AB+-+Barlow+&+Hayes+(1979)


 * **Reference: ** || Barlow, D. H., & Hayes, S. C. (1979). Alternating treatments design: One strategy for comparing the effects of two treatments in a single subject. //Journal of Applied Behavior Analysis, 12//(2), 199-210. doi:10.1901/jaba.1979.12-199 ||
 * **Author's: ** || Barlow, D. H., & Hayes, S. C. ||
 * **Title:** || Alternating treatments design: One strategy for comparing the effects of two treatments in a single subject. ||
 * **Year:** || 1979 ||
 * **Journal: ** || //Journal of Applied Behavior Analysis // ||
 * **Retrieval Information**: ||  http://dx.doi.org/10.1901/jaba.1979.12-199 ||
 * **Bibliography**: ||  ||
 * The authors proposed a new research design they called alternating treatments design which allows for “ the fast alternation of two or more treatments in a single subject ” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 202 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">). This design allows for good internal validity but critics may question its external validity. It is through the repetition of internally valid research on additional groups that external validity is established “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">rather than statistical inference from groups to populations <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 204 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">). Alternate treatments design counterbalance treatments in random ways and can improve internal validity by minimizing sequential confounding, which also allows for statistical analysis. Carry over effects come in two varieties, contrast (the change in “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">behavior in a direction opposite to that expected due to a contrast with another treatment <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 205 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">)) and induction (a “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">positive transfer between treatments with the behavior during one treatment more closely approximating the behavior during a second treatment than would occur if the treatments were applied individually <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 205 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">)). Alternate treatment designs are used when comparing treatment to no treatment, and to compare two distinct treatments. Alternate treatment designs have the advantages of (a) not requiring a withdrawal of treatment, (b) “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">comparison can be made more quickly than in a withdrawal design <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 207 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">), and (c) the possibility that a formal baseline does not have to be conducted. Disadvantages to the alternate treatment design are multiple treatment interference, and it is “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">more cumbersome to arrange than the withdrawal design <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 208 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">), meaning that potential confounding variables need to be counterbalanced. ||
 * **<span style="font-family: 'Times New Roman',Times,serif; font-size: 130%;">Additional References: ** ||  ||
 * N/A ||
 * <span style="font-family: 'Times New Roman',Times,serif; font-size: 130%;">**Retrieval Information**: || <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;"> http://dx.doi.org/10.1901/jaba.1979.12-199 ||
 * <span style="font-family: 'Times New Roman',Times,serif; font-size: 130%;">**Bibliography**: ||  ||
 * <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">The authors proposed a new research design they called alternating treatments design which allows for “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">the fast alternation of two or more treatments in a single subject <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 202 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">). This design allows for good internal validity but critics may question its external validity. It is through the repetition of internally valid research on additional groups that external validity is established “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">rather than statistical inference from groups to populations <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 204 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">). Alternate treatments design counterbalance treatments in random ways and can improve internal validity by minimizing sequential confounding, which also allows for statistical analysis. Carry over effects come in two varieties, contrast (the change in “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">behavior in a direction opposite to that expected due to a contrast with another treatment <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 205 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">)) and induction (a “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">positive transfer between treatments with the behavior during one treatment more closely approximating the behavior during a second treatment than would occur if the treatments were applied individually <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 205 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">)). Alternate treatment designs are used when comparing treatment to no treatment, and to compare two distinct treatments. Alternate treatment designs have the advantages of (a) not requiring a withdrawal of treatment, (b) “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">comparison can be made more quickly than in a withdrawal design <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 207 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">), and (c) the possibility that a formal baseline does not have to be conducted. Disadvantages to the alternate treatment design are multiple treatment interference, and it is “ <span style="color: #0000ff; font-family: 'Times New Roman',Times,serif; font-size: 120%;">more cumbersome to arrange than the withdrawal design <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">” ( <span style="font-family: 'Times New Roman',Times,serif; font-size: 90%;">p. 208 <span style="font-family: 'Times New Roman',Times,serif; font-size: 120%;">), meaning that potential confounding variables need to be counterbalanced. ||
 * **<span style="font-family: 'Times New Roman',Times,serif; font-size: 130%;">Additional References: ** ||  ||
 * N/A ||
 * **<span style="font-family: 'Times New Roman',Times,serif; font-size: 130%;">Additional References: ** ||  ||
 * N/A ||