1.6: Designing a Statistical Study
- Page ID
- 58859
\( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)
\( \newcommand{\dsum}{\displaystyle\sum\limits} \)
\( \newcommand{\dint}{\displaystyle\int\limits} \)
\( \newcommand{\dlim}{\displaystyle\lim\limits} \)
\( \newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\)
( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\)
\( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\)
\( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\)
\( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\)
\( \newcommand{\Span}{\mathrm{span}}\)
\( \newcommand{\id}{\mathrm{id}}\)
\( \newcommand{\Span}{\mathrm{span}}\)
\( \newcommand{\kernel}{\mathrm{null}\,}\)
\( \newcommand{\range}{\mathrm{range}\,}\)
\( \newcommand{\RealPart}{\mathrm{Re}}\)
\( \newcommand{\ImaginaryPart}{\mathrm{Im}}\)
\( \newcommand{\Argument}{\mathrm{Arg}}\)
\( \newcommand{\norm}[1]{\| #1 \|}\)
\( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\)
\( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\AA}{\unicode[.8,0]{x212B}}\)
\( \newcommand{\vectorA}[1]{\vec{#1}} % arrow\)
\( \newcommand{\vectorAt}[1]{\vec{\text{#1}}} % arrow\)
\( \newcommand{\vectorB}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\( \newcommand{\vectorC}[1]{\textbf{#1}} \)
\( \newcommand{\vectorD}[1]{\overrightarrow{#1}} \)
\( \newcommand{\vectorDt}[1]{\overrightarrow{\text{#1}}} \)
\( \newcommand{\vectE}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash{\mathbf {#1}}}} \)
\( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\(\newcommand{\longvect}{\overrightarrow}\)
\( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)
\(\newcommand{\ket}[1]{\left| #1 \right>}\)
\(\newcommand{\bra}[1]{\left< #1 \right|}\)
\(\newcommand{\braket}[2]{\left< #1 \vphantom{#2} \right| \left. #2 \vphantom{#1} \right>}\)
\(\newcommand{\braopket}[3]{\left< #1 \vphantom{#2}\vphantom{#3} \right| #2 \vphantom{#1}\vphantom{#3} \left| #3 \vphantom{#1}\vphantom{#2} \right>}\)
\(\newcommand{\qmvec}[1]{\mathbf{\vec{#1}}}\)
\(\newcommand{\op}[1]{\hat{\mathbf{#1}}}\)
\(\newcommand{\expect}[1]{\langle #1 \rangle}\)
\(\newcommand{\dfn}[1]{\emph{\textbf{#1}}}\)
Launching Your Statistical Study
As we move forward in the course, you’ll be applying the skills you’re learning by designing and carrying out your own statistical study. This will be a semester-long project where you take on the role of a statistician asking a real-world question, collecting or analyzing relevant data, uncovering patterns, and sharing what you’ve found.
In this short section, we’ll outline the structure of a statistical study and identify what you’ll need to include as you begin planning your investigation.
What Is a Statistical Study?
A statistical study uses data to answer a question about a population or process. A good study is built on clear thinking, purposeful design, and awareness of bias and variability.
Statistical studies can take different forms, including:
- Surveys: collecting responses from individuals using questions
- Observational studies: recording observations without interference
- Experiments: intentionally applying treatments and comparing outcomes
- Data analyses: working with existing datasets to explore a question
You’ll choose a question and approach that fits your interests and access to data.
Variables in a Study
Many statistical questions ask whether one variable is related to, or affects, another. Two terms describe the roles these variables play:
- Explanatory variable: the variable we think may explain or influence changes in another variable. In an experiment, it is the treatment the researchers apply.
- Response variable: the outcome we measure to see whether it changes.
Example: In the Tree Health Study, nearby construction (yes or no) is an explanatory variable, and health score is the response variable.
When we see a relationship between an explanatory variable and a response variable, a third variable may also be part of the story:
- Confounding variable: a variable that is related to both the explanatory variable and the response variable, so their effects on the response can’t be separated.
- Lurking variable: a confounding variable that the study didn’t measure or include. Because it isn’t in the data, it can easily go unnoticed.
Example: Trees near construction sites may also be closer to busy roads, and road pollution can harm tree health too. If the researchers recorded each tree’s distance to the nearest road, that distance is a confounding variable they can account for in their analysis. If they didn’t record it, it is a lurking variable, and some of the decline they blame on construction could really be caused by traffic.
Careful study design helps limit the influence of these variables. We’ll come back to them when we discuss correlation and causation in Chapter 9.
Elements of a Well-Planned Study
As you begin, here are the major components you’ll need to outline (many of which connect to ideas from earlier in this chapter):
- A good statistical question: something that involves variability and can be answered with data
- A target population: the group you want to learn about
- A sampling strategy or data source: how you’ll choose participants or find your data
- A plan for data collection or acquisition: what variables you’ll record, and how
- Ways to minimize bias: including your role in the study and any design choices
- A timeline or check-ins: since this will unfold over several weeks
What Happens Next?
We will look at the premise of a semester-long study investigating housing affordability in your area.