Textbook Notes (363,550)
Canada (158,417)
Psychology (9,573)
PSYB01H3 (585)
Chapter 9

Chapter 9

4 Pages
Unlock Document

University of Toronto Scarborough
David Nussbaum

Chapter 9 Small-N and Single-Subject Designs Single-subject designs/single-case designs: N=1; allows a systematic procedure for testing changes in a subjects behaviour Small-N design: N=1-9  Useful in clinical processes of assessment, establishing intervention goals and specific outcomes, providing intervention and evaluating progress Foundation of Small-N Designs o Small-N design: in-depth study of a single or few subjects under tightly controlled experimental conditions in which the independent variable(s) is repeatedly manipulated over successive trails or conditions and in which the dependent variable(s) is repeatedly measured o Four components Repeated measurement of dependent variable Baseline phase Treatment phase(s), with all subjects exposed to each phase Graphic display, perhaps supplemented by statistical analysis Repeated Measurement o Must be able to measure subjects status on target problems at regular intervals usually repeatedly both before and during intervention o If unable to do it prior to intervention may still be able to construct preintervention measures by using data already collected or by asking about past experiences Baseline Phase o Baseline phase (A): represents the period in which the intervention to be evaluated is not offered to the subject (control group) ; several measures of DV are taken (increases internal validity) o Patterns  Stable line: line that is relatively flat with little variability in scores; desirable as easy to detect changes  Different Baseline Patterns  Trend: either increasing or decreasing during baseline period  Linear: increasing or decreasing at a constant rate  Curvilinear: rate of change is accelerating over time  Cyclic: regular increases and decreases  No Pattern  Reasons for variability  Lack of reliability of measurement; look for alternative measure  Lack of consistency in measurement  Lack of consistency in life of client  When have a pattern can predict scores in the future  More data points more certain of the pattern; need 3 consecutive measures that fall in some pattern to have confidence in shape Internal Validity o Repeated measurement controls threats to internal validity of problems of maturation, instrumentation, statistical regression, and testing o These threats are problematic when baseline data is reconstructed from existing data or memory o Stable line: threats can be ruled out o Trend: difficult to rule out some threats  Maturation: would expect linear or curvilinear not horizontal; more difficult to demonstrate effectiveness of intervention  Statistical regression and testing effects: initial impact in baseline measures; high score lower in second measure but will level out to stable pattern with enough measures  External event: repeated measures cannot control for this ; longer time between measures greater possibility of external event Treatment Phase o Treatment phase (B): time period during which the intervention is implemented; repeated measurements; recommended to be same length as baseline; measures are compared with baseline Graphing o Y axis: scores of dependent variable; x axis time Measuring Targets of Intervention o Target measures can be measured simultaneously or sequentially o Four ways to characterize measures of behaviours, status or functioning  Frequency: count; useful for targets that happen regularly but too much that its uncountable  Duration: length of time an event or some symptoms lasts ; measured for each occurrence; need operational definition for beginning and end  Interval: length of time between events; also need clear definitions; not good for events that occur frequently unless point of intervention is to delay onset  Magnitude: intensity of particular behaviour or state; scale o Important who conduct the measurement o Reliability and validity of tests should be tested on subjects of same age gender and ethnicity as focus client o Want nonreactive measures: measures should not influence the responses people provide o Measurement must be cheap, easy, and not take up too much time as it has to be repeated o Must be sensitive enough to detect changes Analyzing Small-N and Single-Subject Designs o Visual inspection o Statistical approach: two-standard deviation-band, chi-square analysis or time series o Practical (or clinical) significance: has the intervention made a meaningful difference in the well-being of the subject  Principles to reduce uncertainty  Setting criteria: establish with the client or community the criteria for success; if intervention reaches this it is successful  Cut-off scores: whether intervention has reduced problem to level below a clinical cut off score  Costs and benefits: weigh costs and benef
More Less

Related notes for PSYB01H3

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.