Statistics lab analysis
Open your materials, follow the steps, then turn in your work.
Analyze your physiology dataset using descriptive statistics and a comparison test.
1. Open your materials
Use the materials named in the first step below. Open lesson resources.
2. Start the work
Compute summary statistics for each condition in a spreadsheet.
Show all 5 required steps
- Compute summary statistics for each condition in a spreadsheet.
- Run or interpret a t-test comparing your conditions.
- Determine whether the difference is statistically meaningful.
- Record the analysis steps so they are reproducible.
- Submit your completed statistical analysis.
Lost your place? Find your spot: if you have not computed summary statistics (mean, and the spread) for each condition yet, do that first; if you have those, run or interpret the t-test; if you have a p-value, decide whether the difference is statistically meaningful; then make sure every step is written down before you submit.
Check your work before submitting
- Your analysis reports statistics and a comparison result.
- You can state whether a difference is statistically meaningful.
Before lab work: read the safety rules
- Wear the required PPE, keep the bench clear, handle equipment only as directed, and know where the eyewash, sink, and spill kit are before you start.
- Human samples and data stay private: label with a code, never a name, and dispose of materials in the correct waste container, then wash your hands.
3. Turn in your work
DueCheck Schoology- Hand in
- Spreadsheet statistical analysis: summary statistics per condition, t-test result with interpretation, and reproducible step documentation.
How to submit and name your file
Use the submission route shown on today's today's page.
In Schoology, open your course and the assignment for this lesson. Attach your file, select Submit, and check that it appears in the submission.
PDF upload helpYou get two school days for every day you were absent, so this deadline moves with you.
How this lesson connects
Keep using what you learned last class: The graph type encodes a claim about your data, so choosing one that fits a two-condition comparison (and starting the axis fairly) is what lets the real pattern show instead of a manufactured one. Today: A difference between averages could come from chance when the data are spread out, so you run a t-test and record every step, because that is what lets you (and anyone else) trust the result is real and repeatable.
Optional: listen or watch a unit review▸
Need help? Warm-up, timing, and directions▸
💡 Big idea: A difference between averages could come from chance when the data are spread out, so you run a t-test and record every step, because that is what lets you (and anyone else) trust the result is real and repeatable.
- 0-10Open the spreadsheet dataset and verify it matches your submitted
- 10-30Compute summary statistics for each condition: mean, SD, and count
- 30-55Run or interpret a t-test comparing the two conditions; record the result and what it means
- 55-65State whether the difference is statistically meaningful and explain in plain language
- 65-77Record all analysis steps so they are reproducible; submit the completed analysis
- 77-80Exit check: what would change in your conclusion if your had been twice as large?
- • Today you run the full statistical analysis on your physiology dataset.
- • You will use a spreadsheet to compute summary statistics and run or interpret a t-test.
- • Every step must be documented so the analysis can be reproduced -- undocumented analysis is not publishable.
- • Statistical analysis appears directly in the Molecular and Genetic Technology and data-skills strands of WebXam 072125.
- • How to compute summary statistics for each condition in a spreadsheet and interpret what they mean.
- • How to run or interpret a t-test and state whether the result is statistically meaningful.
- • Why recording every analysis step enables someone else to reproduce your result.
PLTW connection and today's work
Open Problem 2 in your myPLTW course shell and locate the statistics-analysis or data-interpretation activity to review the spreadsheet format and t-test guidance.
Today's stopping point: The graph draft is done; by end of today your full statistical analysis with summary stats, t-test result, and reproducible steps should be submitted.
PLTW activity titles identify the course connection. If your account will not open, use the posted materials for today and tell Mr. Mendoza. Do not mark an online activity complete unless you completed it.
Course connection
- Activity 2.1.3 Making Results Meaningful
Use the turn-in directions at the top of this page. Do not create a second submission unless your teacher asks for one.
Show another explanation or a smaller first step
Need help? Choose a starting point
Finish the assigned lab safely before starting extra practice.
Lesson resources: reading, slides, and vocabulary▸
The deck carries the prior idea forward, lets you inspect an analogy, maps the rule to biology, and ends with the same evidence decision and exit ticket used on this page.
Generated from this lesson's canonical data with a red-team citation check.
The graph type encodes a claim about your data, so choosing one that fits a two-condition comparison (and starting the axis fairly) is what lets the real pattern show instead of a manufactured one.
A difference between averages could come from chance when the data are spread out, so you run a t-test and record every step, because that is what lets you (and anyone else) trust the result is real and repeatable.
A research team lays out its question, variables, controls, sampling plan, measurement record, and analysis before deciding what the data support.
- Which variable is changed or compared?
- Which conditions and measurements must stay consistent?
- Which conclusion is inside the study's evidence boundary?
Define variables, controls, sampling, units, and the analysis plan before interpreting a result; analysis cannot repair biased or inconsistent measurement.
A well-organized classroom study can still be limited by , measurement quality, confounding, and the population represented.
- • Question and variable cards map to the study design.
- • Control and measurement cards map to fair, reproducible data collection.
- • The conclusion card maps to a bounded claim supported by the analysis.
Driving question: Your two conditions have different averages. But is that gap big enough to trust, or small enough that random variation between your subjects could have produced it by accident?
What you already know: The graph type encodes a claim about your data, so choosing one that fits a two-condition comparison (and starting the axis fairly) is what lets the real pattern show instead of a manufactured one.
New idea: A difference between averages could come from chance when the data are spread out, so you run a t-test and record every step, because that is what lets you (and anyone else) trust the result is real and repeatable.
Visual or model: F1. F1. A lesson illustration or teaching diagram for Statistics lab analysis. Use it with E1-E3; it is a model or context image, not experimental or patient data. What to notice: Trace the labeled system, test, or design relationship and identify which evidence should trigger revision.
- Observe or measure the relevant feature in statistics lab analysis.
- Organize the observation with a stable evidence ID.
- Apply this rule: Define variables, controls, sampling, units, and the analysis plan before interpreting a result; analysis cannot repair biased or inconsistent measurement.
- Choose the option the evidence supports and state the limit of the conclusion.
Real biomedical example: Your two conditions have different averages. But is that gap big enough to trust, or small enough that random variation between your subjects could have produced it by accident?
What the evidence supports: E1-E3 and F1 support the daily take-home when the response meets the stated success criteria.
What it cannot prove: The package does not support claims beyond this lesson's or any real patient diagnosis.
- • t-test: A statistical test that compares the average values of two groups to judge whether their difference is likely real or just due to chance.
- • validity: How well a test or study actually measures what it claims to, so the conclusions truly reflect reality.
- • reliability: The degree to which a measurement, method, or person produces the same dependable result each time under the same conditions.
- • limitation: A weakness or boundary of a study, design, or method that restricts how far its results can be trusted or applied.
- • : A result unlikely to be due to chance, often shown by a p-value below a set threshold such as 0.05.
Use it now: Choose one decision option. Cite E1 and E3, then explain how the rule connects the evidence to your choice.
Go further, optional: The source links below are optional enrichment. Every fact required for today's local evidence decision appears in this lesson package.
A planned study connects its question to defined variables, controls, sampling, measurement, and analysis so the resulting data can support a bounded and reproducible conclusion.
Limit: A statistical difference or trend does not automatically establish practical importance, causation, generalizability, or freedom from bias.
Define variables, controls, sampling, units, and the analysis plan before interpreting a result; analysis cannot repair biased or inconsistent measurement.
Limit: A well-organized classroom study can still be limited by , measurement quality, confounding, and the population represented.
Your analysis reports statistics and a comparison result.
Limit: E3 defines the classroom product or success criterion. It is not independent scientific evidence and cannot justify a clinical or causal claim.
PLTW-BFH-2027-03-12 · Simulated classroom evidence scenario
Your role: biomedical design team member
Decision: Your team must decide what the evidence from statistics lab analysis supports before submitting the lab report named on today's page.
- • Wait until the records show whether each pair of readings came from one person, because a p-value cannot reveal that.
- • Run the t-test and write down every step, so the difference between your two averages can be trusted and repeated.
- • Report the difference now, because the two averages are clearly not the same and that gap is your result.
Response: State one choice, cite at least two evidence IDs, explain the rule that connects them, and add one limitation. Submit it as the lab report.
Claim ceiling: Today's evidence supports a classroom claim about statistics lab analysis. It cannot prove causation, diagnose a real patient, or justify action outside this room.
Reason for review: Your team must decide what the evidence from statistics lab analysis supports before submitting the lab report named on today's page.
Context: A statistic is only trustworthy if someone else, following your recorded steps, would get the same result. Reproducibility, not a low p-value, is what makes a finding science.
- • T1: Compute summary statistics for each condition in a spreadsheet.
- • T2: Run or interpret a t-test comparing your conditions.
- • T3: Determine whether the difference is statistically meaningful.
- • T4: Record the analysis steps so they are reproducible.
- • T5: Submit your completed statistical analysis.
- • E1: A planned study connects its question to defined variables, controls, sampling, measurement, and analysis so the resulting data can support a bounded and reproducible conclusion.
- • E2: Define variables, controls, sampling, units, and the analysis plan before interpreting a result; analysis cannot repair biased or inconsistent measurement.
- • E3: Your analysis reports statistics and a comparison result.
Measurements: Use only the measurements, units, graph, or counts supplied in today's task. No additional patient measurement is implied.
Figure finding: Teaching diagram for Statistics lab analysis. Trace the labeled system, test, or design relationship and identify which evidence should trigger revision. This is a teaching model, not patient or experimental data.
Uncertainty: This is a composite classroom scenario. Missing history, measurements, or confirmation tests remain unknown and limit the conclusion.
Mean = sum of values / number of values. Median = middle ordered value. Range = maximum - minimum.
For 2, 4, 4, and 10: mean = 20 / 4 = 5, median = 4, and range = 10 - 2 = 8.
Mean, median, and range keep the measurement unit. Order the values before finding the median.
Calculate the requested summary for today's supplied values, then write what it reveals and what it hides.
Students often think Students think that if the two averages are different, the difference is automatically real and worth reporting.. The trap: A gap between two averages is not proof of anything on its own. If the values within each group are spread out widely, that same gap could easily come from chance, which is exactly what a t-test checks, so reporting the difference without the test can announce a discovery that is not there.
Research question: Is the after-activity heart rate significantly higher than resting?
Summary statistics (from my spreadsheet):
- Rest: mean 72.0 bpm, SD 1.6, n = 5
- Activity: mean 97.6 bpm, SD 2.7, n = 5
Comparison test: two-sample t-test on rest vs activity means.
Result: t was large and the p-value was about 0.0001, well below 0.05.
Interpretation: Because p is less than 0.05, a difference this large would be unlikely if activity made no difference at all, so I treat the difference as real. Note what p does NOT say: it is not the probability that chance caused my result, and it says nothing about whether 25 bpm matters clinically.
Reproducible steps (so a classmate could repeat it):
1. Enter the five rest and five activity readings in two columns.
2. Use AVERAGE and STDEV on each column.
3. Use the T.TEST function (two-tailed, two-sample) on the two columns.
4. Compare the returned p-value to 0.05.
This model shows the level of evidence and organization needed to complete: Completes the Problem 2 statistics analysis: summary statistics per condition, a t-test result with interpretation, and reproducible step documentation.
- State the question and method.
- Present the observations and data with units.
- Explain the result, limitations, and next investigation.
Keep the structure. Replace the question, facts, measurements, and evidence. Then recheck units, vocabulary, and whether the conclusion goes beyond the evidence.
Also due today: Submit your completed statistical analysis spreadsheet on Schoology by end of period.
- CER:
- Claim, Evidence, Reasoning: make a claim, back it with evidence, explain your reasoning.
- SOP:
- Standard Operating Procedure, the exact steps to follow (especially in a lab).
- Tracker:
- Your PLTW progress log where you record completed evidence.
- myPLTW:
- The PLTW course site where you do the online activities. Find it in Clever with your Microsoft sign-in, right next to Schoology.
Tap the speaker to hear a term. Add two of these to your notebook glossary with a definition and an example in your own words.
Pick just 2 or 3 words from today and make them yours: write what each one means in your own words, name the context clue or evidence that helped, then give one example from what you actually did in Statistics lab analysis. Try your own words first; the glossary is there if you get stuck. This is voluntary and counts as extra credit, so keep it short.
Saved on this device. Show Mr. Mendoza or add these to your notebook glossary to claim the extra credit.
Classroom documents for this lesson are posted in Schoology. Open Clever, then Schoology, and find each one by the name shown on its card.
Use this if you were absent, got stuck, or need another pass before you submit the lesson artifact.
Placement rationale
Matched Statistical analysis and t-test reasoning by path:Biomedical-Innovations/Problem-2_Human-Physiology/2.1_Human-Physiology; keywords:statistical analysis. Score 138. Visibility: student-schoology (student-facing resource; link through Schoology rather than local path).
Use this if you were absent, got stuck, or need another pass before you submit the lesson artifact.
Placement rationale
Matched Statistical analysis and t-test reasoning by path:Biomedical-Innovations/Problem-2_Human-Physiology/2.1_Human-Physiology; keywords:statistical analysis. Score 134. Visibility: student-schoology (student-facing resource; link through Schoology rather than local path).
Open this when the class reaches this activity and use it to complete the required lesson artifact.
Placement rationale
Matched Statistical analysis and t-test reasoning by path:Biomedical-Innovations/Problem-2_Human-Physiology/2.1_Human-Physiology. Score 126. Visibility: student-schoology (student-facing resource; link through Schoology rather than local path).
Sign in to Clever with your district Microsoft account to open Schoology or myPLTW. Follow today's posted steps. If myPLTW will not open, use the posted alternative and tell Mr. Mendoza. Turn in your completed work through the Schoology assignment.
Practice: try a question, then check your answer▸
Claim ceiling for this check: Today's evidence supports a classroom claim about statistics lab analysis. It cannot prove causation, diagnose a real patient, or justify action outside this room.
Your t-test gives p = 0.02, using the common 0.05 cutoff. In plain words, what does that tell you about the difference between your two conditions?
Write an answer and pick a confidence to unlock the key.
Fast retrieval with instant answers, not the commit-then-reveal check above. Try each from memory first: write what you remember about the earlier units, then check yourself here.
Missed class or ready for more?▸
Run this before you touch the bench. It is built from the real lab procedure, so the decisions you make here are the ones you will make with the equipment in your hands.
I can name the procedure's purpose and the evidence I will record. I can state today's specific hazards and the control for each. If this deck does not name them, I ask Mr. Mendoza before I touch anything. My data table is ready before materials are handled.
Finish the checklist before you handle any material.
- • Wear the required PPE, keep the bench clear, handle equipment only as directed, and know where the eyewash, sink, and spill kit are before you start.
- • Human samples and data stay private: label with a code, never a name, and dispose of materials in the correct waste container, then wash your hands.
- 1Before materials are handled, identify the purpose, variables or comparison, controls, measurement units, and stop-work condition.
- 2Compute summary statistics for each condition in a spreadsheet.
- 3Run or interpret a t-test comparing your conditions.
- 4Determine whether the difference is statistically meaningful.
- 5Record the analysis steps so they are reproducible.
- 6Submit your completed statistical analysis.
- 7Record each result in the prepared table before interpreting it. Mark missing, repeated, or invalid results truthfully.
- 8Complete the named cleanup and waste route, remove PPE safely, wash hands when required, and confirm the station is ready for the next group.
| Trial or sample ID | Independent condition | Measured result with units | Observation before interpretation | Quality-control note |
|---|---|---|---|---|
Before the procedure, predict the result and cite the rule behind the prediction.
After the procedure, compare the result with the prediction and name one limitation or source of uncertainty.
What today's skills lead to. These are real health-science careers this course builds toward. Tap one to see, on the US Department of Labor's O*NET site, what the job actually involves, what it pays, and how fast it is growing.
Complete the statistics analysis on your spreadsheet dataset: compute summary statistics, run or interpret a t-test, and record reproducible steps with the result.
Khan Academy Statistics and ProbabilityUse the submission route shown on today's today's page.
Class still runs. Complete the online activity above (it's self-guided). Need the concept taught without a teacher? Use this authoritative explainer:
Khan Academy Statistics and Probability- CompleteEvery required part of the artifact is present, nothing left blank.
- AccurateThe science and the data are correct and match the evidence.
- Scientific reasoningYou explain your claim with evidence and reasoning (CER), not just an answer.
- Professional communicationClear, organized, labeled, and written the way a clinician or scientist would.
- SubmittedGo to Schoology to turn this in. Submit one PDF. Put your first and last name in the document header. Name the file: FirstName LastName - Assignment Title - YYYY-MM-DD.pdf. If you cannot get in, see Mr. Mendoza. Do not skip the work.
- Error analysis and method · counts doubleName a specific limit of the method and how it moved your result, and compare what you predicted to what happened. "Human error" does not count; say what about the procedure or instrument caused it.
This week
My Progress dashboard