PSY 380 Topic 1 descriptive statistics exercise example

Introduction to Probability and Statistics Grand Canyon University Free custom sample in 24 to 48h

This PSY 380 Topic 1 sample paper describes how long 15 students took to fall asleep before an exam and shows what the mean conceals. It was written for GCU PSY 380, Introduction to Probability and Statistics, catalog code PSY-380, taken within Grand Canyon University's BS in Psychology. With working shown, the mean is 20.0 minutes, the median 15.0, the sample standard deviation 16.6 and the interquartile range 12. A frequency display reveals a right skew, and Tukey's fence flags 45 and 69 minutes as outliers. Anscombe's quartet explains why the display is not optional, and sleep quality guidance from Ohayon and colleagues gives the two outliers meaning.

CoursePSY 380 Introduction to Probability and Statistics
TopicTopic 1
Paper typeDescriptive statistics exercise
LengthAbout 980 words, 2 pages
FormatAPA 7 student paper
SchoolGrand Canyon University (GCU)
ProgramBS in Psychology
UpdatedOctober 2026

Free sample paper for PSY 380 Topic 1

1

What the Mean Conceals: Describing How Long Fifteen Students Took to Fall Asleep

[Author Name]

College of Humanities and Social Sciences, Grand Canyon University

PSY-380: Introduction to Probability and Statistics

Topic 1 Descriptive Statistics Exercise

[Instructor Name]

[Date]

The organization, setting and figures below are a composite written as a model document. No real employer, client, colleague or patient is described.

What this page is doingThe title states the exercise's central finding. The data set is constructed for coursework; the sources are real.
2

What the Mean Conceals: Describing How Long Fifteen Students Took to Fall Asleep

The Data

Fifteen undergraduate students in a composite sleep study recorded how many minutes it took them to fall asleep on the night before a midterm exam, a measure called sleep onset latency, estimated from a wrist-worn activity monitor. The values, in minutes and sorted from smallest to largest, are: 5, 8, 10, 10, 12, 12, 14, 15, 15, 18, 20, 22, 25, 45 and 69. This exercise computes the summary values, displays the distribution beside them and states what the mean conceals once the shape is visible. Every value is given with its symbol and units, and with enough working to check.

Central Tendency

The sum of the scores is ΣX = 300 minutes, and with n = 15, the mean is M = ΣX / n = 300 / 15 = 20.0 minutes.

The median is the middle score when the data are ordered. With 15 scores, it is the eighth: Mdn = 15.0 minutes.

The mode is the most frequent value. Three values, 10, 12 and 15, each appear twice, so the data have no single mode. Reporting a mode would add little here.

The mean and median separate by 5 minutes. That gap is not resolved by choosing one; it is a finding, explained below.

Variability

The range is the highest score minus the lowest: 69 minus 5 equals 64 minutes.

For the standard deviation, each score's deviation from the mean was squared and summed. The deviations are -15, -12, -10, -10, -8, -8, -6, -5, -5, -2, 0, 2, 5, 25 and 49, and their squares sum to SS = 3,842. The sample variance divides SS by n minus 1: s² = 3,842 / 14 = 274.4 square minutes. The sample standard deviation is its square root, s = 16.6 minutes.

The quartiles summarize the middle of the distribution. The lower quartile, the median of the seven scores below the median, is Q1 = 10 minutes; the upper quartile, the median of the seven scores above it, is Q3 = 22 minutes. The interquartile range, Q3 minus Q1, is IQR = 12 minutes.

The Shape

The distribution is shown beside the summary values, because the shape is the argument.

Table 1

Frequency Distribution of Sleep Onset Latency, n = 15

Minutes to fall asleepNumber of studentsDisplay
0 to 92##
10 to 198########
20 to 293###
30 to 390
40 to 491#
50 to 590
60 to 691#

Most students fell asleep within 10 to 19 minutes, and the scores pile up on the left with a tail running right, a positive skew: a long tail stretches toward high values, produced by two students who took 45 and 69 minutes. Using the rule Tukey (1977) proposed for identifying unusual values, a score counts as an outlier once its distance above the upper quartile exceeds 1.5 IQRs. That threshold is 22 + 1.5 × 12 = 40 minutes, so both 45 and 69 are outliers.

What the Mean Conceals

The mean of 20 minutes is larger than all but three of the fifteen scores. It does not describe a typical student; it is pulled upward by the two long latencies. The median of 15 minutes better describes the typical student, and the gap between the two is itself a sign of right skew. Removing the two outliers, which this exercise does only to show their influence, not to discard them, would give a mean of 186 / 13 = 14.3 minutes, close to the median. The standard deviation of 16.6 minutes is similarly inflated by the tail; the interquartile range of 12 minutes better describes the spread of the middle half.

Anscombe (1973) built four small data sets whose means, variances and correlations matched almost exactly yet whose plots looked nothing alike, which is why the display is not optional. Here, a reader given only the mean and standard deviation might picture a symmetric spread around 20 minutes, with a quarter of students taking over half an hour. The display shows instead a tight cluster with two students far outside it.

Choosing What to Report

Because mean and median separate, both are reported, together with both measures of spread. For a skewed distribution like this one, the median and interquartile range give the better picture of an ordinary student and of the middle half, while the mean and standard deviation are still worth reporting because later analyses, and readers comparing studies, often rely on them. A results sentence in the format psychology uses might read: sleep onset latency was right-skewed (Mdn = 15.0 min, IQR = 12.0; M = 20.0 min, SD = 16.6), with two students above 40 minutes. One sentence thus reports where scores sit, how far they range, which way they lean and which ones stand apart.

What the Results Tell Us About Behavior

The central tendency tells us that the typical student fell asleep in about 15 minutes before the exam. The variability tells us that most students were similar to one another, within a 12-minute middle band. The shape tells us something the summary values hide: two students had a very different night. The two outliers should be examined rather than deleted. They may reflect a measurement problem, such as a monitor worn loosely, or they may be the most important result in the data: students for whom exam stress severely disrupted sleep. Guidance on sleep quality has treated latencies of 30 minutes or less as consistent with good sleep and much longer latencies as a marker of poor sleep (Ohayon et al., 2017). By that standard, thirteen students slept normally and two did not, a pattern the mean of 20 minutes would have hidden entirely.

All values are rounded to one decimal place, following common practice for behavioral data (Gravetter & Wallnau, 2017).

References

Anscombe, F. J. (1973). Graphs in statistical analysis. The American Statistician, 27(1), 17-21. https://doi.org/10.1080/00031305.1973.10478966

Gravetter, F. J., & Wallnau, L. B. (2017). Statistics for the behavioral sciences (10th ed.). Cengage Learning.

Ohayon, M., Wickwire, E. M., Hirshkowitz, M., Albert, S. M., Avidan, A., Daly, F. J., Dauvilliers, Y., Ferri, R., Fung, C., Gozal, D., Hazen, N., Krystal, A., Lichstein, K., Mallampalli, M., Plazzi, G., Rawding, R., Scheer, F. A., Somers, V., & Vitiello, M. V. (2017). National Sleep Foundation's sleep quality recommendations: First report. Sleep Health, 3(1), 6-19. https://doi.org/10.1016/j.sleh.2016.11.006

Tukey, J. W. (1977). Exploratory data analysis. Addison-Wesley.

The PSY-380 Topic 1 assignment instructions

Topic 1 in PSY-380 asks students to compute and interpret descriptive statistics for a small data set. Strong exercises show every value with its symbol, units and enough working to check, and place a display of the distribution beside the summary values rather than in an appendix. Students should describe skew, outliers or clusters in words and connect them to what the measure records about people. Where mean and median separate, both should be reported and the gap explained. Rounding should be consistent, and each result should be followed by a sentence saying what it tells a reader about the behavior that produced the data.

How this PSY 380 Topic 1 example is built

The finished exercise shows the numbers and their meaning in the same document. Every computed value appears with its symbol, its units and enough working for a reader to follow where it came from, since an unexplained figure cannot be checked or given credit. A histogram or equivalent display sits with the summary values rather than in an appendix, because the shape is the argument. Skew, an outlier or a second cluster is described in words and connected to what the measure was recording about people. Where mean and median separate, both are reported and the gap is explained rather than resolved silently. Rounding is consistent throughout. Each result is followed by a sentence saying what it tells anyone about the behavior that produced the data.

PSY 380 Topic 1 rubric: what Excellent looks like

Faculty reward numbers and meaning in the same place. An Excellent exercise computes mean, median, range, sample variance, standard deviation and quartiles with working shown. Credit goes to a frequency display beside the values and to identifying outliers with Tukey's interquartile fence. The rubric values reporting both mean and median, explaining their gap as a sign of skew and showing the outliers' pull without deleting them. Strong exercises cite Anscombe on why displays matter and give a results sentence in psychology's format. Top marks go to connecting two long latencies to sleep quality.

PSY 380 Topic 1 help: mistakes that cost marks

Two different losses operate on this topic. The first is arithmetic: a mean computed on the wrong denominator, a standard deviation taken with the variance formula, or a value reported without units is simply incorrect, and no quality of writing repairs it. The second is silence. Pages of correct output with no interpretation answer half the rubric, because the criteria ask what the numbers show about the behavior, not only what they equal. Reporting a mean for a set with an extreme value, while never mentioning the value, misdescribes the data. Computing a mean on ranked or categorical responses produces a number with no meaning. Missing working also costs, since partial credit needs something to look at.

Get a PSY-380 Topic 1 example written to your instructions

Send the PSY-380 Topic 1 assignment instructions, the rubric posted in your classroom and the data set your section was given. We write a custom example against those criteria, with the working shown, the distribution displayed and every result read back to the question the data were meant to answer, in 24 to 48 hours. The first one is free.

More PSY 380 papers and BS in Psychology samples

PSY 380 Topic 1 questions, answered

Why report the median when the mean is standard?

Because they answer differently when the distribution is not symmetric. One extreme score pulls the mean toward itself and leaves the median where it was, so a large gap between them is a signal about the data rather than a nuisance. Reporting both, and saying which better represents this particular sample, is a judgment the criteria on this topic reward.

Does the display matter if the numbers are right?

It does, and the topic exists partly to show why. Data sets with very different shapes can produce the same mean and standard deviation, so summary values alone cannot distinguish a symmetric set from one with two clusters or a long tail. The graph is what makes the difference visible, and instructors on this topic generally allocate marks to it explicitly.

How much working should I show?

Enough that a reader can follow the route to each number. Where software produced the output, say which procedure was run and paste the relevant portion rather than the whole file. Showing the path matters most when something goes wrong, since a small slip with visible steps can attract partial credit, while a bare wrong figure has nothing to award.

Where can I find a free PSY 380 Topic 1 sample paper?

The descriptive exercise is shown here complete: the data, central tendency, variability, the shape, what the mean conceals, what to report and what the results say about behavior. Share your PSY 380 Topic 1 prompt for a free exercise.

Why is the median the better typical value in PSY 380 Topic 1?

Two long latencies, 45 and 69 minutes, pull the mean up to 20, above all but three scores. The median of 15 sits where most students actually were.