You get a bonus - 1 coin for daily activity. Now you have 1 coin

58. Statistical decisions and formal planning of an experiment

Lecture



Planning an experiment is organizing its conduct in accordance with the assumed experimental model, while mentally comparing it with a flawless exemplar of its implementation, in order to obtain reliable data.

A distinction is made between formal and substantive planning.

Formal planning is directed at the choice of a scheme, a plan for organizing interactions, and the specification of the minimal effect (in differences of the DV).

The tasks of formal planning:

- ensuring internal validity

- providing the conditions for making decisions about the experimental effect

- applying data-processing schemes that are adequate to the metric of the scales used and to the method of data collection.

In the narrow sense, planning involves two aspects connected with taking into account the subsequent statistical decisions:

1) Discussing the question of how the experimental effect will be assessed. The decision may concern the choice between measures of association and measures of difference. Statistical measures of association can be used to establish covariation between the IV and the DV, while measures of difference can indicate the absence of differences in DV values between different experimental conditions.

2) Establishing the minimal effect sufficient for making a judgment about the obtained differences in the experimental and control conditions, given the observed relationship between changes in the IV and the DV. Mathematical planning. It begins with the choice of a mathematical model and includes the aspects of determining Type I and Type II errors and of rejecting or not rejecting null hypotheses.

Formal planning concludes with the specification of the scheme for manipulating the IV, which determines the methods of data processing. Data processing includes statistical decisions:

Stage 1. Presenting the DV values in a form that makes it possible to use one or another data-processing plan. Here there is a transition from the experimental hypothesis to the statistical hypothesis.

Stage 2. Choosing statistical criteria, taking into account the scale to which the measured variable corresponds. Then there is a reverse move: from the statistical hypothesis to the experimental or counter-hypothesis.

In addition, one must assess the level of significance and the internal and operational validity.

Comments

To leave a comment

If you have any suggestion, idea, thanks or comment, feel free to write. We really value feedback and are glad to hear your opinion.
To reply

Lectures and tutorial on "Experimental psychology"

Terms: Experimental psychology