PDF Version

Knowledge Expectations for METR 4303
Statistical Meteorology

Purpose: This document describes the principal concepts, technical skills, and fundamental
understanding that all students are expected to possess upon completing METR 4303, Statistical
Meteorology. Individual instructors may deviate somewhat from the specific topics and order listed
here.

Pre-requisites: Grade of C or better in MATH 2423, CS 1313 (or CS 1323), or permission of
instructor.

Upon entering this course, students should have a working knowledge of limits, differentiation,
integration and experience programming in any language with an idea of the basics of how to write a
computer program.

Goal of the Course: This course is designed to illustrate the interplay between statistics and
meteorology. At a first glance, statistics may seem not as exciting (to many of us) as, say,
chasing tornadoes. However, projects that receive national funding for chasing have considerable
experimental design built in and the resulting data are almost always statistically analyzed to
evaluate competing theories, among other things. In order to understand how experiments are
designed and analyzed, the course will cover theory of descriptive statistics, a brief overview of
probability and probability distributions, inferential statistics, and regression. The relevance to
the atmosphere will be examined through use of meteorological data sets and by review of key
journal articles which have relied on statistics for support and illumination. If the class is
successful, you will exit with an enthusiasm for statistics and a “toolbox” of techniques to apply
to data sets using Splus.
Topical Knowledge Expectations

I. Descriptive Statistics
• Understand the ideas of scale that data are measured on.
• Understand and be able to apply measures of location. Know each methods pros and cons.
• Understand and be able to apply measures of variability. Know each methods pros and cons.
• Understand skewness and kurtosis.
• Understand what resistant measures are and when to apply them.
• Understand boxplots and other graphical exploratory data analysis devices.
• Understand how to construct and fully analyze scatterplots.
• Know the formulation of Pearson’s and Spearman’s correlation.