

If assumption not fulfilled then Willcoxon T test (Non-parametric test)

iii. Independent t- test (unpaired)
Comparing Two Means (Different Population)
T-test type: Description Example
iii. Independent An Independent Samples t-test Effect of Hamstring stretching and
compares the means for two groups. muscle energy techniques to improve
Samples t-test hip Straight Leg Raise.
Take values of 2 groups:
Group 1: Hamstring stretching
Group 2: Muscle energy techniques
Compare mean of Group 1 and 2.

Assumptions of Independent Sample T test

• Data are continuous
• The data follow the Normal distribution
• The two samples are independent
• Both samples are simple random samples from their respective populations.

If assumption not fulfilled then Mann-Whitney Test (Non-parametric test)

 Summary
Analysis Type Example Parametric Test Equivalent Non-
Parametric Test
Compare one group Compare 1st semester students One sample t-test Sign Test
(compare population mean mean result (one group) With
with reference population previous 1st semester students mean
mean) result
(One sample)
Compare mean for To compare plasma glucose level of Paired sample t- Willcoxen T test
quantitative individual before and after meal test
measurements taken from
same individual/same
group
(2 sample-Same
population)
Compare mean between 2 To compare girls' heights (group 1) Independent Mann-Whitney Test
independent groups with boys' heights (group 2) Samples t-test
(2 sample-Different
population)
 Non- Parametric tests
Analysis Type Equivalent Non-Parametric Test
Compare one group Sign Test
(compare population with The 1 sample sign test is a nonparametric hypothesis test used to determine
reference population) whether statistically significant difference exists between the median of a
non-normally distributed continuous data set and a standard. This test
basically concerns the median of a continuous population.

Compare median Willcoxen T test

(2 sample -Same population) The Wilcoxon test, which can refer to either the rank sum test or the signed
rank test version, is a nonparametric statistical test that compares two paired
groups.
Wilcoxon signed rank test comparing medians for paired samples.
Compare median Mann-Whitney Test
(2 sample-Different population) The Mann-Whitney U test is a non-parametric test that can be used in place
of an unpaired t-test. It is used to test the null hypothesis that two samples
come from the different population (median).
How to write Data Analysis part in Synopsis;
 SPSS Analysis- Independent t-test
• Example:
• Comparative effects of calorie-controlled diet and exercise training programme on
weight loss and lowering cholesterol levels in inactive overweight males.
• Population: random sample of inactive overweight males
• This sample was then randomly split into two groups:
• Group 1 underwent a calorie-controlled diet (n=20)
• Group 2 undertook the exercise-training programme (n=20)

• In order to determine which treatment programme was more effective, the mean
cholesterol concentrations were compared between the two groups at the end of
the treatment programmes.
 SPSS Statistics
• In SPSS Statistics, we separated the groups for analysis by creating a grouping
variable called Treatment (i.e., the independent variable), and gave the "diet
group" a value of "1" and the "exercise group" a value of "2" (i.e., the two groups
of the independent variable). Cholesterol concentrations were entered under the
variable name Cholesterol (i.e., the dependent variable). In our enhanced
independent t-test guide, we show you how to correctly enter data in SPSS
Statistics to run an independent t-test
• SPSS Sheet
SPSS- Statistical Package for the Social Sciences
Data view sheet
SPSS- Variable view sheet
Example: Variable view
Example: Data view
SPSS- Variable view sheet Treatment
Diet group
Diet group
Exercise group
Exercise group
Exercise group

1.00 Diet group

2.00 Exercise group
 How to apply t-test on SPSS:
• Step1: Click Analyze > Compare Means > Independent-Samples T Test.
on the top menu, as shown below:
 SPSS- Independent t-test
Step 3: Transfer the dependent variable, Cholesterol,
Step 2: You will be presented with the Independent- into the Test Variable(s): box, and transfer the
Samples T Test dialogue box, as shown below: independent variable, Treatment, into the Grouping
Variable: box, by highlighting the relevant variables
and pressing the SPSS Right Arrow Button buttons. You
will end up with the following screen:
 SPSS- Independent t-test
Step 4: You then need to define the groups Step 5: Enter "1" into the Group 1: box and
(treatments). Click on the Define Options Button enter "2" into the Group 2: box. Remember
button. You will be presented with the Define Groups that we labelled the Diet Treatment group as 1
dialogue box, as shown below: and the Exercise Treatment group as 2.

Note: If you have more than 2 treatment groups in your study (e.g., 3 groups: diet, exercise and drug treatment groups), but
only wanted to compared two (e.g., the diet and drug treatment groups), you could type in 1 to Group 1: box and 3 to Group
2: box (i.e., if you wished to compare the diet with drug treatment).
 SPSS- Independent t-test

Step 6: If you need to change the confidence level limits Step 7: Click the Continue Button button. You will be
or change how to exclude cases, click the Options Button. returned to the Independent-Samples T Test dialogue
You will be presented with the following: box.
Step 8: Click the Continue Button button
 SPSS- Independent t-test

Group Statistics Table

This table provides useful descriptive statistics
for the two groups that you compared,
including the mean and standard deviation.

Independent Samples Test Table

This table provides the actual results from
the independent t-test.

You can see that the group means are statistically

significantly different because the value in the
"Sig. (2-tailed)" row is less than 0.05. Looking at
the Group Statistics table, we can see that those
people who undertook the exercise trial had
lower cholesterol levels at the end of the
programme than those who underwent a calorie-
controlled diet.
• Conclusion:
• This study found that overweight, physically inactive male
participants had statistically significantly lower cholesterol
concentrations (5.80 ± 0.38 mmol/L) at the end of an exercise-
training programme compared to after a calorie-controlled diet
(6.15 ± 0.52 mmol/L), t(38)=2.428, p=0.020.
 Parametric Test
Analysis for more than 2 Groups

Types of ANOVA
i. One way Repeated measurement ANOVA.
ii. One way ANOVA
 2. Parametric Test- Anova
i. One way Repeated measurement ANOVA
Type of Anova Description Example
i.One way Repeated When we take measurement more We need to see short term and long
than 2 time form same subjects we term effects of hamstring stretch in
measurement ANOVA apply Repeated measurement improving SLR.
(Extension of Paired Sample t-Test) ANOVA. • Value before treatment-week 1
Comparing More than Two Means • Short term effects –week 3
(Same Population) • Long term effects – week 6
To compare mean of 3 means in same
group we apply Repeated
measurement ANOVA

Assumptions:
The data are continuous.
The data, i.e., the differences for the matched-pairs, follow a Normal distribution.
The sample of pairs is a simple random sample from its population.

If assumption not fulfilled then Friedman ANOVA (Non-parametric test)

 2. Parametric Test- Anova
ii. ANOVA.
Type of Anova Description Example
ii. One way ANOVA We use ANOVA when we want to Comparison of effectiveness of different
(Extension of independent Sample t- compare the averages of techniques in improving SI joint
Test) quantitative data in more than 2 dysfunction;
groups. Group 1: Maitland Mobilization
Group 2: Mulligan Mobilization
Comparing More than Two Means Group 3: Mulligan + Clamshell exercise
(Different Population)

Assumption of ANOVA:
• Data should be continuous
• Data should be normally distributed
• Data should be taken at random
• All groups should be independent

If assumption not fulfilled then Kruskal-Wallis ANOVA (Non-parametric test)

 Summary
Analysis Type Description Example Parametric Test Equivalent Non-
Parametric Test
Comparing More than When we take One way Repeated Friedman ANOVA
Two Means (3 or more) measurement more than measurement ANOVA.
(Same Population) 2 time form same
subjects
Comparing More than We use ANOVA when we One way ANOVA Kruskal-Wallis ANOVA
Two Means (3 or more) want to compare the
(Different Population) averages of quantitative
data in more than 2
groups.
 Non-Parametric Tests:
Analysis Type Equivalent Non-Parametric Test
Comparing More than Two Friedman ANOVA
Means (3 or more) The Friedman test is the non-parametric alternative to the one-way ANOVA
(Same Population) with repeated measures.
• It is used to test for differences between groups when the dependent
variable being measured is ordinal.
• It can also be used for continuous data that has violated the assumptions
necessary to run the one-way ANOVA with repeated measures (e.g., data
that has marked deviations from normality).
Comparing More than Two Kruskal-Wallis ANOVA
Means (3 or more) The Kruskal-Wallis H test (sometimes also called the "one-way ANOVA on
(Different Population) ranks") is a rank-based nonparametric test that can be used to determine if
there are statistically significant differences between two or more groups of an
independent variable on a continuous or ordinal dependent variable. It is
considered the nonparametric alternative to the one-way ANOVA, and an
extension of the Mann-Whitney U test to allow the comparison of more than
two independent groups.
Summary
How to Apply ANOVA in SPSS;
• Example
• A manager wants to raise the productivity at his company by increasing the speed
at which his employees can use a particular spreadsheet program. As he does not
have the skills in-house, he employs an external agency which provides training in
this spreadsheet program. They offer 3 courses: a beginner, intermediate and
advanced course. He is unsure which course is needed for the type of work they
do at his company, so he sends 10 employees on the beginner course, 10 on the
intermediate and 10 on the advanced course. When they all return from the
training, he gives them a problem to solve using the spreadsheet program, and
times how long it takes them to complete the problem. He then compares the
three courses (beginner, intermediate, advanced) to see if there are any
differences in the average time it took to complete the problem.
• Setup in SPSS Statistics
• In SPSS Statistics, we separated the groups for analysis by creating a
grouping variable called Course (i.e., the independent variable), and
• the beginners course a value of "1",
• the intermediate course a value of "2" and
• the advanced course a value of "3".
• Time to complete the set problem was entered under the variable name
Time (i.e., the dependent variable).
• In our enhanced one-way ANOVA guide, we show you how to correctly
enter data in SPSS Statistics to run a one-way ANOVA
 SPSS- 1 way Anova
Step 1: Click Analyze > Compare Means > One-Way ANOVA... on the top menu, as
shown below.
 SPSS- 1 way Anova

Step 2: You will be presented with the Step 3: Transfer the dependent variable, Time, into
One-Way ANOVA dialogue box: the Dependent List: box and the independent
variable, Course, into the Factor: box using the
appropriate Right arrow buttons (or drag-and-drop
the variables into the boxes), as shown below:
SPSS- 1 way Anova
Step 5: Click on the Options button. Tick the
Step 4: Click on the Post hoc button. Tick Descriptive checkbox in the –Statistics– area, as
the Tukey checkbox as shown below: shown below:
• SPSS Statistics
• Descriptive Table
• The descriptive table (see below) provides some very useful descriptive statistics,
including the mean, standard deviation and 95% confidence intervals for the
dependent variable (Time) for each separate group (Beginners, Intermediate and
Advanced), as well as when all groups are combined (Total). These figures are useful
when you need to describe your data
• SPSS Statistics
• ANOVA Table
• This is the table that shows the output of the ANOVA analysis and whether there
is a statistically significant difference between our group means. We can see that
the significance value is 0.021 (i.e., p = .021), which is below 0.05. and, therefore,
there is a statistically significant difference in the mean length of time to
complete the spreadsheet problem between the different courses taken.We can
find this out in the Multiple Comparisons table which contains the results of the
Tukey post hoc test.
• SPSS Statistics
• Multiple Comparisons Table
• From the results so far, we know that there are statistically significant differences
between the groups as a whole.
Conclusion:
• There was a statistically significant difference between groups as
determined by one-way ANOVA (F(2,27) = 4.467, p = .021). A Tukey
post hoc test revealed that the time to complete the problem was
statistically significantly lower after taking the intermediate (23.6 ±
3.3 min, p = .046) and advanced (23.4 ± 3.2 min, p = .034) course
compared to the beginners course (27.2 ± 3.0 min). There was no
statistically significant difference between the intermediate and
advanced groups (p = .989)