N346 Research and
Evidence-Based Practice
Mary Pat Ulicny
October 17, 2022
Random selection of participants from the sampling frame can be performed using a number of mechanisms,
including a random digit-dialing telephone survey, a computerized randomization tool, a spreadsheet randomization
function, a table of random numbers, or by manually “drawing from a hat” or flipping a coin
Module 7 Week of October 17, 2022
Due Today:
Midterm Peer Evaluation-must be submitted today by 11:59
PM to get full points.
Quiz 5 at end of class
Mod. 7 Content
Continue to work in groups on EBP Part #2
Module 7 Learning Objectives
Describe categorical and continuous variables
Describe, identify and interpret characteristics and
meaning of descriptive statistics
Describe logic and purpose of statistical testing and
interpret the meaning of p values as they relate to:
Statistical significance
confidence intervals
Level of Measurement
Purpose: The LOM of a variable determines the statistical tests that can be
used for data analysis.
Broad view LOM: Categorical and Continuous
Categorical Variables – variables with discrete values, e.g. gender, eye color
and marital status
Continuous Variables – a variable that can take on an infinite range of values
along a specified continuum, e.g. height, speed, temperature
Continuous variables allow researchers to use stronger,
more rigorous statistical tests than categorical variables.
UMSON Update
Jan19
Continuous
Categorical
UMSON Update
Jan19
Categorical Variables
Gender
Want enough categories Male
that people fall into one Female
or another
Not so many that people Gender
are confused, thinking Male
more than one option Female
Non-binary
Transgender
Other
Prefer not to answer
Continuous Variables
Have values that are already meaningful numbers
Age, weight, body temp, heart rate, urine output,
Numbers already have meaning to people
1. Do you commute to campus? Yes or No
2. Anxiety as measured by summed score of 10-item
Categorical Likert-response questionnaire.
3. Heart rate.
or 4. Very important, low importance, neutral,
Continuous? important, not at all important
5. Depression as score of 16 or above on CES-D
questionnaire.
6. Gender
7. Steps on a pedometer
8. Age in years
9. Age as young adult (18-29), middle age (30-64),
and elderly (65 and older)
10. Race
DESCRIPTIVE STATISTICS
Descriptive Statistics
Describe characteristics of a sample by summarizing data using
measures of central tendency and measures of variability.
You will see descriptive statistics in Tables 1 (sometimes 2)
Can be used numerically in tables or graphically
Do not allow you to show relationships between variables
or causality (Inferential statistics)
Descriptive Statistics: Frequency Distributions
Systematic arrangement of numeric values of a variable from
low to high, with a count of the number of times (&/or
percentage) for each value
Frequency data can be described in terms
of:
Shape
Central tendency
Variability
Can be presented in a table (e.g., Ns and
percentages) or graphically (e.g., frequency
polygons)
Descriptive Statistics: Frequency Distributions
Can use this on all levels of data including nominal.
Help give order to numeric data
Most often arranged from lowest to highest
Count of how many times and % usually - N(%)
Can display in table or graphs
Does not tell you if differences in counts are significant or
meaningful.
Cannot establish cause and effect.
43%
31%
26%
None Some A lot
Anxiety Level
Continuous Variable - Distribution
Shape
Central Tendency
Variability
Continuous Variable - Shape
Two considerations for describing the
shape of the distribution of one
continuous variable:
Modality - how many high points
Modality (highest count only)
Symmetry
Unimodal and Bimodal curves
Shapes of Distributions
Symmetric (no skew)
each half the same
Skewed (asymmetric)
Positive skew
(long tail points to the right)
Negative skew
(long tail points to the left)
Normal
Distribution
Graph Graph
A B
MEASURES
OF CENTRAL
TENDENCY
Measures of Central Tendency
Index (measure) of “typicalness” of a set of scores, from
the center of the distribution
Mode—the most frequently occurring score
Ex: 2, 3, 3, 3, 4, 5, 6, 7, 8, 9 Mode = 3
Median—the point in a distribution above which
and below which 50% of cases fall
Ex: 2, 3, 3, 3, 4 | 5, 6, 7, 8, 9 Median = 4.5
Mean—equals the sum of all scores divided by the
total number of scores (aka average)
Ex: 2, 3, 3, 3, 4, 5, 6, 7, 8, 9 Mean = 5.0
Comparing Measures of Central Tendency
Mode, useful overall descriptor,
especially for categorical measures
(e.g., single=0, married=1, divorced=2)
Median, useful mainly as descriptor of
typical value when distribution is
skewed (e.g., household income)
Mean, most stable and widely used
indicator of central tendency (e.g.,
average age)
Which Measure of Central Tendency to Use
1. The exam results were unusually negatively skewed. Which measure of
central tendency would be most appropriate?
2.
3. The researcher is writing a research article. Which measure of central
tendency would best describe the variable “weight”?
4.
5. Which measure of central tendency would best describe a patient’s anxiety
score on the Beck Anxiety Inventory?
6.
7. In a table describing the characteristics of the sample, income is “low - <
$50,000”, “middle - $50,001 – $100,000” and “high – >100,000” which
measure of central tendency would be most appropriate.
VARIABILI
TY
VARIABILITY
The degree to which scores in a distribution are spread out or dispersed.
Homogeneous—little variability
Heterogeneous—great variability
2 INDEXES OF VARIABILITY
1. Range: highest value minus lowest value
2. Standard Deviation
Oldest person in sample is 55, youngest
person in sample is 23 range is 32
2. Standard deviation (SD)
More complete picture of variability
average distance away from mean;
usually reported with the mean
38(1.85) or 38 + 1.85
What if the SD above was 11.85
instead?
Heterogeneity—great variability, higher SD
Homogeneity—little variability, lower SD
In a perfect world, “normal” distribution
Recap - Distribution
Shape
Modality, symmetry
Central tendency
Mean, median, mode
Variability
Range, standard deviation
Table 1. Participant characteristics
and baseline Serum Ferritin
Table 1. Patient
characteristics
and baseline measures
Confidence Intervals
Statistical inference – Estimation of
Parameters
Point estimation—A single descriptive statistic
that estimates the population value (e.g., mean age of
sample)
Interval estimation—A range of values within
which a population value probably lies
Involves computing a confidence intervals
(CI) around the point estimate
Confidence Intervals
CIs indicate the upper and lower confidence limits
and the probability that the population value is between
those limits.
For example, a 95% CI of 40–50 for a sample mean of
45 indicates there is a 95% probability that the
population mean is between 40 and 50.
Let’s Practice
Which Measure of Central Tendency Would Be
Most Helpful?
1. The exam results were unusually negatively skewed. Which measure of central
tendency would be most appropriate?
2. The researcher is writing a research article. Which measure of central tendency
would best describe the variable “gender”?
3. Which measure of central tendency would best describe a patient’s anxiety score on
the Beck Anxiety Inventory?
Categorical or Continuous?
Categorical or Continuous?
Categorical or Continuous?
UMSON Update
Jan19
Practice
What are attributes of the shape of the
graph?
a.
a. Bimodal and negatively skewed
b. Unimodal and negatively skewed
c. Unimodal and positively skewed
d. Multimodal and non-skewed
Researchers concerned about the dramatic increase in U.S.
bankruptcies over the past 30 years.
They plot the years 1980 to 2012 on the x-axis (horizontal) and number
of bankruptcies on the y-axis (vertical). What would the shape of this
graph look like?
a. Negatively skewed.
b. Positively skewed.
Practice
If the data are normally distributed, which measure of central tendency should the researcher use to
describe the sample’s age (in years)?
a. Mode
b. Median
c. Mean
d. Range
