Business and Management Statistics Using Excel

Explore the relationship between two variables using a scatter plot and a fitted regression line. Learn to read the equation, interpret intercept and slope, and predict costs from sales.

Organize numerical data and visualize distributions in Excel using histograms and pivot tables. Explore a mutual funds data set and 2005 returns to illustrate histogram construction and interpretation.

Learn to analyze data with pivot tables by transforming the mutual funds dataset into rows, columns, and values using a classic layout, counting funds by category and risk.

Explore how pivot tables analyze qualitative fund categories such as large cap, mid cap, and small cap with risk, calculating fractions and percentages of grand total, columns, and rows.

Explore descriptive statistics for mutual fund returns using Excel's data analysis tools, computing mean, median, quartiles, percentiles, variance, covariance, standard deviation, skewness, kurtosis, and range.

Explore descriptive statistics in Excel by computing the median, quartiles, and percentiles from a data set; learn to sort data, rank observations, and verify the median with VLOOKUP and commands.

Explore descriptive measures in Excel: compute median, quartiles, and percentiles, and see how outliers affect the mean but not the median, using lookup techniques.

Explore descriptive statistics by computing the mean (X bar), median, quartiles, and percentiles from scratch, then assess mode and a box and whisker diagram to identify skewness in returns data.

Learn to compute variance and standard deviation from the mean, including squaring deviations and using n-1 for samples, with manual steps and Excel shortcuts.

Explore skewness and kurtosis in descriptive statistics, and learn to use standard deviation and coefficient of variation in Excel to compare risk across distributions.

Compute the correlation coefficient by standardizing covariance with the standard deviations of x and y, and interpret its magnitude and sign to assess linear relationships in sample data.

Explore how the empirical rule links a normal distribution's mean and standard deviation to 68%, 95%, and 99.7% ranges, using a $120 mean and $11 standard deviation for dinner bills.

Standardize data with z-scores for normally distributed variables, using mean 120 and sd 12 to express deviations in standard units and apply the empirical rule of 68% and 95%.

Compute marginal probabilities from the table margins by dividing margin totals (245, 346, 247) by 838, showing the chances of average, high, and low risk funds.

Explore conditional probability by shrinking the sample to a column or row and calculating exact chances from contingency and relative frequency tables.

Compute probability of A or B with P(A) + P(B) − P(A and B). Use high risk vs mid cap and large cap vs low risk as pivot table examples.

Apply Bayes' theorem to flip conditional probabilities and compute the probability of disease given a positive test, using prior 0.03, sensitivity 0.9, and false positive rate 0.02 with contingency table.

Explore the concept of expected value as a weighted average, computing E(x) by summing x times P(x) with unequal probabilities, and using Excel sumproduct for efficiency.

Learn to compute variance as the weighted average of squared deviations from the expected value for discrete random variables, using relative frequencies and the sum-product formula.

Apply the binomial distribution to compute the probability of exactly six bad chips in a sample of 50 with p = 0.05, using factorials in Excel.

Learn to compute binomial probabilities for a sample of 50 defective chips and determine the expected value using Excel's binomial function.

Compute the variance of a binomial distribution from squared deviations around the mean, using Excel’s sumproduct. Verify with the formula n p (1−p) for a 50-trial, 0.05 defect rate.

Explore the binomial distribution by building histograms of probabilities and their cumulative sums, compare manual calculations with Excel's binom dist, and interpret how cumulative probabilities approach one.

Compute binomial probabilities step by step, including P(X=3), P(X>3), and P(X≥5), using discrete and cumulative methods before moving to Poisson.

Verify the Poisson distribution's expected value and variance by computing the sample sum product with lambda set to six, confirming both equal six for the post office patron count.

Apply the Poisson distribution to calculate and interpret probabilities for counts, such as X=4, X≥3, and X<7, using cumulative sums and total probability, and connects to the upcoming normal distribution.

Explore continuous random variables and density functions, focusing on the normal density function with bell-shaped curves parameterized by mu and sigma, showing how mean and spread affect probabilities.

Study the uniform (rectangular) probability distribution, where outcomes from A to B have equal probability, with density height 1/(B−A), area under the density equals one, and mean (A+B)/2.

Explore the uniform distribution with a bank waiting time example; calculate interval probabilities as rectangle areas for 0–120 s, 10–30 s, and 35 s or more, with Excel notes.

Compute the probability that the sample mean from a normal population with mu=28 and standard deviation=5 (n=25) lies between 27.5 and 28.5 using the standard deviation of x-bar = 1.

Show how larger sample sizes tighten the sample-mean distribution, reduce the standard error, and boost the chance that x-bar falls near the mean, such as between 27.5 and 28.5.

Calculate the probability that a sample proportion falls between 0.62 and 0.67 using the population proportion 0.63, sample size 100, and the standard deviation of a proportion.

Compute probabilities for the sample proportion using z values and inverse normal, and determine the 90% symmetric interval and its P-values.

Compute probabilities for sample proportions by standardizing P1 and P2 to Z, test 5% and 95%, and observe how larger n shrinks the standard deviation.

Compute a 95% confidence interval for the average force to break insulators using the t distribution with x bar and its standard error from a 30-sample study, noting normality checks.

Conduct a two-tailed test of the population mean (mu=7500) using n=64; with observed mean 7250, z exceeds 1.96, so reject H0 at 5% significance.

Apply two-tailed hypothesis testing for a population mean using z statistics, p-values, and rejection regions, and interpret how a computed z leads to rejecting the null at 0.05.

Conduct a two-tailed hypothesis test for the population mean with unknown sigma, using the t statistic (df = n−1) from a 27-sample to test mu = 45.

Perform a one-tailed test for the population mean at 1% significance using the t statistic, critical value, and p-value; conclude not to reject H0, supporting mu ≤ 85.5.

Explore one-tailed hypothesis testing of a population proportion with a chrome market-share example. Calculate p-hat and z, compare to 5% significance, and decide whether to reject H0.

Explore one-tailed hypothesis testing of population proportion using the z test, p values, and decision rules to reject or fail to reject H0, comparing sample and population proportions.

Learn to test the equality of two independent population means using a two-sample t test with pooled variance, covering degrees of freedom and decision rules.

This lecture demonstrates a hands-on two-sample t-test for equality of two unknown population means using pooled variance, X-bar and S squared from two samples.

Explore testing the equality of two population means using a two-tailed t test, interpret the p value, and assess normality and small-sample assumptions.

Explore the equality of two population proportions with z tests, the pooled p-bar, and confidence intervals for differences, and compare to the equality of two means before moving to variances.

Learn to test equality of two population variances using the F test: compare sample variances, compute the F statistic, and interpret the F distribution against a two-tailed 5% critical value.

Compute the p value for the F test to assess equality of two population variances. Note the two-tailed p value, degrees of freedom, and normality assumptions behind the test.