Systems and methods for designing experiments

Abstract

Methods and systems for designing an experiment using a computer to determine whether the experiment is a true experiment are described. These approaches allow a user who is unsophisticated in the complexities of true experimental design to design and deploy an experiment that produces substantially confound-free results and can be used to determine and quantify any causal relationship between independent and dependent variables. The computer may select one or more independent and/or dependent variables of the experiment or may assist the user in selection of independent and/or dependent variables. Formation of control and treatment groups, randomization and/or blocking to reduce the effects of confounding variables may be performed by the computer with or without input from the user.

1 . In a digital signage network that presents content on digital signage players according to a schedule, a method for assessing an effect that the content presented has on behavior of viewers of the content, comprising:
 identifying an independent variable associated with an aspect of displaying the content;   identifying a dependent variable that varies with the independent variable and that is associated with the behavior of the viewers of the content;   displaying the content on a plurality of digital signage players of the digital signage network in a manner that varies the independent variable and that is randomized to exclude confounding variables;   collecting information on the dependent variable and analyzing changes in the dependent variable to determine a cause and effect relationship between the independent variable and the dependant variable; and   drawing a statistical inference, from the cause and effect relationship between the independent variable and the dependant variable, of a relationship between the content and the behavior of the viewers of the content.   
     
     
         2 . A method of  claim 1 , further comprising blocking one or more confounding variable. 
     
     
         3 . A method of  claim 1 , further comprising counterbalancing one or more confounding variable. 
     
     
         4 . A method of  claim 1 , wherein the content comprises at least one of graphics, text, video clips, still images, audio clips, and web pages. 
     
     
         5 . A method of  claim 1 , wherein the behavior of viewers comprises at least one of purchasing, eye movements, picking up products, and reduction in way-finding times. 
     
     
         6 . In a digital signage network that presents content on a plurality of players according to a playlist, a method of evaluating the effectiveness of content used to promote sales of a product, comprising:
 selecting test locations in the digital signage network where experimental content and control content will be presented;   generating a playlist for the experimental content;   generating a playlist for the control content;   presenting, on the players of the digital signage network at the test locations, the playlist for the experimental content and the playlist for the control content randomized such that schedule and location confounds are eliminated;   collecting data regarding sales of the product at the test locations;   determining, based on the collected data, if the experimental content is effective at influencing the sales of the product.   
     
     
         7 . A method of  claim 6 , further comprising blocking of the experimental content and the control content. 
     
     
         8 . A method of  claim 6 , further comprising counterbalancing of the experimental content and the control content. 
     
     
         9 . A method of  claim 6 , wherein the experimental content comprises at least one of graphics, text, video clips, still images, audio clips, and web pages.