Skip to main content

Statistical Power

Go Search
Home
About
New Atlas
Atlas, A-Z
Atlas Maps
MPP/MPA Programs
Subjects
Core Topics
Illustrative Courses
Topic Encyclopedia
Concept Dictionary
Competencies
Career Tips
IGOs
Best Practices Project


 
PPGPortal > Home > Concept Dictionary > S > Statistical Power
 
Statistical Power

The probability of statistically rejecting a hypothesis that the true effect is zero when in fact the true effect is not zero.

(Oreopoulos, Phil. Class Lecture. PPG 1004 Quantitative Methods for Policy Analysis. University of Toronto School of Public Policy and Governance.)

---------------------------------


Statistical power is useful in determining the size of the sample you need to conduct and experiment or carry out a survey for detecting the minimal effect that you’d like to be able to distinguish from zero.
     
Statistical Power

The probability of statistically rejecting a hypothesis that the true effect is zero when in fact the true effect is not zero.

(Oreopoulos, Phil. Class Lecture. PPG 1004 Quantitative Methods for Policy Analysis. University of Toronto School of Public Policy and Governance.)

---------------------------------


Statistical power is useful in determining the size of the sample you need to conduct and experiment or carry out a survey for detecting the minimal effect that you’d like to be able to distinguish from zero. For example, if the true effect from a program is to increase college enrolment by 2 percentage points, from a mean of 0.4, I’d like to know how large a random sample needs to be to by 80%. It is likely that my hypothesis test will reject the estimated effect to be zero.

Approved for glossaryposting by Ben Eisen on January 14, 2011


Important Notices
© University of Toronto 2008
School of Public Policy and Governance