Notes on Data Interpretation and Analysis
Introduction to Data Interpretation
Instructor: Paul Tooney
Contact: Paul.Tooney@newcastle.edu.au
Learning Objectives
Understand populations, sampling & sample size
Identify data presentation types and their strengths/limitations
Describe and compare data
Discuss data distribution types
Define measures of central tendency
Introduction to hypothesis and hypothesis testing
Importance of sample size & power calculation
Data Presentation
Tables: Display frequency counts and relative frequencies
Graphs:
Bar Charts: Show cases visually (e.g., diseases)
Histograms: Display distribution of data
Box and Whisker Plots: Visualize five-number summaries
Allows for easy trend identification
Concepts
Population: Entire group of interest
Sample: Subset drawn from the population
Statistics: Summarizing numerical values from a population/sample
Sampling Methods
Representative vs. convenience samples
Random sampling techniques to eliminate bias
Sample Size and Error
The optimal sample size depends on the context and accuracy requirements
Sampling error defined as the difference between sample and population statistics
Hypothesis Testing
Aim to determine the probability of observing the data assuming the null hypothesis is true
Null hypothesis (Ho) indicates no effect/difference
Alternative hypothesis (H1) suggests a difference exists
Measures of Central Tendency
Include mode, median, and mean
Dispersion: Indicates data spread (e.g., range, standard deviation)
Simple Linear Regression
Method to evaluate relationships between variables
Coefficient of determination (R²) indicates fit quality of the model
Applications of Statistics in Research
Statistical methods facilitate drawings conclusions from sample to population based on data