β Must-know
Further detail
π A Pareto diagram is a bar graph whose categories are ordered by descending height from left to right.
β Must-know
Quantitative data are summarized with tables or displays because large data sets are difficult to understand without summaries; bar charts and pie charts are better suited to categorical variables.
A stem-and-leaf display separates each observation into a stem and a leaf, lists stems in order, and places each leaf in its stem's row to the right of a bar.
Further detail
For the values 21, 24, 24, 26, 27, 27, 30, 32, 38, and 41, the stem-and-leaf display is 2 | 1 4 4 6 7 7; 3 | 0 2 8; 4 | 1.
For teenage smoking rates in 36 European countries, the histogram bins [10β20), [20β30), [30β40), and [40β50) have frequencies 6, 15, 12, and 3, respectively.
π Histogram bins must have equal widths, but their width and starting point can be adjusted to improve visualization; changing the bins can change the apparent distribution.
β Must-know
Further detail
π When a distribution contains unusual features such as outliers, gaps, or clusters, use the median rather than the mean.
π Formula - The sample mean is , while the population mean is .
For teenage smoking rates in 36 European countries, the mean rate is approximately 27.973%, or about 28%.
For an odd number of observations, the median is the single middle value in the ordered sequence.
For teenage smoking rates in the European-country example, the median is 29%, the average of the 18th and 19th ordered values.
Mean as a balance point; median as the middle value, resistant to extremes.
π Formula - The range is .
π Formula - The sample variance is , while the population variance is .
π Formula - The sample standard deviation is the square root of the sample variance, .
π Formula - The coefficient of variation is calculated as for sample data.
For teenage smoking in Europe, with standard deviation 9.173 and mean 27.973, the coefficient of variation is 0.328, indicating a relatively moderate spread.
The default approximate cutoff for interpreting a coefficient of variation as relatively moderate is 0.4.
β Must-know
π Chebyshevβs Rule states that at least of the data lie within k standard deviations of the mean, for k greater than 1.
π The Empirical Rule applies to unimodal, symmetric, bell-shaped data: approximately 68% lie within one standard deviation, 95% within two, and 99.7% within three standard deviations of the mean.
Further detail
Chebyshevβs Rule guarantees at least three-quarters of the data within two standard deviations of the mean and at least eight-ninths within three standard deviations.
For male students with mean height 171 cm and standard deviation 7 cm, the interval 164β178 cm is one standard deviation from the mean, so approximately 68% fall within it under the Empirical Rule.
Chebyshev applies without a bell shape; the Empirical Rule requires a unimodal, symmetric distribution.
β Must-know
π Formula - For a sample, the z-score is , and for a population it is .
Further detail
A z-score closer to zero indicates a more typical, less unusual data value; a negative z-score indicates a value below the mean, and a positive z-score indicates a value above the mean.
The median is the 50th percentile.
A GMAT score of 560 at the 58th percentile means 58% of test takers scored lower and 42% scored higher.
π Formula - The interquartile range is .
β Must-know
π An observation with an absolute z-score greater than 2 is considered an outlier, and one with an absolute z-score greater than 3 is an extreme outlier.
Further detail
π In a box plot, whiskers extend from the box to the most extreme data values within the fences, while values outside the fences are shown separately as outliers.
Build the box, set the fences, extend whiskers, then mark outliers.
π Mean-based measures, including the mean and standard deviation, are sensitive to extreme values, whereas order-based measures, including the median, quartiles, and IQR, are resistant to them.
π Use the median and IQR instead of the mean and standard deviation when a distribution is not unimodal, is not symmetric, or has outliers, gaps, or clusters.
Sensitivity to Extreme Values
| Measure type | Examples | Response |
|---|---|---|
| Mean-based | Mean, standard deviation | Sensitive to extreme values |
| Order-based | Median, quartiles, IQR | Resistant to extreme values |
Take a 26-question practice quiz on Statistics for Management, with every answer explained.
1. A survey records respondentsβ preferred commute method. Which summary directly reports the number of responses in each method category?
2. A report uses a vertical bar graph to compare percentages across four favorite music genres. Which design follows the conventions for a qualitative-data bar graph?
Memorize the key concepts of Statistics for Management with 80 flashcards.
What does a table of counts list for each category?
The number of observations in it.
How are category counts in a table of counts obtained?
By tallying responses.
What may a table of counts display besides counts?
Percentages.
Upload your class notes and Revizly writes a study guide, a quiz and flashcards in about a minute.
Study guide maker