The systematic process of organizing,
summarizing, and interpreting collected data to
answer research questions or test hypotheses.
data analysis
In nursing research, data analysis helps:
● Transform raw data into ___ ___
● Identify ___, ___, and ___
● Provide ___ ___ to improve patient care and nursing practice
meaningful information
patterns, relationships, and trends
scientific evidence
● Expressed in
numbers
● Can be counted or
measured
● Analyzed using
statistical
procedures
● Objective and
structured in nature
quantitative data
● Narrative or textual
in form
● Subjective and
context-dependent
● Explores meanings
and lived
experiences
● Analyzed through
coding and thematic
interpretation
qualitative data
Collected
directly by the
researcher for
a specific
research
purpose.
primary data
Originally
collected by
another
researcher or
organization
and reused for
a new study.
secondary data
● Survey responses
collected by the
researcher
● Interview transcripts
● Direct patient
assessments
primary data
● Hospital records
● National health databases
● Previously published research datasets
secondary data
Can take any value
within a given range
(e.g., weight,
temperature, blood
glucose level).
continuous
Consist of whole
numbers and cannot be
subdivided (e.g., number
of admissions, number
of falls).
discreet
● Unprocessed information collected in the study.
● Data that has not been analyzed.
raw data
3 steps after raw data collection
data cleaning
data organization
data analysis
Systematic preparation of collected data by checking for missing values, incorrect entries, outliers, and inconsistencies before performing
statistical or qualitative analysis
data cleaning and preparation
purpose of data cleaning:
● Improve ___ and ___ of results
● Prevent misleading ___
● Ensure appropriate ___ ___
accuracy and reliability
conclusions
statistical analysis
purpose of data cleaning:
● Maintain research ___ and ethical ____
● Poorly cleaned data can compromise ___ ___ and evidence-based nursing decisions.
integrity, standards
patient safety
Entering data into the spreadsheet
collection of raw data
true or false - one must assign each respondent a unique identification number
true
common data problem:
Data that is not recorded or left blank in a dataset.
missing values
common data problem:
Values that are extremely high or low compared to the rest of the data.
outliers
common data problem:
Data that does not make sense or contradicts other information (e.g., age = 150 years old).
inconsistent or illogical data
common data problem:
The same data entry appearing more than once in a dataset.
duplicate records
common data problem:
Mistakes made when inputting data (e.g., typing 500 instead of 50).
data entry errors
9 steps for data cleaning
Step 1: Review the Dataset
Step 2: Check for Missing Data
Step 3: Identify Data Entry Errors
Step 4: Check Data Consistency
Step 5: Identify Outliers
Step 6: Check Coding Accuracy
Step 7: Remove Duplicates
Step 8: De-identify Data (Ethical Step)
Step 9: Final Verification
handling missing data:
Examining where and why data is missing to determine if it is random or systematic.
identify patterns of missingness
