Statistics with StatCrunch by the Math Sorcerer

Create a frequency table with four classes by calculating class width from max and min, applying the rounding rule, and building the frequency distribution.

Learn to construct a frequency distribution for stroke-age data in statistics with StatCrunch by calculating an eight-class width, rounding up to five, and counting frequencies to 34.

Combine the frequencies to find the total number of individuals, here 53, across service time categories. Explain that exact values cannot be identified because data lie within class limits.

Compute the relative frequencies from a five-class grade table by summing the counts to 39 and dividing each count by 39, rounding to two decimals (0.08, 0.31, 0.44, 0.10, 0.08).

Identify lower and upper class limits, compute class width, determine class midpoints and boundaries, interpret the frequency table, and total the frequencies to count individuals.

Compute lower and upper class limits from a frequency table, determine class width and midpoints, then establish class boundaries and count individuals for a histogram.

Assess whether the frequency distribution meets strict normal criteria by small–big–small pattern and symmetry; the temperature frequencies do not form a bell-shaped, balanced distribution, so it is not normal.

Assess whether a frequency distribution is normal by identifying a bell-shaped, symmetric pattern in the class frequencies 1, 3, 8, 15, 8, 3, 1 across temperature classes 40–44 and 45–49.

Construct a BMI frequency distribution using class intervals with a lower limit of 15 and a width of 6, counting observations to confirm the total is twenty.

Learn to build a cumulative frequency table by summing class frequencies; values progress from 28 to 61 to 74 to 77, 81, 82, and 83, illustrating the running total.

Define an outlier as a sample value far from the majority, and learn that detecting outliers is a key area of research with real-world usefulness.

Construct a relative frequency distribution from a cigarette tar study, comparing non-filtered and filtered data, filling zero frequencies, computing totals, converting to percentages, and interpreting that filters reduce tar exposure.

Compute the mean and standard deviation from a frequency table by deriving class midpoints, using the class width, and inputting data into a custom stat calculator.

Compute midpoints from the frequency table to form data, enter them into stat crunch, select custom, and compute the mean (37.5) and standard deviation (5.5).

Interpret the histogram by summing bar heights to count the math team members, showing that the total is 13.

Identify the class width as 20 from the histogram and estimate the first class limits as 105 to 125.

Learn to construct a histogram from a frequency distribution of earthquake magnitudes and identify skewness, recognizing a right-skewed distribution with a longer right tail.

Analyze a frequency distribution of low temperatures over a 31-day month to build a histogram and assess approximate normality; identify a bell-shaped, approximately normal data pattern.

Explore how histograms use class frequencies to visualize distributions, interpret shapes, and identify normal versus skewed distributions with bell-shaped and tail-left/right patterns.

Learn to create a pie chart in StatCrunch by selecting flavors and votes, then customize the title and compute the chart from a sample data set.

Create a stem plot, also called a stem-and-leaf display, in StatCrunch by selecting graph stem and leaf, choosing var 1, and clicking compute.

Learn how to create a Pareto chart in StatCrunch by using a bar plot with summary, ordering counts descending, and interpreting vote data for musicians.

Learn to create a scatter plot in StatCrunch by choosing age as the x column and vocabulary size as the y column, then compute to show vocabulary grows with age.

Construct a stem and leaf plot from the test scores by hand and with stack crunch, identify stems and leaves, and interpret the distribution as roughly normal.

Using data from 400 subjects, construct a burrito (pareto) chart to rank job sources in decreasing order, with executive search firms as the top source.

Identify how a dot plot represents each data value as a point. Explain why starting axes at zero avoids non-zero axis distortions in graphs, especially bar graphs.

Explore the four measures of center — mode, median, mean, and midrange — with examples of qualitative data, ordered datasets, and practical software use.

Compute the mean, median, and mode from jersey-number data using stat summary columns in StatCrunch. Note that jersey numbers are nominal data, so these statistics may be meaningless.

Learn how to compute mean, median, mode, and midrange of celebrity net worth using StatCrunch, interpret results for population insight, and assess precision.

Compare male and female pulse rates by computing means and medians in StatCrunch, selecting data with the stat summary command, and noting that females show higher values.

Learn to find the mode in StatCrunch by using stat summary stats, selecting var 1, and computing to reveal the mode. If no unique mode appears, adjust data and recheck.

Explore measures of center using StatCrunch to compute mean, mid-range, median, and mode from the top 10 college tuitions, and interpret what this sample reveals about national tuition.

Explore the range, variance, standard deviation, and the coefficient of variation to understand data variation, with software-assisted calculations and practical examples like math versus English grades.

Master universal statistics notation, including the sample mean x-bar, population mean mu, and the standard deviation and variance symbols s, s^2, sigma, and sigma^2.

Identify the symbols for standard deviations and variances: use s for the sample standard deviation, sigma for the population standard deviation, and square them for the variances.

Use StatCrunch to compute range, sample standard deviation, and sample variance from eleven randomly selected jersey numbers, then interpret nominal data as meaningless for these statistics.

Learn how to compute mean, variance, and standard deviation in StatCrunch by selecting a data column and using stat summary stats columns.

Compute the coefficient of variation by dividing the standard deviation by the mean and multiplying by 100; compare body weights and heights to see which has more variation.

Compare waiting times at two banks using the coefficient of variation in StatCrunch; Bank B shows far greater variation than Bank A, with about 6.5% vs 24.8%.

Compute z scores as (x minus mean) divided by standard deviation to measure how many standard deviations x is from the mean; |z|>2 is unusual.

Apply formula x = x̄ + s z to recover x from mean, standard deviation, and z-score; x̄ = 2, s = 5, z = 3 gives x = 17.

Calculate z scores for Theo and Mr. X using the sample mean and standard deviation, interpret them as below-average performance, and identify unusually low scores beyond two standard deviations.

Compare z-scores to see how far a test grade lies above the mean. A z-score of 2 is two standard deviations above the mean.

Compute z-scores for heights using z = (x−μ)/σ to compare tallest (242 cm) and shortest (85.8 cm) men, showing the shortest has the more extreme score.

Construct a box plot from 30 newborn weights in statcrunch, identify the five numbers summary and the iqr, uncheck fences, draw the box horizontally, compute, and choose the correct option.

Explore a boxplot and five-number summary of male heights, revealing min, first quartile, median, third quartile, and max, with 25–75 percent data distribution.

Find percentiles in StatCrunch by entering numbers in a column and selecting var 1. Type percentiles as comma separated values, e.g., 42, 54, 89, and click compute for the results.

Compute the 90th percentile in StatCrunch by loading data, selecting stat summary stats columns, choosing var 1, entering 90 for percentiles, and clicking compute to get 13.55.

Compute the 25th percentile (Q1) in StatCrunch by selecting the data and using stat summary stats, then entering 25 and viewing the default Q1 display; the result is 0.7.

Explore z-scores as standardized deviations from the mean, identify unusual values beyond -2 or 2, and distinguish the five-number summary min, Q1, Q2 (median), Q3, max from the mean.

Define probability as a number between 0 and 1, inclusive, describing how likely events are to occur, with 1 certain, 0 impossible, and percentages convert to decimals and vice versa.

Explore three ways to generate probabilities: relative frequency approximation, classical probability, and subjective probability. Illustrate with a tooth fairy survey and a coin flip.

Learn how to compute a probability’s complement by subtracting P(A) from 1, identifying the complement of A as all outcomes where A does not occur, yielding 0.996.

Identify values that cannot be probabilities by ensuring they lie between 0 and 1 inclusive; For example, 1.55, 1.4, and 5/3 are invalid, while three fifths and 0.6 are valid.

Calculate the probability of selecting a defective DVR from 50 items, using 18 defects to yield a 36 percent chance.

Assess subjective probability by judging whether 3 girls out of 1,900 births appears significantly low, illustrating how observed counts inform significance judgments in statistics.

Compute the false positive probability in a drug test by dividing 19 by 106, yielding about 0.179, indicating about an 18 percent chance of a false positive.

Compute the probability a subject did not lie in a polygraph test using a 2x2 table of positive and negative results, totaling 99 outcomes with 44 not lying.

Compute the probability of a girl born by dividing the number of girls (274) by the total babies (568), yielding 0.482, and conclude the technique is not effective.

Estimate the probability of a green offspring by dividing green outcomes by total outcomes, using 45 green out of 457, to three decimals, and compare to 0.75 within 5 percent.

Explore classical probability with equally likely outcomes, such as heads or tails and a six‑sided die, and show how relative frequency approaches the actual probability in the long run.

Learn to compute probabilities with the complement rule by converting 75 percent belief to 0.75 and using 1 minus that value to get 0.25 for not believing.

Calculate the probability that a drive-thru order is not accurate by summing not accurate orders to 139 and total orders to 1083, then form the fraction 139/1083 (approximately 0.128).