This webinar is part of the Advanced Methods Webinar Series
Regression is used to examine the relationship between one or more explanatory (independent) variables and an outcome (dependent) variable. Ordinary least squares regression looks at the effect of explanatory variables on the average value of the outcome. But we may want to model the median value or some other quantile (for example we may want to study the 90th percentile waiting time for a procedure rather than the average waiting time).
As well, our ability to draw inferences from ordinary least squares regression (e.g., hypothesis testing, p-values) depends on the residuals being normally distributed with constant variance. Many interesting relationships don’t meet these criteria. Instead the distributions are highly skewed, with non-constant variance.
Quantile regression addresses both these considerations, allowing us to model the medians or other percentiles of an outcome, and works for outcomes with outliers and skewed distributions. This presentation will introduce and explain quantile regression, including its assumptions and advantages and the interpretation of the output.Quantile regression will be illustrated using the SAS® QUANTREG procedure.
Ruth Croxford is a Senior Epidemiologist at ICES. She has Master’s degrees in Statistics from the University of Toronto and in Computer Science from Queen’s University, and will try not to embarrass any of these institutions during this webinar.
At ICES, she has contributed to the design and analysis of projects covering a wide variety of topics in health care. In the process, she’s been extremely fortunate to continually learn from colleagues and researchers. She is pleased to participate in this webinar series, as we all continue to learn from one another.