2. Objectives
Define descriptive statistics.
Describe the frequency distribution.
Identify the purpose of frequency
distribution.
Interpret the frequency distribution.
Describe the data distributions by their
shape.
Describe central tendency.
Explain the types of central tendencies.
Explain the types of variability.
3. Objectives
Describe the concept of bivariate
descriptive statistics.
Describe the contingency tables.
Interpret the contingency tables.
Explain the correlation with examples.
Explain “Describing Risk”.
4. Descriptive statistics
Statistical procedures enable researchers
to organize, interpret, and communicate
numeric information
Descriptive statistics are used to describe
and synthesize data.
5. Frequency Distributions
A systematic arrangement of numeric
values from lowest to the highest, together
with a count (or percentage) of the number
of times each value was obtained.
Example:
Patients’ anxiety scores
(preoperative):22 27 25 19 24 25 23 29 24 20
26 16 20 26 17 22 24 18 26 28
15 24 23 22 21 24 20 25 18 27
24 23 16 25 30 29 27 21 23 24
26 18 30 21 17 25 22 24 29 28
20 25 26 24 23 19 27 28 25 26
6. Score (X) Talli22es Frequency ( f ) Percentage (%)
15 I 1 1.7
16 II 2 3.3
17 II 2 3.3
18 III 3 5.0
19 II 2 3.3
20 IIII 4 6.7
21 III 3 5.0
22 IIII 4 6.7
23 IIII 5 8.3
24 IIII IIII 9 15.0
25 IIII II 7 11.7
26 IIII I 6 10.0
27 IIII 4 6.7
8 III 3 5.0
9 III 3 5.0
30 II 2 3.3
N = 60 % = 100%
8. Frequency Distributions
From the example, we can see at a glance:
◦ What the highest and lowest scores were.
◦ What the most common score was.
◦ Where the bulk of scores clustered.
◦ How many patients were in the sample (N).
None of this was apparent before the data
were organized.
9. Frequency Distributions
Shapes of distributions:
◦ Symmetric or asymmetric (skewed)
◦ Unimodal, bimodal, or multimodal.
◦ Normal distribution.
10. Central Tendency
For variables on an interval or ratio scale, a
distribution of values is usually of less
interest than an overall summary.
Single number that represent the whole
distribution.
Term Average is normally used to designate
central tendency.
Three commonly used kinds of averages, or
measures of central tendency : mode ,
median , mean.
11. Central Tendency
Mode:
◦ The most frequently occurring score value in a
distribution.
◦ Researchers often characterize their samples by
providing modal information on nominal-level
demographics, as the following example: “The
typical (modal) subject was a married white
woman.”
12. Central Tendency
Median:
◦ The point in a distribution above which an below
which 50% of cases fall.
◦ It dose not take into account the quantitative
values of scores.
◦ It is often the preferred index of central tendency
when a distribution is skewed.
Mean:
◦ The most widely used measure of central
tendency.
◦ Unlike the median, the mean is affected by every
score.
14. Variability
Range:
The highest score minus the lowest score in a
distribution.
It ignores score variations between two extremes
Standard Deviation:
The average amount of deviation of values from
the mean.
It is calculated based on every value in a
distribution.
16. Bivariate Descriptive Statistics
Descriptive statistics describe relationships
between two variables.
The two most commonly used methods of
describing two-variable relationships are:
◦ Contingency tables .
◦ Correlation indexes.
17. Bivariate Descriptive Statistics
Contingency Tables:
◦ It is two dimensional frequency distribution in
which the frequencies of two variables are cross-
tabulated.
Example:
Contingency table for gender and smoking status relationship
Smoking Status Women Men Total
n % n % n %
Nonsmoker 10 45.4 6 27.3 16 36.4
Light Smoker 8 36.4 8 36.4 16 36.4
Heavy smoker 4 18.2 8 36.4 12 27.3
Total 22 100 22 100 44 100
18. Bivariate Descriptive Statistics
Correlation:
◦ To what extent are two variables related to each
other?
◦ The question can be answered graphically
(scatter plot), or by calculating the correlation
coefficient.
◦ It describes the intensity and direction of a
relationship.
◦ The most commonly used correlation index is
Pearson’s r (computed with interval or ratio
measures), and Spearman rank-order correlation
(for ordinal measures).
20. Describing Risk
Interpreting findings and facilitating decision
making of evidence-based practice by using
descriptive statistical indexes.
Absolute Risk:
◦ The proportion of people who experienced an
undesirable outcome in each group.
Absolute Risk Reduction:
Comparison of the two absolute risk
Odds Ratio:
◦ The proportion of subjects with the adverse
outcome relative to those without it.
21. Exposure to smoking
cessation intervention
Outcome
Total
Continued Smoking Stopped Smoking
Yes, exposed
(Experimental group) 50 50
100
No, not exposed
(Control group)
80 20 100
Absolute risk, Exposed Group = 50/100 = 0.5
◦ 50% of the exposed group continued smoking even they received
the intervention.
Absolute risk, non-exposed group = 80/100 = 0.8
◦ 80% of the not exposed group continued smoking.
Absolute risk reduction = 0.8-0.5 = 0.3
◦ 30% of the control group subjects would have stopped smoking if
they have received the intervention.
Odds Ratio =
50/50.
80/20.
= 0.25 = 1:4
◦ The estimated odds of continued smoking are 4 times higher
among smokers who don’t get interventions as among those who
do.
22. Summary
Descriptive statistics enables researchers to
synthesize and summarize quantitative data.
In a frequency distribution, numeric values are
ordered from lowest to highest, together with a
count of the number of times each value was
obtained.
Measure of central tendency represent the
average of typical value of variable.
Measure of variability, how spread out the data
are.
Bivariate descriptive statistics describe
relationships between two variables.
Describing risk facilitates decision making of
evidence-based practice by Interpreting the
findings.
23. Conclusion
The data collected in a study do not by
themselves answer research questions or
test research hypothesis.
As a researcher, you will use these
statistical procedures to organize and
interpret the numerical information.
24. References
Polit D. and Beck Ch.(2006).Essentials Of
Nursing Research. Methods, Appraisal, and
Utilization. Lippincott William & Wilkins.
Polit D. and Beck Ch.(2008).Nursing
Research. Generating and Assessing
Evidence for Nursing Practice.