Math 1153 - 1 September 2026 - Section 2.1

Overview

Mike Jacobsen introduces graphical methods for quantitative data in Section 2.1, building a dot plot of age at early-onset dementia diagnosis for 21 people and explaining how to describe its center, spread, left skew, and possible outliers. He distinguishes histograms from categorical bar charts, interprets examples involving synovial-fluid pH and cesium contamination in Pacific bluefin tuna, and shows why defining a study’s population and sample matters for inference.

Key takeaways

For 21 people diagnosed with early-onset dementia, ages ranged from 41 to 61 years and clustered near 58–60, with a tail toward younger ages that makes the distribution left-skewed.
A dot plot places one dot per observation on a number line and stacks repeated values; the age 58 observation occurred most often in the dementia example.
Histograms suit quantitative data because their bars represent numeric intervals; a gap between bars indicates an interval with no observations, unlike the category gaps in a bar chart.
The synovial-fluid pH histogram indicates one subject above pH 7.6 and suggests that most subjects fall roughly between pH 7.0 and 7.5, although binning hides exact measurements.
A study population must include relevant geography and time: the tuna population was Pacific bluefin tuna near California four months after the 2011 Fukushima meltdown, while the sample was the 15 fish caught.
The tuna cesium histogram is bimodal, with clusters around 6–8 and 10–12 becquerels per kilogram; all sampled values exceed the historical 2-becquerel benchmark, but formal inference is needed to establish a population-mean difference.

Chapters

0:00 Class Setup, Quiz Announcement, and Section 2.1 Roadmap

Mike Jacobsen apologizes for a roughly 10-minute delay caused by camera and software problems and plans to restart the camera before future classes.
A quiz is scheduled to be posted Wednesday and discussed Thursday; Jacobsen also previews calculator-based statistics in upcoming quantitative-data sections.
The class shifts from categorical data to numerical measurements for which averages and standard deviations make sense.

2:59 Dot-Plot Example: Ages at Early-Onset Dementia Diagnosis

The data record age at diagnosis in years for a simple random sample of 21 people with early-onset dementia.
Jacobsen explains that quantitative variables have numerical values with meaningful units, unlike categorical responses.
A graph can reveal patterns that are difficult to see in a raw list, including where ages cluster and how widely they vary.

7:38 Choosing a Useful Scale for the Age Dot Plot

The observed ages run from 41 to 61 years, so Jacobsen builds a horizontal axis that contains the full range.
He labels the axis “age at diagnosis in years” to make the variable and unit explicit.
Tick marks every five years—from 40 through 65—provide useful detail without crowding the display with a mark for every year.

12:32 Plotting Individual Ages and Stacking Repeated Values

Each of the 21 observations becomes one dot positioned above its age on the number line.
Repeated ages are stacked vertically; for example, several people in the sample were diagnosed at age 58.
Dots need only be placed in the correct approximate positions, but checking off observations helps avoid missing or duplicating data.

17:10 Reading the Dementia-Age Distribution: Left Skew and Center

The completed display has a main cluster around ages 58–60 and a longer tail toward younger diagnosis ages, so Jacobsen describes it as skewed left.
The minimum and maximum ages—41 and 61 years—communicate the overall spread of diagnosis ages in the sample.
A graph helps estimate the distribution’s center and spread, but a contextual description should refer to ages at early-onset dementia diagnosis.

22:30 Using Mode and Outliers to Describe a Dot Plot

Age 58 is the most frequent diagnosis age in the sample; the most frequently occurring observation is called the mode.
A hypothetical diagnosis age in the late 20s or 30s, far from the main group, would be a potential outlier worth mentioning.
A useful description can note the mode, the range, the direction of skew, or unusual values, while tying claims to the study context.

27:20 Histograms Versus Bar Charts: Synovial-Fluid pH Example

A histogram displays quantitative measurements along a number line and uses bar height to show how many observations fall within each interval.
Unlike a categorical bar chart, histogram bars generally touch; a gap indicates an interval with no observations.
The example measures pH in synovial fluid taken from the knees of people with rheumatoid arthritis, an autoimmune disease affecting joints.

35:46 Reading pH Histogram Frequencies and Typical Ranges

The histogram shows one subject with synovial-fluid pH above 7.6; frequency is read from the height of the corresponding bar.
An interval around pH 7.1–7.25 contains about five observations, illustrating how to translate a bar into a count and range.
A reasonable approximate range for most subjects is pH 7.0–7.5, though grouped histogram bars do not reveal each person’s exact pH.

41:40 Fukushima Cesium Measurements in Pacific Bluefin Tuna

A second example studies cesium-134 and cesium-137 concentrations in a random sample of 15 Pacific bluefin tuna caught off California.
The fish were sampled four months after the 2011 Fukushima nuclear disaster; measurements are in becquerels per kilogram of dry tissue.
Because the concentration has meaningful numerical units and an average is interpretable, the variable is quantitative.

48:19 Defining the Tuna Study’s Population and Sample

The population is Pacific bluefin tuna near the California coast four months after the 2011 Fukushima meltdown—not tuna everywhere or at every time.
The sample is the 15 fish caught for the study; describing the population precisely makes this sample description concise.
Population definitions may depend on geography and time because migratory fish and radioactive contamination levels vary across locations and periods.

52:38 Why Tuna Concentration Data Need a Histogram

A bar chart is inappropriate because the cesium concentrations are quantitative; appropriate displays include a histogram, dot plot, or box plot.
The histogram has two prominent clusters, approximately 6–8 and 10–12 becquerels per kilogram, so the distribution is bimodal.
Descriptions should identify the measured context—radioactivity in tuna tissue—and may also report clusters, range, or other visible features.

57:00 Interpreting the Mean and Previewing TI-84 Statistics

All sampled tuna measurements exceed the historical mean benchmark of 2 becquerels per kilogram; the histogram’s lowest interval begins around 4, while the raw minimum is 4.6.
The sample mean appears to be around 10, providing preliminary evidence that the population mean exceeded 2, but a formal statistical procedure is needed for a firm conclusion.
Upcoming work will calculate sample means and standard deviations with a TI-84 calculator.

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Mike Jacobsen.