Session 3

Confounding variables are those variables
known or suspected to exert an
uncontrolled influence on the dependent
variable



The effects of confounding variables must
be evaluated and eliminated to
demonstrate experimental control

Experimental Control

Steadystatestrategy

– Repeated exposure of a given subject to a given
condition while trying to eliminate or control
extraneous influences on behavior & obtaining a
stable pattern of responding before introducing the
next condition

• “Apatternofrespondingthatexhibitsrelatively
little variation in its measured dimensional
quantities over a period of time”

Steady State Strategy &

Repeated measures of behavior in given setting



Requires at least 3 consecutive phases:







– Initial baseline (A)
– Intervention (B)
– Return to baseline (A)

• Withdrawal (Reversal) designs
– A/B/A

– A/B/A/B
– A/B/B+C/B/B+C

Reversal Design

The goal of withdrawal designs is to show a functional
relationship between the target behavior (dependent
variable) and the intervention (independent variable).



This occurs when the experimental control is increased
when the intervention is subsequently withdrawn so that
baseline conditions are again in effect



Experimental control (internal validity) is demonstrated
by showing that the target behavior changes as a
function of the change in condition (phase change)



Particularly well-suited for treatments involving
environmental change strategies

AppliedBenefitsofestablishingabaseline
level of responding



–  To obtain descriptions of antecedent-behavior-
consequent correlations for the planning of an
effective treatment



–  Valuable guidance in setting initial criteria for
reinforcement



–  Baseline data may reveal the behavior targeted for
change does not warrant intervention

Nature & Function of Baseline Data