CH 1: Data
Categorical vs. Quantitative
◦ Discrete vs. Continuous Quantitative Data
Populations vs. Samples
Data Analysis
◦ Identify the research objective
◦ Collect the information needed
◦ Organize and summarize the information
◦ Draw conclusions form the information
Data coding
Stacked vs. Unstacked Data.
Types of studies
◦ Observational vs. Experiment (Advantages and disadvantages)
“Gold Standard” for Experiments
◦ Large sample size
◦ Random assignment to groups
◦ Placebo used
◦ Double-blind
CH 2: Visual Summaries
Categorical variables
◦ Bar Charts
◦ Pie Charts
Numerical variables
◦ Dot Plots
◦ Histograms
◦ Stem Plots
Shape (including deviations of the overall pattern)
◦ Symmetric
uniform
bell shaped
other symmetric shapes
◦ Asymmetric
right skewed
left skewed
◦ Unimodal, bimodal
Typical Value (center)
Variability (spread)
CH 3: Numerical Summaries
Symmetric Distributions
◦ Mean
◦ Variance and S.D.
Empirical Rule
◦ 68, 95, 99%
◦ Z-scores
Skewed Distributions
◦ Median
◦ IQR
Quartiles
Five-Number Summary
◦ Min, Q1, Median, Q3, Max
◦ Boxplot is visual representation
Fence Rule
CH 4: Regression Analysis: Exploring Associations Between Variables
Response (Y, predicted ) variable vs. Explanatory (X, predictor) variable
Scatterplots (Graphical descriptor of associations)
◦ Shape (linear, curved, etc)
◦ Trend ( + or -)
◦ Strength (how close are points?)
Possible outliers
Correlation (Numerical descriptor of associations)
◦ -1< r < 1
◦ The closer to -1 or 1 the stronger the relationship
Regression line
◦ y = a + bx
◦ Used often to predict future values
Coefficient of Determination
◦ R^2
