Statistical approaches to trial durations in episodic affective illness

Robert M. Post, Todd L'Herrou, David A. Luckenbaugh, Mark A Frye, Gabriele S. Leverich, Kirstin Mikalauskas

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

In light of the high variability in illness characteristics and patterns among patients with bipolar illness, parallel group designs present severe methodologic difficulties. Crossover, off-on-off-on (B-A-B-A), and other individualized designs may be a useful substitute, but no consensus exists about how to estimate the individual trial durations required in these instances. Several methods for determining optimum trial lengths in crossover designs are presented, illustrated, and discussed. These include: chi-square (χ2) for the expected versus observed number of either episodes or days well; exceeding two standard deviations for average duration of episodes or euthymic intervals; or the Sequential Probability Ratio Test (SPRT), which detects when mean values differ from prior statistical expectations. Each method was applied to three demonstration cases using data from actual clinical trials of three patients with different patterns of recurrent affective illness. Each method detected changes in illness severity, although different tests appeared to be sensitive to differing cycle patterns in the patients illustrated. We suggest that these types of analyses and others can be used as indicator statistics to augment global impressions and clinical judgment, and to assist in determining individualized trial durations, both in formal clinical trials and in clinical treatment settings. Once individual responsivity is confirmed with an appropriate interplay of trial design and statistical analysis, the percentage response in a given population can then be compared to other agents or in other populations. Moreover, meta-analytic techniques based on addition of z scores from individuals' effect sizes can then be used to assess overall significance of a drug effect in a given population or subpopulation. The need for further development of appropriate and alternate study designs and analysis methods for bipolar illness is highlighted. Approaches to estimating required trial durations in individuals with different cycle frequencies in crossover and B- A-B-A designs constitute one element of that exploration.

Original languageEnglish (US)
Pages (from-to)71-87
Number of pages17
JournalPsychiatry Research
Volume78
Issue number1-2
DOIs
StatePublished - Mar 20 1998
Externally publishedYes

Fingerprint

Clinical Trials
Population
Cross-Over Studies
Consensus
Pharmaceutical Preparations
Therapeutics

Keywords

  • Bipolar disorder
  • Psychopharmacology
  • Research design
  • Statistics

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry
  • Psychology(all)

Cite this

Post, R. M., L'Herrou, T., Luckenbaugh, D. A., Frye, M. A., Leverich, G. S., & Mikalauskas, K. (1998). Statistical approaches to trial durations in episodic affective illness. Psychiatry Research, 78(1-2), 71-87. https://doi.org/10.1016/S0165-1781(97)00144-3

Statistical approaches to trial durations in episodic affective illness. / Post, Robert M.; L'Herrou, Todd; Luckenbaugh, David A.; Frye, Mark A; Leverich, Gabriele S.; Mikalauskas, Kirstin.

In: Psychiatry Research, Vol. 78, No. 1-2, 20.03.1998, p. 71-87.

Research output: Contribution to journalArticle

Post, RM, L'Herrou, T, Luckenbaugh, DA, Frye, MA, Leverich, GS & Mikalauskas, K 1998, 'Statistical approaches to trial durations in episodic affective illness', Psychiatry Research, vol. 78, no. 1-2, pp. 71-87. https://doi.org/10.1016/S0165-1781(97)00144-3
Post RM, L'Herrou T, Luckenbaugh DA, Frye MA, Leverich GS, Mikalauskas K. Statistical approaches to trial durations in episodic affective illness. Psychiatry Research. 1998 Mar 20;78(1-2):71-87. https://doi.org/10.1016/S0165-1781(97)00144-3
Post, Robert M. ; L'Herrou, Todd ; Luckenbaugh, David A. ; Frye, Mark A ; Leverich, Gabriele S. ; Mikalauskas, Kirstin. / Statistical approaches to trial durations in episodic affective illness. In: Psychiatry Research. 1998 ; Vol. 78, No. 1-2. pp. 71-87.
@article{be679316558b4f1fa71c1d91c939d6a5,
title = "Statistical approaches to trial durations in episodic affective illness",
abstract = "In light of the high variability in illness characteristics and patterns among patients with bipolar illness, parallel group designs present severe methodologic difficulties. Crossover, off-on-off-on (B-A-B-A), and other individualized designs may be a useful substitute, but no consensus exists about how to estimate the individual trial durations required in these instances. Several methods for determining optimum trial lengths in crossover designs are presented, illustrated, and discussed. These include: chi-square (χ2) for the expected versus observed number of either episodes or days well; exceeding two standard deviations for average duration of episodes or euthymic intervals; or the Sequential Probability Ratio Test (SPRT), which detects when mean values differ from prior statistical expectations. Each method was applied to three demonstration cases using data from actual clinical trials of three patients with different patterns of recurrent affective illness. Each method detected changes in illness severity, although different tests appeared to be sensitive to differing cycle patterns in the patients illustrated. We suggest that these types of analyses and others can be used as indicator statistics to augment global impressions and clinical judgment, and to assist in determining individualized trial durations, both in formal clinical trials and in clinical treatment settings. Once individual responsivity is confirmed with an appropriate interplay of trial design and statistical analysis, the percentage response in a given population can then be compared to other agents or in other populations. Moreover, meta-analytic techniques based on addition of z scores from individuals' effect sizes can then be used to assess overall significance of a drug effect in a given population or subpopulation. The need for further development of appropriate and alternate study designs and analysis methods for bipolar illness is highlighted. Approaches to estimating required trial durations in individuals with different cycle frequencies in crossover and B- A-B-A designs constitute one element of that exploration.",
keywords = "Bipolar disorder, Psychopharmacology, Research design, Statistics",
author = "Post, {Robert M.} and Todd L'Herrou and Luckenbaugh, {David A.} and Frye, {Mark A} and Leverich, {Gabriele S.} and Kirstin Mikalauskas",
year = "1998",
month = "3",
day = "20",
doi = "10.1016/S0165-1781(97)00144-3",
language = "English (US)",
volume = "78",
pages = "71--87",
journal = "Psychiatry Research",
issn = "0165-1781",
publisher = "Elsevier Ireland Ltd",
number = "1-2",

}

TY - JOUR

T1 - Statistical approaches to trial durations in episodic affective illness

AU - Post, Robert M.

AU - L'Herrou, Todd

AU - Luckenbaugh, David A.

AU - Frye, Mark A

AU - Leverich, Gabriele S.

AU - Mikalauskas, Kirstin

PY - 1998/3/20

Y1 - 1998/3/20

N2 - In light of the high variability in illness characteristics and patterns among patients with bipolar illness, parallel group designs present severe methodologic difficulties. Crossover, off-on-off-on (B-A-B-A), and other individualized designs may be a useful substitute, but no consensus exists about how to estimate the individual trial durations required in these instances. Several methods for determining optimum trial lengths in crossover designs are presented, illustrated, and discussed. These include: chi-square (χ2) for the expected versus observed number of either episodes or days well; exceeding two standard deviations for average duration of episodes or euthymic intervals; or the Sequential Probability Ratio Test (SPRT), which detects when mean values differ from prior statistical expectations. Each method was applied to three demonstration cases using data from actual clinical trials of three patients with different patterns of recurrent affective illness. Each method detected changes in illness severity, although different tests appeared to be sensitive to differing cycle patterns in the patients illustrated. We suggest that these types of analyses and others can be used as indicator statistics to augment global impressions and clinical judgment, and to assist in determining individualized trial durations, both in formal clinical trials and in clinical treatment settings. Once individual responsivity is confirmed with an appropriate interplay of trial design and statistical analysis, the percentage response in a given population can then be compared to other agents or in other populations. Moreover, meta-analytic techniques based on addition of z scores from individuals' effect sizes can then be used to assess overall significance of a drug effect in a given population or subpopulation. The need for further development of appropriate and alternate study designs and analysis methods for bipolar illness is highlighted. Approaches to estimating required trial durations in individuals with different cycle frequencies in crossover and B- A-B-A designs constitute one element of that exploration.

AB - In light of the high variability in illness characteristics and patterns among patients with bipolar illness, parallel group designs present severe methodologic difficulties. Crossover, off-on-off-on (B-A-B-A), and other individualized designs may be a useful substitute, but no consensus exists about how to estimate the individual trial durations required in these instances. Several methods for determining optimum trial lengths in crossover designs are presented, illustrated, and discussed. These include: chi-square (χ2) for the expected versus observed number of either episodes or days well; exceeding two standard deviations for average duration of episodes or euthymic intervals; or the Sequential Probability Ratio Test (SPRT), which detects when mean values differ from prior statistical expectations. Each method was applied to three demonstration cases using data from actual clinical trials of three patients with different patterns of recurrent affective illness. Each method detected changes in illness severity, although different tests appeared to be sensitive to differing cycle patterns in the patients illustrated. We suggest that these types of analyses and others can be used as indicator statistics to augment global impressions and clinical judgment, and to assist in determining individualized trial durations, both in formal clinical trials and in clinical treatment settings. Once individual responsivity is confirmed with an appropriate interplay of trial design and statistical analysis, the percentage response in a given population can then be compared to other agents or in other populations. Moreover, meta-analytic techniques based on addition of z scores from individuals' effect sizes can then be used to assess overall significance of a drug effect in a given population or subpopulation. The need for further development of appropriate and alternate study designs and analysis methods for bipolar illness is highlighted. Approaches to estimating required trial durations in individuals with different cycle frequencies in crossover and B- A-B-A designs constitute one element of that exploration.

KW - Bipolar disorder

KW - Psychopharmacology

KW - Research design

KW - Statistics

UR - http://www.scopus.com/inward/record.url?scp=0032549725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032549725&partnerID=8YFLogxK

U2 - 10.1016/S0165-1781(97)00144-3

DO - 10.1016/S0165-1781(97)00144-3

M3 - Article

C2 - 9579704

AN - SCOPUS:0032549725

VL - 78

SP - 71

EP - 87

JO - Psychiatry Research

JF - Psychiatry Research

SN - 0165-1781

IS - 1-2

ER -