Automated hypothesis testing

• US 8,370,107 B2
• Filed: 10/24/2011
• Issued: 02/05/2013
• Est. Priority Date: 04/11/2006
• Status: Expired due to Fees

• Current Assignee: MoreSteam.com LLC
• Original Assignee: Morestream.com LLC
• Inventors: Hathaway, William M.
• Primary Examiner(s): Raymond, Edward
• Application Number:
  US13/279,711
• Publication Number:
  US 20120041715A1
• Time in Patent Office: 470 Days
• Field of Search: 702/179, 702182-185, 702/188
• US Class Current: 702/179
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range

Abstract

A method of automatically applying a hypothesis test to a data set. The method reduces errors made in failing to appreciate predicate assumptions of various statistical tests, and elicits a series of indications from the user regarding characteristics of interest embodied by the data set to select an appropriate statistical test. The system also reduces errors in constructing competing null and alternative hypothesis statements by generating a characterization of the data and defining null and alternative hypotheses according to the indications, selected statistical test, and conventions adopted with respect to the tests. The system also establishes a significance level, calculates the test statistic, and generates an output. The output of the system provides a plain interpretation of the quantitative results in the terms indicated by the user to reduce errors in interpretation of the conclusion.

Claims

1. A non-transitory computer readable medium including computer executable instructions for:

providing on a display a hierarchal map of a decision process for choosing a hypothesis test, to be executed using one or more data sets, from a plurality of hypothesis tests;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a plurality of data types;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a plurality of statistical parameters of interest;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a plurality of sample sizes;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a relationship between a pair of data sets;

receiving from an input device an indication of the data type of the one or more data sets;

receiving from the input device an indication of which of the plurality of statistical parameters of interest is to be tested;

receiving from the input device an indication of the sample size of the one or more data sets;

receiving from the input device an indication of which test of the plurality of tests is to be executed;

receiving from the input device an indication of the relationship of the pair of data sets;

selecting a test to execute based on one or more received indications;

providing on the display a description of the selected test;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a difference of interest;

receiving from the input device an indication of the difference of interest;

receiving from the input device an indication of a location of the data sets in a memory;

providing on the display a plurality of hypotheses based on the data sets;

receiving from the input device an indication of which of the plurality of hypotheses to test;

providing on the display a description, understandable by a user unfamiliar with statistical analysis, of a significance level;

receiving from the input device an indication of the significance level for the selected test;

executing the selected test on the one or more data sets based on indications received;

providing on the display an explanation, understandable by a user unfamiliar with statistical analysis, of the results of executing the test;

providing on the display a summary, understandable by a user unfamiliar with statistical analysis, of the results of executing the test; and

providing on the display one or more graphs, understandable by a user unfamiliar with statistical analysis, of the results of executing the test.

2. The non-transitory computer readable medium of claim 1, wherein the plurality of hypothesis tests includes one or more of a one proportion Z-test, a one proportion binomial test, a two proportion Z-test, a multi proportion Chi-square test, a one mean Z-test, one mean t-test, a two means Z-test, a two sample t-test;

an F-test Anova, a Chi square test, and an F-ratio test.

3. The non-transitory computer readable medium of claim 1, wherein the plurality of data types includes one or more of attribute data and variable data.

4. The non-transitory computer readable medium of claim 1, wherein the plurality of statistical parameters of interest includes one or more of proportion, mean, and variance.

5. The non-transitory computer readable medium of claim 1, wherein the plurality of sample sizes includes one or more of one sample, two samples, and more than two samples.

6. The non-transitory computer readable medium of claim 1, wherein the relationship between the pair of data sets includes one or more of paired and not paired.

7. The non-transitory computer readable medium of claim 1, wherein the plurality of data types includes attribute data and variable data.

8. The non-transitory computer readable medium of claim 1, wherein the plurality of statistical parameters of interest includes proportion, mean, and variance.

9. The non-transitory computer readable medium of claim 1, wherein the plurality of sample sizes includes one sample, two samples, and more than two samples.

10. The non-transitory computer readable medium of claim 1, wherein the relationship between the pair of data sets includes paired and not paired.