0% found this document useful (0 votes)
19 views8 pages

Understanding Unusual Observations in Statistics

This in-class activity focuses on using the Empirical Rule to identify unusual observations in the context of medical studies involving mice. Students will learn to calculate standardized scores and apply these concepts to determine if liver and spleen weights are typical or atypical. The activity includes collaborative discussions, problem-solving, and a transition to future topics related to probability distributions.

Uploaded by

serkan özel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
19 views8 pages

Understanding Unusual Observations in Statistics

This in-class activity focuses on using the Empirical Rule to identify unusual observations in the context of medical studies involving mice. Students will learn to calculate standardized scores and apply these concepts to determine if liver and spleen weights are typical or atypical. The activity includes collaborative discussions, problem-solving, and a transition to future topics related to probability distributions.

Uploaded by

serkan özel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Introductory Statistics First Edition (2021)

Instructor Edition

In-Class Activity 4.E


What Is Unusual?
Overview and student objectives
In-Class Activity Length: 25 minutes
Prior In-Class Activity: In-Class Activity 4.D, “Good Tax Policy?”
Next In-Class Activity: In-Class Activity 5.A, “What’s in My Sandwich?” (25 minutes)
Constructive Perseverance Level: 1
Content Learning Outcomes: DP.5.A, DP.5.C, DP.2.D
DCMP Learning Goals: Communication, Problem Solving

Overview
In this in-class activity, students apply the Empirical Rule within a medical context to
determine “unusual” observations. Students are introduced to a quantifiable measure to
compare observations using standardized units and determine if an observation is
outside the range of usual values.

Objectives
Students will understand:
• Standardized scores and the Empirical Rule can be used to determine if an
observation is usual or unusual.
Students will be able to:
• Utilize standardized scores and the Empirical Rule to determine if an observation
is unusual.
• Compare two observations by calculating and comparing the standardized score.
Suggested resources and preparation
Materials and technology
• Computer, projector, document camera
• Preview Assignment 4.E
• Student Pages for In-Class Activity 4.E
• Practice Assignment 4.E
Prerequisite assumptions
Students should be able to:
• Convert values into standardized scores.

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

• Use a value’s standardized score to determine whether the value is above,


below, or equal to the mean.
• Explain the Empirical Rule.
Making connections
This activity:
• Connects back to measures of center and spread.
• Connects forward to probability distributions and hypothesis testing.
Background context
In the preview assignment, students were introduced to the Empirical Rule.
Suggested instructional plan
Frame the activity (5–7 minutes)
Resources
and Structure
Instructor Suggestions
Think-Pair-
Share • Have students read and answer Question 1 independently. Then,
have students discuss their answers in pairs before sharing with the
full group.

• Transition to the in-class activity by briefly discussing the Objectives


for the activity.

Activity flow (16–18 minutes)


Resources
and Structure
Instructor Suggestions

• Use the last part of Question 1—“Are there alternatives to having


human volunteers participate in clinical trials?”—to lead into the two
paragraphs that follow the objectives.
Individual • If it hasn’t come up already, mention that one alternative to testing on
Reading humans is testing on mice. Then have students read both paragraphs
individually.

Think-Pair- • Make sure to give students enough time to process the information
share they have read individually first.
• In pairs, have students formulate any questions they might have
about this context.
• Have pairs share their questions and address them. Possible
questions that will come up include:

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

Literacy o “What is a genome?” [Answer: A genome is an organism’s


Support complete set of genetic instructions. Each genome contains all
of the information needed to build that organism and allow it to
grow and develop. Our bodies are made up of millions of cells,
each with their own complete set of instructions for making us,
like a recipe book for the body. This set of instructions is
known as our genome and is made up of DNA.1]
For more information on genomes, visit
[Link]
o “What is toxicity?” [Answer: The degree to which a substance
(a toxin or poison) can harm humans or animals.2]
o “Why is organ weight used to measure toxicity?” [Answer:
Organ weight changes are indicators of chemically-induced
organ damage.3 Hence, changes in organ weight are often
associated with treatment-related effects.]

Pair or Group
Questions 2 and 3
Work • Have students work on these problems in pairs or small groups.
• Optional: You may want to assign half of the pairs or small groups
Question 2 (livers) and the other half of the pairs or small groups
Question 3 (spleens). Make sure students share their answers
across groups during the debrief of these questions.
• Students were introduced to the Empirical Rule in the preview
assignment, but it will be helpful to display the following graph:

1
What is a genome? (2017, January 6). Yourgenome. Retrieved from
[Link]
2
Definition of toxicity. (2021, March 29). RxList. Retrieved from
[Link]
3
Lazic, S. E., Semenova, E., & Williams, D. P. (2020, April 20). Determining organ weight toxicity with
Bayesian causal models: Improving on the analysis of relative organ weights. National Center for
Biotechnology Information. [Link]

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

• If students have difficulty with Questions 2 and 3, point back to the


listed means and standard deviations. Using the horizontal axis on
the chart, ask: “What values are associated with 68% of the data?”
[Answer: One standard deviation greater than the mean (𝜇 + 𝜎) and
one standard deviation less than the mean (𝜇 − 𝜎)]

Debrief • Debrief these questions before continuing. Address any issues or


questions that arise.

Questions 4
• If students have difficulty answering Question 4, it is okay to mention
that an observation that is two standard deviations from the mean is
considered unusual. Point back to the chart and ask: “What
percentage of the data is within two standard deviations of the
Guiding
mean?” [Answer: 95%]
Questions • Follow-up question: “In this context, between which two values are
95% of the data?” [Answer: 0.825 g and 1.173 g for liver and 0.072 g
and 0.100 g for spleen]
• Follow-up: Have students identify a value that is not within 0.825 g
and 1.173 g for livers and not within 0.072 g and 0.100 g for spleens.
• Debrief this question by having groups share a few unusual values. If
Debrief it does not come up during the debrief, make sure to include and talk
about values that are more than two standard deviations greater than
the mean AND two standard deviations less than the mean.
Question 5
!"#
• It might be helpful to display the standardized score formula: 𝑧 = $
.
• Throughout this question, develop the inclination to talk about
“standard deviations from the mean.”

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

Wrap-up/transition (2 minutes)
Resources
and Structure
Instructor Suggestions

Wrap-up • Have students share their answers to Question 5.


• Ensure students are communicating appropriately using statistical
terms. In this question, the liver weight of 1.07 g is 0.816 standard
deviations above the mean and the spleen weight of 0.104 g is 2.571
standard deviations above the mean.
• The spleen shows a higher level of toxicity because the weight of the
spleen is highly unusual at 2.571 standard deviations above the mean,
whereas the liver weight is within one standard deviation above the
mean.
• Make sure students understand that z-scores do not have units
associated with them.
Transition
• In the next activity, we will be investigating the relationship between
the energy content of food and the carbon footprint.

Suggested assessment, assignments, and reflections


• Give Practice Assignment 4.E.
• Give the preview assignments, if any, for the activities you plan to complete in
the next class meeting.

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

In-Class Activity 4.E What Is Unusual? ANSWERS


Around the world, pharmaceutical companies conduct clinical trials to evaluate the
safety and efficacy of their drugs. Clinical trials are research studies performed on
people and are aimed at evaluating if a new drug is safe and effective. People who
participate in clinical trials are volunteers.

1) Why do you think someone would volunteer


to participate in a clinical trial? What are the
pros and cons? Are there alternatives to
having human volunteers participate in
clinical trials?
Answers will vary.
Credit: iStock/Geber86

Objectives for the activity


You will understand:
¨ Standardized scores and the Empirical Rule can be used to determine if an
observation is usual or unusual.
You will be able to:
¨ Utilize standardized scores and the Empirical Rule to determine if an observation is
unusual.
¨ Compare two observations by calculating and comparing the standardized score.

Mice are often used in medical studies to evaluate the effects of chemicals and
pharmaceuticals. One reason for this is that scientists know a lot about the genome of a
mouse. They are bred in labs to be identical, so the only thing different between them is
the treatment. Mice also have short lifespans, which allows scientists to model the
effects of a drug over their entire lifespan (about 800 days). It is much more difficult to
understand the effects of a drug over the lifetime of a human.
The toxicity of a chemical and its impact on vital organs is of interest when assessing
the effects of a chemical treatment. A standard method used to measure the level of
toxicity in an organ is to use the organ’s weight.4
In this in-class activity, we will be looking at the weights of the livers and spleens in 26-
week old female C57BL/6J laboratory mice. The mean liver weight is 0.999 grams (g)
4
Sellers, R. S., Mortan, D., Michael, B., Bindhu, M., Roome, N., Johnson, J. K., Yano, B. L., Perry, R., &
Schafer, K. (2007). Society of toxicologic pathology position paper: Organ weight recommendations for
toxicology studies. Toxicologic Pathology. 35(5), 751-755. [Link]

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

with a standard deviation of 0.087 g, and the mean spleen weight is 0.086 g with a
standard deviation of 0.007 g.5

2) Use the Empirical Rule to answer the following. Round your answers to three
decimal places.

Part A: About 68% of the mice will have liver weights between ____ and _____.
Answer: 0.912 g; 1.086 g

Part B: About 95% of the mice will have liver weights between ____ and _____.
Answer: 0.825 g; 1.173 g

Part C: About 99.7% of the mice will have liver weights between ____ and _____.
Answer: 0.738 g; 1.26 g

3) Use the Empirical Rule to answer the following. Round your answers to three
decimal places.

Part A: About 68% of the mice will have spleen weights between ____ and _____.
Answer: 0.079 g; 0.093 g

Part B: About 95% of the mice will have spleen weights between ____ and _____.
Answer: 0.072 g; 0.100 g

Part C: About 99.7% of the mice will have spleen weights between ____ and _____.
Answer: 0.065 g; 0.107 g

4) What do you think are unusual spleen and liver weights? Why?
Answers will vary.

5
The Jackson Laboratory. (2021). Organ weight summary. [Link]
mice-and-services/b6j-data-
[Link]?la=en&hash=E24ADBC35E64976367B3B08AFFDCE7A1FC434C4D

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin
Introductory Statistics First Edition (2021)
Instructor Edition

Sample answer: Typically, unusual is more than two standard deviations away from
the mean. An unusual spleen weight is less than 0.072 g or greater than 0.100 g. An
unusual liver weight is less than 0.825 g or greater than 1.173 g.

5) A higher organ weight is an indicator of higher toxicity. Suppose a mouse has a liver
weight of 1.07 g and a spleen weight of 0.104 g.

Part A: Calculate and interpret the z-score for the liver weight of 1.07 g.
%.'("'.)))
Answer: z = '.'*(
= 0.816
The liver weight of 1.07 g is 0.816 standard deviations above the mean.

Part B: Calculate and interpret the z-score for the spleen weight of 0.104 g.
'.%'+"'.'*,
Answer: z = '.''(
= 2.571
The spleen weight of 0.104 g is 2.571 standard deviations above the mean.

Part C: Which organ shows a higher level of toxicity?


Answer: The spleen shows a higher level of toxicity because the weight of the
spleen is highly unusual at 2.571 above the mean, whereas the weight of the liver is
only slightly higher than the mean.

Copyright © 2021, The Charles A. Dana Center at The University of Texas at Austin

Common questions

Powered by AI

The liver weight of 1.07 g, with a z-score of 0.816, is within one standard deviation above the mean, suggesting it is within the usual range. In contrast, the spleen weight of 0.104 g, with a z-score of 2.571, is more than two standard deviations above the mean, marking it as unusual and indicative of higher toxicity .

The Empirical Rule can be applied to determine the normal weight range for the liver by calculating intervals based on standard deviations from the mean. For example, in a study with a liver mean weight of 0.999 g and a standard deviation of 0.087 g, about 95% of liver weights would fall between 0.825 g and 1.173 g, defining the normal range .

Using mice in clinical studies is advantageous because they have known genomes, can be bred to be genetically identical, and have short lifespans, allowing scientists to observe drug effects over an entire lifespan relatively quickly. However, disadvantages include potential differences in drug effects between mice and humans, limiting the direct applicability of results to human physiology .

Organ weight is a critical measure in determining toxicity because changes in organ weight can indicate chemically-induced organ damage. This makes it a valuable indicator of treatment-related effects, providing insights into the level of harm a substance can cause .

An unusual observation in medical research data is typically one that is more than two standard deviations away from the mean, according to the Empirical Rule. This implies that the observation lies outside the typical 95% range, which in toxicity studies could indicate a substance's significant impact on organ weight, and thereby its toxic effect .

The Empirical Rule states that about 95% of data in a normal distribution lies within two standard deviations of the mean. This means data falling beyond this range is considered unusual .

The Empirical Rule helps determine if an observation is usual or unusual by providing a quantifiable measure to compare observations based on their standardized scores. Observations are considered unusual if they fall outside a certain percentage range dictated by the Empirical Rule, specifically if they are more than two standard deviations away from the mean .

Understanding the genome of laboratory mice facilitates medical research by ensuring genetic consistency, allowing scientists to attribute differences in trial outcomes solely to treatment variables rather than genetic differences. This controlled genetic environment aids in accurately assessing pharmaceutical effects and toxicities, contributing to replicable and reliable study outcomes .

Z-scores assess toxicity levels by indicating how many standard deviations an organ's weight is above or below the mean. A higher z-score suggests greater deviation from the norm, signifying potentially higher toxicity. For example, a spleen weight with a z-score of 2.571 suggests high toxicity, as it is significantly above the mean .

Bypassing human trials for animal models can mitigate ethical concerns related to human testing risks but poses scientific implications due to biological differences between species, which might lead to imprecise efficacy and safety data. Although animal models provide beneficial preliminary data and circumstantial evidence, they can't fully replicate human physiological responses, necessitating subsequent human trials .

You might also like