THE VR SCHOOL
  • Schools & Districts
    • License the academy
    • Free program for your students
    • Request a demo
  • Catalog
    • AI & Data
    • Cybersecurity & Web
    • Programming
    • Health Science
    • All Guilds
    • All courses
  • Families
  • Accreditation
  • Log In
  • Request a demo
  • Home
  • Courses

RLP Statistics A — Exploring Data, Study Design and Probability

Curriculum

  • 4 Sections
  • 20 Lessons
  • 10 Weeks
Expand all sectionsCollapse all sections
  • Unit 1: Exploring One-Variable Data
    5
    • 1.1
      Distributions and the Statistical Process
      50 mins
    • 1.2
      Measuring Center and Spread
      50 mins
    • 1.3
      Comparing Distributions Across Missouri
      50 mins
    • 1.4
      Standardizing, Transforming and Reporting
      50 mins
    • 1.5
      Performance Task — Climate Station Profile
      150 mins
  • Unit 2: Two-Variable Data and Regression
    5
    • 2.1
      Scatterplots and Correlation
      50 mins
    • 2.2
      Least-Squares Regression
      50 mins
    • 2.3
      Residuals, Influence and Causation
      50 mins
    • 2.4
      Exponential Models and the Limits of Extrapolation
      50 mins
    • 2.5
      Performance Task — Bivariate Investigation Report
      150 mins
  • Unit 3: Designing Studies: Samples and Experiments
    5
    • 3.1
      Populations, Samples and Bias
      50 mins
    • 3.2
      Simulating Sampling Variability and the Margin of Error
      50 mins
    • 3.3
      Experiments, Observational Studies and Confounding
      50 mins
    • 3.4
      Comparing Treatments with a Randomization Test
      50 mins
    • 3.5
      Performance Task — Design, Run and Report a Study
      150 mins
  • Unit 4: Probability, Random Variables and the Binomial Model
    5
    • 4.1
      Probability Rules and Two-Way Tables
      50 mins
    • 4.2
      The Multiplication Rule, Trees and Counting
      50 mins
    • 4.3
      Random Variables, Expected Value and Variance
      50 mins
    • 4.4
      The Binomial Model
      50 mins
    • 4.5
      Performance Task — Expected-Value Decision Analysis
      150 mins

Standardizing, Transforming and Reporting

Unit 1  ·  Modeling & Reporting Workshop  ·  Lesson 4 of 20

Standardizing, Transforming and Reporting

A1.DS.A.2RLP-STATSA
Two rain gauges compare highlighted wet and dry observations by distance from their different means.
By the end of this lesson I can…

use z-scores to compare values from different distributions, predict how changing units affects center and spread, and organize a statistical report.

Instruction

Comparing across distributions. Which was more extreme: St. Louis receiving 61.28 inches in 2015, or Kansas City receiving only 22.31 inches in 2012? The raw numbers cannot answer, because the two stations have different typical amounts and spreads. A z-score measures how many standard deviations a value lies from its mean:

z = (x − x̄) / s

Using the 1973-2024 summaries from Lesson 1.3, for St. Louis 2015: z = (61.28 − 41.04) / 8.40 ≈ 2.41. For Kansas City 2012: z = (22.31 − 38.72) / 8.33 ≈ −1.97. The St. Louis wet year was further from its station’s mean, in the wet direction, than the Kansas City dry year was in the dry direction. Springfield’s wettest year (1990, 63.20 in) gives z ≈ 2.26, and Columbia’s driest (1980, 23.68 in) gives z ≈ −2.13. A z-score has no units, which is exactly why it allows comparison. A z-score also depends on the reference period: measured against all 75 years of St. Louis data (mean 38.81, SD 8.42), the same 2015 total scores z ≈ 2.67.

Be careful: a z-score says how far, not how rare. How rare a value of z = 2.41 is depends on the shape of the distribution, which is what the normal model in Statistics B addresses. At these four stations the wettest years sit between 1.99 and 2.56 standard deviations above the mean and the driest between 1.97 and 2.24 below it, about equally far on both sides, which fits distributions that are close to symmetric. For strongly skewed data, large positive z-scores are much more common than large negative ones.

Changing units. NOAA publishes data in both Fahrenheit and Celsius. St. Louis’s annual mean temperature over 75 years has mean 56.64°F and SD 1.88°F. What happens in Celsius, where C = (5/9)(F − 32)?

  • Adding or subtracting a constant shifts every value, so it shifts the mean and median by that constant, and leaves the SD and IQR unchanged. Everything moves together, and the distances between values do not change.
  • Multiplying by a constant multiplies the mean, median, SD and IQR by that constant (by its absolute value for spread).

So the Celsius mean is (5/9)(56.64 − 32) ≈ 13.69°C, and the Celsius SD is (5/9)(1.88) ≈ 1.04°C. The subtraction of 32 does not touch the SD. A converted z-score is unchanged, because the shift and the scale cancel.

The statistical report. Every unit in this course ends with a report. Readers need these parts, in this order:

  1. Question. One precise statistical question, naming the variable, the cases and the comparison.
  2. Data. Source (agency, dataset, station IDs, retrieval date), how the data were produced, and known limitations such as missing years, station moves or calendar-year versus water-year totals.
  3. Analysis. Displays on a common scale, with labeled axes and units, and summaries chosen to fit the shape, with the method stated (for example, quartiles by QUARTILE.INC).
  4. Interpretation. An answer to the question in context, with the numbers that support it.
  5. Limitations and next steps. What the data cannot show, and what would be needed to show it.

Evaluating reports (A2.DS.A.7). Apply the same checklist to reports you read. A news story saying “the wettest year on record” should tell you which station, which kind of year (calendar year or water year, which runs from October to September) and compared with what baseline. If it does not, the claim cannot be checked.

📖 Read for this lesson

The reading opens over the lesson; close it to come back to exactly where you were. The checks below draw on it.

  • How Extreme Was That Year? Eight Extremes, Two Temperature Scales and the Water-Year TrapNOAA NCEI Global Summary of the Year (four Missouri stations, 1973-2024; St. Louis 1950-2024) and Global Summary of the Month (St. Louis Lambert, USW00013994, 2013-2024); retrieved November 10, 2026 · about 4 min

    The wettest and driest year at each of the four stations with their z-scores, ten years of St. Louis temperature in both °F and °C, and the calendar-year versus water-year table that supplies a real limitation for your Data section.

Vocabulary in context

  • z-score — The number of standard deviations a value lies above (positive) or below (negative) the mean.
  • linear transformation — Changing every value by x → a + bx, such as converting units; it shifts center by a and scales center and spread by b.
  • water year — The 12 months from October 1 to September 30, used by NOAA and the USGS for precipitation and streamflow so that a single winter is not split across two years.
  • limitation — A feature of the data or method that restricts what conclusions can be drawn.

Formative check

Work through these before moving on. They are not graded — they tell you whether the standard below has landed yet.

Fill in the blank

Converting St. Louis temperatures from °F to °C subtracts 32 and multiplies by 5/9, so the SD of 1.88°F becomes about °C; subtracting 32 changes the SD by .

+50 XP

St. Louis 2015: 61.28 in (mean 41.04, SD 8.40). Kansas City 2012: 22.31 in (mean 38.72, SD 8.33). Which statement is correct?

Compare the absolute values of the z-scores: 2.41 > 1.97.
Myth or Fact?

A report that says ‘the wettest year in decades’ without naming the station, the type of year and the baseline gives enough information to check the claim.

To check the claim you need the location, whether it is a calendar or water year, and the comparison period.

Find the wettest and driest years at your chosen station for the Unit 1 task, and compute their z-scores. Then write the Question and Data sections of your report (about 150 words), including station ID, dataset name, retrieval date and at least one limitation.

0 words
Quick self-check

How confident are you that you can compare values from different distributions with z-scores and predict how unit changes affect summaries?

Not yetVery confident

Practice

Work these on paper or in your notebook, then open Check your answer. Aim for all of Fluency and Application; try at least one Challenge.

Printable version: this unit’s practice workbook (PDF)

Fluency

Build speed and accuracy with the core skill.

  1. St. Louis 2024: annual mean temperature 61.2°F; the station’s 1973-2024 mean is 57.14°F and SD 1.85°F. Find the z-score.
    Check your answer
    Answer: z ≈ 2.20
    (61.2 − 57.14) / 1.85
  2. Kansas City 2012: annual mean temperature 58.7°F; the station’s 1973-2024 mean is 54.68°F and SD 1.70°F. Find the z-score.
    Check your answer
    Answer: z ≈ 2.37
    (58.7 − 54.68) / 1.70
  3. Springfield 2024: annual mean temperature 59.7°F; the station’s 1973-2024 mean is 56.63°F and SD 1.49°F. Find the z-score.
    Check your answer
    Answer: z ≈ 2.06
    (59.7 − 56.63) / 1.49
  4. Columbia 2012: annual mean temperature 59.3°F; the station’s 1973-2024 mean is 54.97°F and SD 1.73°F. Find the z-score.
    Check your answer
    Answer: z ≈ 2.51
    (59.3 − 54.97) / 1.73
  5. Convert Kansas City’s mean annual temperature (54.68°F) and its SD (1.70°F) to Celsius.
    Check your answer
    Answer: Mean ≈ 12.60°C; SD ≈ 0.94°C.
    C = (5/9)(F − 32); the SD is only multiplied by 5/9.
  6. Convert St. Louis’s mean annual precipitation (41.04 in) and SD (8.40 in) to millimeters (1 in = 25.4 mm).
    Check your answer
    Answer: Mean ≈ 1042 mm; SD ≈ 213 mm.
    Multiplying by a constant scales both center and spread.
  7. Every value in a data set is increased by 3. What happens to the mean, median, SD and IQR?
    Check your answer
    Answer: Mean and median increase by 3; SD and IQR are unchanged.

Application

Use the skill in context. Show your reasoning.

  1. Using the four z-scores above, which station-year was the most unusually warm relative to its own station’s record? Answer in a sentence with numbers.
    Check your answer
    Answer: Columbia 2012: z ≈ 2.51, about 2.5 standard deviations above its station’s mean.
    Compare z-scores, not degrees.
  2. A headline says: ‘Record rain soaks St. Louis—wettest year ever!’ List four pieces of information a reader needs to check the claim.
    Check your answer
    Answer: The station (or area), the kind of year (calendar or water year), the period of record used as the baseline, and the data source (with the value itself).
    A2.DS.A.7: which statistic, from what data, compared with what.
  3. A student writes: ‘St. Louis’s 2015 rainfall had z = 2.41, so only 1% of years are that wet.’ What is wrong with the reasoning?
    Check your answer
    Answer: A z-score tells how far a value is from the mean, not how rare it is. Rarity depends on the shape of the distribution and on the data used; here 2 of the 52 years (2015 and 2008) were at least 2 SD above the mean, about 3.8%, not 1%.
    Normal-model percentages come in Statistics B, and only when the shape supports them.

Challenge

Stretch problems. Expect to think before you write.

  1. Prove that a z-score does not change when every value is transformed by y = a + bx with b > 0.
    Check your answer
    Answer: The new mean is a + b·x̄ and the new SD is b·s, so z_new = (a + bx − a − b·x̄)/(b·s) = (x − x̄)/s.
    The shift cancels in the numerator; the scale cancels between numerator and denominator.

Review

Keep earlier skills sharp.

  1. (From Lesson 1.2) For the data 4, 7, 7, 9, 13, find the mean and the sample standard deviation.
    Check your answer
    Answer: Mean 8; s ≈ 3.317.
    Σ(x − x̄)² = 16 + 1 + 1 + 1 + 25 = 44; 44/4 = 11.
  2. (From Lesson 1.1) Which display shows the five-number summary directly?
    Check your answer
    Answer: A box plot.

Missouri Learning Standards — Mathematics (data and probability) addressed: A1.DS.A.2, A1.DS.A.1, A2.DS.A.7, MP.4, MP.6

Instructional focus: Standardized scores, linear transformations and the structure of a statistical report

Reading

How Extreme Was That Year? Eight Extremes, Two Temperature Scales and the Water-Year Trap

NOAA NCEI Global Summary of the Year (four Missouri stations, 1973-2024; St. Louis 1950-2024) and Global Summary of the Month (St. Louis Lambert, USW00013994, 2013-2024); retrieved November 10, 2026 · Public domain (works of the United States government)

Why this reading. The workshop asks you to find the wettest and driest years at a station, compute their z-scores and write the Data section of a report with at least one honest limitation. Here are the eight extremes for the four stations with their z-scores, ten years of St. Louis temperature in both Fahrenheit and Celsius so the unit-change rules can be checked on real numbers, and a limitation that catches rainfall reports often: the calendar year and the water year are not the same year.

Table 1. The wettest and driest year at each station, 1973-2024

Means and sample standard deviations of the 52 calendar-year totals (NOAA Global Summary of the Year; the data are the Lesson 1.3 reading). z = (x − mean) / SD.

StationMean (in)SD (in)Wettest yearzDriest yearz
St. Louis (Lambert)41.048.402015: 61.28+2.411976: 23.48−2.09
Kansas City (International)38.728.331973: 55.31+1.992012: 22.31−1.97
Springfield45.197.961990: 63.20+2.261980: 27.37−2.24
Columbia (Regional)41.328.271993: 62.51+2.561980: 23.68−2.13

Two things to notice. First, the wet and dry extremes sit about equally far from the mean: the wettest-year z-scores run from +1.99 to +2.56 and the driest from −1.97 to −2.24. That fits distributions that are close to symmetric, in contrast to a strongly skewed variable, where the high side runs much farther out. Second, the lesson’s comparison of St. Louis 2015 (z = +2.41) with Kansas City 2012 (z = −1.97) can now be extended: the most extreme dry year at any of the four stations is Springfield’s 1980 (−2.24), shared in date with Columbia’s (−2.13). Against all 75 years of St. Louis data, 2015 scores z = +2.67 and 2008 (57.96 in) scores +2.27.

Table 2. St. Louis annual mean temperature, 2015-2024, in two units

Celsius values are (5/9)(F − 32), shown to two decimals.

Year2015201620172018201920202021202220232024MeanSD
°F58.860.460.257.457.258.259.057.860.461.259.061.418
°C14.8915.7815.6714.1114.0014.5615.0014.3315.7816.2215.030.788

Check the rules: (5/9)(59.06 − 32) = 15.03, and (5/9)(1.418) = 0.788. The subtraction of 32 moved the mean and did nothing to the SD. The z-score of 2024 is (61.2 − 59.06) / 1.418 = +1.51 in either unit; in Celsius it is (16.22 − 15.03) / 0.788 = +1.51. Over all 75 years the same record has mean 56.64°F and SD 1.875°F, which convert to 13.69°C and 1.042°C.

Table 3. Calendar year against water year at St. Louis

Water agencies, NOAA and the USGS often total precipitation and streamflow over a water year, October 1 to September 30, so that one winter is not split across two years. These totals are built from NOAA’s Global Summary of the Month for the same station (retrieved November 10, 2026). The last column is the annual total from the Global Summary of the Year, for comparison.

Water yearWater-year total (in)Calendar-year total from monthly sums (in)GSOY annual (in)
Oct 2014 – Sep 201552.3361.2861.28
Oct 2015 – Sep 201652.6641.4641.46
Oct 2016 – Sep 201738.6136.6936.69
Oct 2017 – Sep 201838.7742.6042.62
Oct 2018 – Sep 201954.6854.0254.02
Oct 2019 – Sep 202050.1650.0150.02
Oct 2020 – Sep 202145.8842.5042.51
Oct 2021 – Sep 202246.6048.9748.96
Oct 2022 – Sep 202335.7933.1633.18
Oct 2023 – Sep 202442.9250.8450.84

Two limitations appear in one table. The water-year total and the calendar-year total for “2015” differ by 8.95 inches (52.33 against 61.28), and for 2016 by 11.20 inches (52.66 against 41.46), because December 2015 alone brought 11.75 inches: it belongs to calendar 2015 but to water year 2016. And the monthly sums disagree with the annual product by 0.01 or 0.02 inch in several years (2018, 2020, 2021, 2022, 2023): NOAA rounds each product separately from the daily data. Neither is an error. Both belong in a Data section.

A claim to check

“2015 was the wettest year St. Louis has had.” On the calendar record in this table (1950-2024), 2015’s 61.28 inches ranks first of 75, 3.32 inches above the next year (2008). But the record begins in 1950, so “ever” is not something this table can support. And on the water-year record for 2015-2024 the two water years that share 2015’s months total 52.33 and 52.66 inches, while the wettest water year of the decade is Oct 2018 – Sep 2019 at 54.68 inches. The claim can only be checked once the station, the kind of year and the baseline are named.

What to do

  1. Compute z-scores for the wettest and driest years at the station you will use in the Unit 1 task (the data are in the Lesson 1.3 and 1.5 readings). Check two of them against Table 1.
  2. Convert one row of the Lesson 1.5 temperature table to Celsius and confirm that the SD scales by 5/9 and the z-scores do not change.
  3. Write the Question and Data sections of your report, about 150 words, naming the dataset, station id, retrieval date and at least one limitation from this reading.

Sources: NOAA NCEI Global Summary of the Year (GSOY), station USW00013994 (St. Louis Lambert International Airport), data service query used here (ncei.noaa.gov); NOAA NCEI Global Summary of the Year (GSOY), station USW00003947 (Kansas City International Airport), data service query used here (ncei.noaa.gov); NOAA NCEI Global Summary of the Year (GSOY), station USW00013995 (Springfield Weather Service Office Airport), data service query used here (ncei.noaa.gov); NOAA NCEI Global Summary of the Year (GSOY), station USW00003945 (Columbia Regional Airport), data service query used here (ncei.noaa.gov); NOAA NCEI Global Summary of the Month (GSOM), station USW00013994, PRCP, data service query used here (ncei.noaa.gov)

Up NextComplete & Continue →

Leave a Reply Cancel reply

Comparing Distributions Across Missouri
Prev
Performance Task — Climate Station Profile
Next

© 2026 The VR School | Career content by Wiley | Powered by Sejal Learning Systems.

Join free · Accreditation · Privacy Policy · Terms of Service

Modal title

Main Content