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.

Description

FIELD OF THE INVENTION [0001] The present invention relates to methods and systems for designing true experiments. BACKGROUND [0002] Experiments are typically conducted to determine empirically if there are relationships between two or more variables. An experiment typically begins with the formation of one or more hypotheses positing that there is a relationship between one or more independent variables and one or more dependent variables. For example, a researcher at a pharmaceutical company might formulate a hypothesis that the amount of a new drug that patients take will be related to the blood pressure of patients. Independent variables are the variables defined or manipulated by the experimenter during an experiment (e.g., the amount and / or frequency of a drug administered to patients). Dependent variables are the variables posited to depend on the value of the independent variable (e.g., the blood pressure of patients). The experimenter then conducts an experiment to determin...

AI Technical Summary

Benefits of technology

[0010] According to various approaches, the computer may select one or more independent variables of the experiment and / or may select one or more dependent variables. The computer may automatically form one or more control groups of the experiment and / or one or more treatment groups of the experiment, including automatically randomizing the treatment or control groups. In some implementations, the computer may apply techniques (for example, blocking and counterbalancing) to reduce effects of one or more confounding variables.

[0011] According to other approaches, the computer may assist the user in various steps involving the experiment. For example, the computer may assist the user in selection of one or more independent variables and / or one or more dependent variables. The computer may assist the user in forming at least one of a control group and a treatment group. The computer may assist the user in randomizing samples to control and treatment groups and may alternatively or additionally apply techniques to reduce effects of one or more confounding variables of the experiment.

[0015] In some implementations, the system may assist the user in various functions associated with the experiment. In these implementations, the system includes a user interface configured to accept input from a user. The design processor may be configured to assist the user in selection of at least one of an independent variable and a dependent variable of the experiment using the user input. The design processor may be configured to assist the user in selection of at least one of a control group and a treatment group of the experiment based on the user input and may also assist the user in randomizing the groups and in applying blocking to reduce effects of one or more confounding variables of the experiment based on the user input.

Problems solved by technology

Confounding variables make it impossible to know which factor (variable) caused any observed change in the dependent variable(s).

And thus, the existence of confounding variables that are not properly controlled during the experiment renders it impossible to make statistical inferences about causal relationships between the independent and dependent variables.

Quasi-experiments and correlational designs may allow relationships between independent and dependent variables to be established, but it is not possible to determine whether those relationships are causal.

However, the complexity of designing of a true experiment that appropriately controls or eliminates confounding variables may be significant.

Images