Non-parametric statistics tests : Beginner to Advanced level

Review core hypothesis testing concepts, define the alternate hypothesis, errors, p-value, and six steps; compare non parametric and parametric testing, and discuss advantages, disadvantages, and applications.

Learn to apply non parametric hypothesis testing when data are not normally distributed, assess normality, and use distribution-free alternatives like Kruskal-Wallis for ordinal or non-normal data.

Compare parametric and non-parametric hypothesis testing by outlining six essential factors, including definitions, data types, central tendency, power, outliers, and applicability.

Explore seven types of non parametric hypothesis tests in detail, comparing traditional critical-value methods with p-value approaches, and practice practical examples to apply both methods.

Explore the one-sample sign test, a nonparametric alternative for testing a population median against a target value. Learn the assumptions, six-step procedure, and interpretation through a supermarket example.

Perform a one-sample sign test in Minitab to assess whether the population median chromium content in stainless steel equals 18 percent, with normality checks, outlier consideration, and 5% significance.

Explore the one sample Wilcoxon test, a nonparametric alternative using ranks to compare a population median to a target value. Learn six steps, assumptions, and a practical Six Sigma example.

Apply a one-sample wilcoxon test in minitab to assess whether a median reaction time equals 12 minutes, after confirming non-normal data and interpreting a p-value of 0.227.

Apply the Wilcoxon signed rank test to paired data by computing differences, ranking absolute differences (averaging ties), and comparing the test statistic to the critical value at 5% significance.

Apply the Wilcoxon signed rank test to paired before and after data in Minitab, using differences to test if the population median differs from zero at 95% confidence.

The Mann-Whitney test, a non-parametric test, compares the medians of two independent samples using ranks; learn its six-step procedure and how to perform it manually and with an app.

Learn to perform a two-sample nonparametric Mann-Whitney test in Minitab to compare the durability medians of two paint brands, with normality checks and 5% significance.

Learn Mood's median test for comparing three or more groups using nonparametric methods. Perform the test manually and with software, build a contingency table, compute observed and expected frequencies, and interpret the chi-square result to decide if group medians differ.

Compare medians of unoccupied beds across three hospitals with Kruskal-Wallis in Minitab. Check normality by group, stack data into response and factor columns, and interpret p-value and mean ranks.

Explore Friedman's nonparametric hypothesis test as an alternative to ANOVA for randomized block design, using ranks to compare treatment effects across blocks.

Apply Friedman nonparametric test on randomized block data to compare advertising types: direct mail, newspaper, and magazine, using Minitab, interpreting p-values and median ranks to identify newspaper as most effective.

Boosts your grasp of non parametric hypothesis testing for lean six sigma certification exams through practice questions, study materials, and 24/7 doubt solving support.