Hypothesis Testing Cheat Sheet

Key Concepts How to Conduct a Hypothesis Test

◊ Hypothesis testing uses statistical tests to determine if a hypothesis is true. Steps to Follow
1. Define the null and alternative hypothesis.
◊ The null hypothesis, H0, is the statement that there IS NO statistically
significant difference or relationship between variables. 2. Conduct the test.
3. Using data from the test:
◊ Any differences that are observed are due to chance. It is a statement of “no
• Calculate the test statistic (i.e. F) and the critical value (i.e. F crit).
effect” or “no difference.” It is the hypothesis which a researcher tries to
disprove, reject or nullify. • Calculate a p value and compare it to a significance level (α) or
confidence level (1-α). For example, if the significance level = 5%,
◊ The alternative hypothesis, H1 or Ha, is the statement created by research- then the confidence level = 95%.
ers when they speculate upon the outcome of a research or experiment. 4. Interpret the results to accept or reject the null hypothesis.
◊ The alternative hypothesis states that there IS a statistically significant
difference or relationship between variables.
Interpreting the Results
Test Method Compare Result
◊ The alternative hypothesis is what the researcher really thinks is the cause of Classical test statistic > critical value Reject the null hypothesis
a difference. For example, they may be testing the effects of a new drug. (i.e. F > F crit)
Classical test statistic < critical value Cannot reject the null hypothesis
How Does Hypothesis Testing Improve Products & Processes? (i.e. F < F crit) (Accept the null hypothesis)
Hypothesis testing can be used in business operations as well. Tests can help identify
differences between machines, formulas, raw materials, medications, etc. Without p value p value < α Reject the null hypothesis
such testing, employees may change the product or process causing more variation. p value p value > α Cannot reject the null hypothesis
Hypothesis tests enable data driven decisions. (Accept the null hypothesis)

Three Hypothesis Testing Methods

Translating Stat Speak to English
1. Classical: Compare a test statistic to a critical value.
2. p value: Probability of a test statistic being contrary to the null hypothesis. Null Hypothesis: means or variances are not significantly different.
3. Confidence Interval: Is the test statistic between or outside of the confi- Reject the Null Hypothesis Cannot Reject the Null Hypothesis
dence interval. (Accept the Null Hypothesis)
p value < α p value > α
Type I and Type II Errors
Type I error - Reject a null hypothesis that is true (Producer’s Risk) Means or Variances are different Means or Variances are the same
Means or Variances are not the Means or Variances are not different
Type II error - Not reject a null hypothesis that is false (Consumer’s Risk)
same
© 2022 KnowWare International Inc.
Download 30-Day Trial at: www.qimacros.com 2696 S. Colorado Blvd., Ste. 555
Denver, CO 80222
rev 2-2022 888-468-1537 or 303-756-9144
 Hypothesis Testing Cheat Sheet
Examples of Statistical Tests included in QI Macros for Excel
Test of Means Test of Variances Test of Relationships And More

ANOVA f test Chi-square AQL Sampling Tables

t tests Levenes test Descriptive Statistics Normality Test
z test Multiple Regression Analysis Sample Size Calculator

Advantages of Using QI Macros Example of QI Macros Results

• Just select your data and then the test you want from QI Macros menu.
• Performs all of the calculations and interprets the results for you.
(i.e. Reject null hypothesis because p < α, means are different)
• Draws a box plot or other chart to better explain the results.
• Compatible with PC and Mac. Excel 2013-2021 and Office 365.
• Reduce risk of manual calculations or your own Excel formulas.
• Save Time!
Not Sure Which
Statistical Test to Run?
QI Macros Stat Wizard
will analyze your data and
run the correct tests for you.

© 2022 KnowWare International Inc.

Download 30-Day Trial at: www.qimacros.com 2696 S. Colorado Blvd., Ste. 555
Denver, CO 80222
rev 2-2022 888-468-1537 or 303-756-9144