Nursing Research 6
glovesme
chapter_12.pptxChapter 12
Data Analysis
Analyses as a Subject
Data must be compiled, analyzed and interpreted into a meaningful context
Quantitative vs. Qualitative
Quantitative analyses is the numerical representation and manipulation of observations using statistical techniques for the express purpose of describing and explaining the outcomes of research as they pertain to the hypothesis. (Numbers)
Qualitative analyses uses logical deductions to decipher gathered data dealing with the human element and does not rely on numerical values or mathematical models to explain the results. (Words)
Quantitative Analyses
Referred to as Statistical Analyses
Uses Mathematical Equations to Interpret Data
The Mathematical Equations are Dependent Upon:
Measurement Scale
Independent Variable
Dependent Variable
Measurement Scales
Nominal – simplest, used for id or categorizing purposes only
Ex: gender, race, pt id numbers
White =1, Hispanics =2…ect.
Ordinal – more precise, includes order
Ex: transplant recipient on waiting list
Interval – includes order and size. Lack s defined size.
Degrees Fahrenheit. Each degree has equal distance
Ratio – most precise, shows order and size
Weight: 1 pound weighs less than 2 pounds
Quantitative Analyses
Statistics – objective mathematical used to interpret data.
Types of statistics
Descriptive techniques
Correlational techniques
Descriptive Statistics
What are they?
Tools that we use to:
Describe
Summarize
Reduce
Manage Data
Descriptive stats allows the reader to grasp an understanding of the variables.
1
Definitions
Data:
numerical result
Variable:
trait or characteristic that can be manipulated
Population
all subjects in a defined group
Sample
subgroup of a population
Data by graphs
Normally distributed
Data Types
Discrete
measures with limited values
Continuous
measures with any value
Ungrouped Data
non arranged measures
Grouped Data
arranged measures
Descriptive VS. Inferential
Both rely solely on the study of variables
Descriptive statistics describe a chosen group
Descriptive statistics are not generalizability
Inferential Statistics can be generalized to a larger group
Measures of Central Tendency
Mean – Average
Median - Exact Middle
Mode - Most Frequent
Variability
Describes how the data vary between each score and also from the mean
Two types EBP may report:
The range
The standard deviation
Range: subtract the lowest score from the highest score. Ex: SBP 130 one time, next time 122. 130-122=8. the range is 8
Shows that the upper and lower scores varried evenly, 4 each way
Variability
Standard deviation: is the square root of variance.
It’s the mean of the mean
Analysis of Ungrouped Data
Rank Order
Frequency Distribution
Measures of Central Tendency
Analysis of Grouped Data
Grouping causes loss of information
More manageable
Frequency Distribution
Mean
Median
Quartile Deviation
Standard Deviation
Inferential Statistics
• Statistics test differences between groups
• Types of Statistics
Chi-square: nominal data compared
Independent t tests
Dependent t tests
One & Two Way ANOVA
Variable Types
Independent
Cause
Manipulated
Measured
Predicted to
Predictor
X
Dependent
Effect
The consequence
Outcome
Predicted from
Criterion
Y
Determining the Statistic
Based upon Research Design
Based Upon Measurement Scale of the Independent Variable
Based Upon Measurement Scale of the Dependent Variable
Statistics by Variable
Independent Dependent Statistical Variable Test
1 nominal 1 nominal Chi-square
1 nominal (2 groups) 1 continuous t test
1 nominal (>2 groups) 1 continuous One-way ANOVA
2 nominal 1 continuous Two-way ANOVA
Statistical Test Examples
Chi-Square- gender by disease
Independent t test—differences between men and women
Dependent t test—pre-post test measures
One-way ANOVA—ethnicity by blood pressure
Two-way ANOVA—treatment (experimental and control) by occasion (pre- and post-)
Repeated Measures ANOVA
Typical use: Do two or more groups change differently over trials (over time)?
Example: Two groups (treatment and control) are measured every 2 weeks for 12 weeks.
Analysis is a between (group)–by–within (trials) ANOVA with repeated measures on trials (trials are time, every 2 weeks).
Qualitative Analyses
Using words to support or develop theory
Inductive reasoning required
Has a theory, narrows down to a hypothesis, centers no the results
Case Study
Types of case studies
Descriptive: Develops a detailed descriptive image of the question
Interpretive: Classification and concept of an idea
Evaluative: Determines merits of best practices
Observational Study
Observed behaviors of an individual or group
Less obtrusive studies reveal a better view of the behavior
Narrative content used to explain the behavior
Attempts to characterize a hypothesis based upon inductive reasoning
Differences between Quantitative and Qualitative Analyses
Quantitative Analyses
Deductive reasoning
Focuses on numerical counts and likelihood
Statistical in nature
Empirical Findings
Large Samples
Random Assignment to treatment groups
Representative of the population
Generalizable results
Qualitative Analyses
Inductive reasoning
Focuses on the nature of the observation
Field work and observational in nature
Small Sample Sizes, many times individualized
Non Random sample
Representative only to that which is being observed in a time and place
Summary Aspects
Quantitative analyses interprets results from numerical data.
Quantitative analyses requires knowledge of measurement scales
Statistical in nature and driven by the number and types of variables as well as the apriori research design
Qualitative analyses interprets results with the use of written and verbal descriptors
Used for the following research activities:
Developmental research
The case study
Job analysis
Observational research
Unobtrusive research techniques
Summary Point
Quantitative analysis uses numerical values to explain the outcome of a research project.
Qualitative analysis uses words or phrases to explain the outcomes of a research project.
Nominal scales use only identification or categories.
Ordinal scales uses rankings.
Summary Points continued
Interval scales work in equal distance.
Ratio scales have an absolute zero point.
Central tendencies are the mean, median, and mode.
Variability of the data describes how the data varies between each score and also from the mean.
Summary Points continued
Standard deviation allows an individual the ability to describe data based on a normal distribution and the percentages of the normal distribution expected to occur between each standard deviation unit.
Chi Square is used when the dependent variable is scaled nominally to determine if an association between the variables.
T-test is used for one nominal variable for two groups.
ANOVA is used for one nominal variable with more than two groups.
Case studies leads to larger quantitative trials.
