<div class="breadcrumb breadcrumbs"><div class="breadcrumb-trail"> <span class="breadcrumb-title">Browse:</span> <a href="https://quant667-spph.sites.olt.ubc.ca" title="Quantitative Methods for for the Assessment & Analysis of Exposure Data" rel="home" class="trail-begin">Home</a> <span class="sep">/</span> <a href="https://quant667-spph.sites.olt.ubc.ca/week-by-week-class-preparation/" title="Week by Week Class Preparation">Week by Week Class Preparation</a> <span class="sep">/</span> Week 4: Analyses of Categorical vs. Continuous Variables </div></div>
Slides are here:
To prepare for this class:
A. Please read the following:
- from PDQ Statistics, pages 41-52 “Comparison Among Many Means: ANOVA”
B. Please consider the following questions for discussion in class:
- What are different sources of variability within a dataset?
- What is “within group” variability and how does it compare with “between group” variability?
- What is the null hypothesis for an ANOVA?
- What methods can we use to visualize the relationship between a continuous variable and a categorical variable?
C. Get your radon dataset ready for analysis
- Ensure that you know how to define the reference category for categorical variables in Deducer
Objectives of this class:
A. Hypothesis generation for categorical variables
- Which variables in the radon dataset are categorical?
- How might they be associated with the radon concentrations?
- How can we test our hypotheses?
B. Visualization of continuous variables by categorical variables
- Density plots for each value of the dichotomous variable
- Box plots
C. Comparing the means to multiple groups of samples
- ANOVA (analysis of variance)
- Overall association with the categorical variable
- Association with specific categories of the variable
D. Simple linear regression
- Dependent and independent variables
- The null hypothesis
- Dummy variables for categorical variables
- Interpretation of coefficients
- Standard reporting