Statistical methods are indispensable to the practice of science. But statistical
hypothesis testing can seem daunting, with P-values, null hypotheses, and the
concept of statistical significance. This article explains the concepts associated
with statistical hypothesis testing using the story of “the lady tasting tea,” then
walks the reader through an application of the independent-samples t-test
using data from Peter and Rosemary Grant’s investigations of Darwin’s
finches. Understanding how scientists use statistics is an important component
of scientific literacy, and students should have opportunities to use statistical
methods like this in their science classes.
Key Words: AP Biology; college science; data analysis; data interpretation; IB
Biology; inquiry instruction; secondary school science; statistical analysis; statistics.
Statistical methods are indispensable to
the practice of science, and understanding
science includes understanding the role
statistics play in its practice. Students
must be given opportunities to analyze
data in their science classes, using statistical methods that are suited to the data and
age-appropriate. Middle school science
students should be able to construct and
interpret graphs, understand variation,
calculate a mean, and understand what
standard deviation tells us about a distribution. High school and college biology
students should be able to construct and
interpret error bars, and perform and
interpret statistical hypothesis tests like chi-square and the independent-samples t-test. Here, I explain the meaning of statistical
significance and related terms associated with hypothesis testing,
using an application of the independent-samples t-test as an
Variation & Sampling
As we engage students with inquiry labs, situations arise where students must make decisions based on data. Statistics allow us to organize data for interpretation and deal with variation in the data. There
are many sources of variation. Some variation, like the genotypic and
phenotypic differences between organisms, is characteristic of the systems we study. But some of the variation we see is induced by data
collection (Wild, 2006). Figure 1 distinguishes the sources of induced
variation from the real variation in which we are interested. Measurement error can arise from mistakes made by the person making the
measurements or from limitations or flaws in the measuring devices.
Other errors can occur during the collection and processing of data.
For example, a number could be entered in the wrong column on a
data table or spreadsheet. Finally, there is always
sampling error. Sampling error results when a sample that is intended to represent the entire population does not adequately do so.
Being meticulous in your data collection and
sampling methods may reduce or eliminate many
of these sources of induced variation. For example,
careful attention to detail can reduce or eliminate
the chance of measurement errors or accidents
occurring during data collection and processing.
But measuring devices will always have limitations
resulting in some degree of variation and uncer-
tainty, however small. And unless we only deal with
cases where populations are very small and we can
measure every individual, there will always be some
sampling error. Statistical methods help us filter out any real variation
in sample data from the surrounding noise caused by induced variation
so that we can learn something about our population of interest.
Students must be
given opportunities to
analyze data in their
science classes, using
that are suited to the
data and age-
The American Biology Teacher, Vol. 81, No. 8, pp. 535–542, ISSN 0002-7685, electronic ISSN 1938-4211. © 2019 National Association of Biology Teachers. All rights
reserved. Please direct all requests for permission to photocopy or reproduce article content through the University of California Press’s Reprints and Permissions web page,
www.ucpress.edu/journals.php?p=reprints. DOI: https://doi.org/10.1525/abt.2019.81.8.535.
THE AMERICAN BIOLOGY TEACHER MAKING DECISIONS WITH DATA
FREEMAN, SCOTT; HERRON, JON C., EVOLUTIONARY ANALYSIS, 4th, ©2007.
Reprinted by permission of Pearson Education, Inc., New York, New York.
FEATURE ARTICLE Making Decisions with Data:
Understanding Hypothesis Testing
& Statistical Significance
• ROBERT A. COOPER