Abstract
Since generalized nonlinear mixed-effects modeling methodology of ordered categorical data became available in the pharmacokinetic/pharmacodynamic (PK/PD) literature over a decade ago, pharmacometricians have been increasingly performing exposure–response analyses of such data to inform drug development. Also, as experiences with and scrutiny of these data have increased, pharmacometricians have noted fewer transitions (or greater correlations) between response values than predicted by the model. In this paper, we build on the latent variable (LV) approach, which is convenient for incorporating pharmacological concepts such as pharmacodynamic onset of drug effect, and present a PK/PD methodology which we term the multivariate latent variable (MLV) approach. This approach uses correlations between the latent residuals (LR) to address extra correlation or a fewer number of transitions, relative to if the LR were independent. Four approximation methods for handling dichotomous MLV data are formulated and then evaluated for accuracy and computation time using simulation studies. Some analytical results for models linear in the subject-specific random effects are also presented, and these provide insight into modeling such repeated measures data. Also, a case study previously analyzed using the LV approach is revisited using one of the MLV approximation methods and the results are discussed. Overall, consideration of the simulation and analytical results lead us to some conclusions we feel are applicable to many of the models and situations frequently encountered in analysis of such data: the MLV approach is a flexible method that can handle many different extra correlated data structures and therefore can more accurately predict the number of transitions between response values; incorrect modeling of the population covariances by implementing an LV model when extra correlation exists is not likely to (and in many cases does not) influence accuracy of the population (marginal) mean predictions; adequate prediction of the population mean probabilities achieves adequate predictions of the population variances, regardless of the correct specification of the population covariances—that is, if the LV model accurately predicts the means in the presence of extra correlation, it will accurately predict the variances; the between subject random effects component to the model describe the marginal covariances in responses—not the marginal variances as with continuous-type data. From these conclusions we make a general statement that it may not be necessary to model the extra correlation in every case using the MLV model, which requires technical implementation with currently available commercially or publically available software. The LV model may be sufficient for answering many of the typical questions arising during drug development. The MLV approach should be considered however if prediction or simulation of individual level data is an objective of the analysis.
Similar content being viewed by others
Notes
This implies that parameterizations with time-changing random effects, such as including an η × time term in the model, not only change the correlation structure, but will exert influence on population mean time profile in much more pronounced fashion than with continuous data.
References
Sheiner LB (1994) A new approach to the analysis of analgesic drug trials, illustrated with bromfenac data. Clin Pharmacol Ther 56:309–322
Sheiner LB, Beal SL, Dunne A (1997) Analysis of nonrandomly censored ordered categorical longitudinal data from analgesic trials. J Am Stat Assoc 92:1235–1244
Hutmacher MM, Krishnaswami S, Kowalski KG (2008) Exposure-response modeling using latent variables for the efficacy of a JAK3 inhibitor administered to rheumatoid arthritis patients. J Pharmacokinet Pharmacodyn 35:139–157
Hu C, Xu Z, Rahman MU, Davis HM, Zhou H (2010) A latent variable approach for modeling categorical endpoints among patients with rheumatoid arthritis treated with golimumab plus methotrexate. J Pharmacokin Pharmacodyn 37:309–321
Lacroix BD, Lovern MR, Stockis A, Sargentini-Maier ML, Karlsson MO, Friberg LE (2009) A pharmacodynamic Markov mixed-effects model for determining the effect of exposure to certolizumab pegol on the ACR20. Clin Pharmacol Ther 86:387–395
Felson DT, Anderson JJ, Boers M, Bombardier C, Furst D, Goldsmith C, Katz LM, Lightfoot R Jr, Paulus H, Strand V, Tugwell P, Weinblatt M, Williams HJ, Wolfe F, Kieszak S (1995) ACR preliminary definition of improvement in rheumatoid arthritis. Arthritis Rheum 38:727–735
Karlsson MO, Schoemaker RC, Kemp B, Cohen AF, van Gerven JM, Tuk B, Peck CC, Danhof M (2000) A pharmacodynamic Markov mixed-effects model for the effect of temazepam on sleep. Clin Pharmacol Ther 68:175–188
Xu H, Craig BA (2009) A probit latent class model with general correlation structures for evaluating accuracy of diagnostics tests. Biometrics 65:1145–1155
Beal SL (2001) Ways to fit a PK model with some data below the quantification limit. J Pharmacokin Pharmacodyn 28:481–504
Ahn JE, Karlsson MO, Dunne A, Ludden TM (2008) Likelihood based approaches to handling data below the quantification limit using NONMEM VI. J Pharmacokinet Pharmacodyn 35:401–421
Mendell NR, Elston RC (1974) Multifactorial qualitative traits: genetic analysis and prediction of recurrence risks. Biometrics 30:41–57
Rice J, Reich T, Cloninger CR, Wette R (1979) An approximation to the multivariate normal integral: its application to multifactorial qualitative traits. Biometrics 35:451–459
Smith C, Mendell NR (1974) Recurrence risks from family history and metric traits. Ann Hum Genet 37:275–286
Cappellari L, Jenkins SP (2003) Multivariate probit regression using simulated maximum likelihood. Stata J 3:278–294
Joe H (1995) Approximations to multivariate normal rectangle probabilities based on conditional expectations. J Am Stat Assoc 90:957–964
SAS Institute Inc (2002) SAS software: usage and reference, version 9. SAS Institute Inc, Cary
MathSoft Inc (2005) S-Plus for Windows. Data Analysis Division, MathSoft Inc, Seattle
Beal SL, Sheiner LB, Boeckmann AJ (eds) (1989–2006) NONMEM users guides. Icon Development Solutions, Ellicott City
Drezner Z, Wesolowsky GO (1990) On the computation of the bivariate normal integral. J Stat Comput Simul 35:101–107
Kuhn E, Lavielle M (2005) Maximum likelihood estimation in nonlinear mixed effects models. Comput Stat Data Anal 49:1020–1038
Bock RD, Gibbons RD (1996) High-dimensional multivariate probit analysis. Biometrics 52:1183–1194
Kremer M, Bloom BJ, Breedveld FC, Coombs J, Fletcher MP, Gruben D, Krishnaswami S, Burgos-Vargas R, Wilkinson B, Zerbini CAF, Zwillich SH (2006) The safety and efficacy of a JAK inhibitor in patients with active rheumatoid arthritis: results of a double-blind, placebo-controlled phase IIa trial of three dosage levels of CP-690, 550 versus placebo. Arthritis Rheum 60:1895–1905
Ochi Y, Prentice RL (1984) Likelihood inference in a correlated probit regression model. Biometrika 71:531–543
Liang KY, Zeger SL (1986) Longitudinal data analysis using generalized linear models. Biometrika 73:13–22
Jacqmin-Gadda H, Proust-Lima C, Amiéva H (2010) Semi-parametric latent process model for longitudinal ordinal data: application to cognitive decline. Stat Med 29:2723–2731
Genz A (1992) Numerical computation of multivariate normal probabilities. J Comput Graph Stat 1:141–149
Yano I, Beal SL, Sheiner LB (2001) The need for mixed-effects modeling with population dichotomous data. J Pharmacokinet Pharmacodyn 28:389–412
Philipson PM, Ho WK, Henderson R (2008) Comparative review of methods for handling drop-out in longitudinal studies. Stat Med 27:6276–6298
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendices
Appendix 1: Stochastic integral approximation
where \( e_{kj}^{ * } = \Upphi^{ - 1} \left( {1 - y_{k} + \left( { - 1} \right)^{{\left( {1 - y_{k} } \right)}} u_{kj}^{ * } \Upphi \left( {\left( { - 1} \right)^{{\left( {1 - y_{k} } \right)}} \left( {q_{k} - \sum\limits_{g = 1}^{k - 1} {s_{g,k} e_{gj}^{ * } } } \right)s_{k,k}^{ - 1} } \right)} \right) \) and \( u_{kj}^{ * } \) is a random draw from U(0,1).
Appendix 2: Gaussian quadrature
Borrowing some of the quantities from Appendix 1,
where \( e_{kl}^{IOV} = \Upphi^{ - 1} \left( {1 - y_{k} + \left( { - \Upphi \left( {\eta_{kl}^{IOV} } \right)} \right)^{{\left( {1 - y_{k} } \right)}} \Upphi \left( {\left( { - 1} \right)^{{\left( {1 - y_{k} } \right)}} \left( {q_{k} - \sum\limits_{g = 1}^{k - 1} {s_{g,k} e_{gl}^{IOV} } } \right)s_{k,k}^{ - 1} } \right)} \right) \) and η IOV kl is a N(0,1) random effect. Note that in this case the e’s and the η’s have two subscript variables to imply that a different sequence of random effects was used for each conditional probability.
Appendix 3: Binary variable method
From Drezner and Wesolowsky
K(q i1, q i2; ρ12) ≈ Φ(q i1, q i2; ρ12) and ρ12 is the correlation between ε 1 and ε 2.
where K(·) is defined above. Let \( M_{l} = \Upphi \left({\left({- 1} \right)^{{1 - y_{l}}} q_{l}} \right) \) and \( C_{ll} = M_{l} - M_{l}^{2} \) and \( C_{lm} = H_{lm} - M_{l} M_{m} \), then
Based on preliminary evaluation (not shown) the 3 point approximation of K which can be programmed with 1 line of code has acceptable accuracy compared to the 5 or 10 point approximation.
Appendix 4: Mendell–Elston
This approximation is defined recursively. We slightly modify the notation of Rice et al. for clarity and construct a general likelihood.
where \( Z_{{l\left| {0,1, \ldots ,j} \right.}} = \left( {Z_{{l\left| {0,1, \ldots ,j - 1} \right.}} - a_{{j\left| {0,1, \ldots ,j - 1} \right.}} r_{{jl\left| {0,1, \ldots ,j - 1} \right.}} } \right)\sigma_{{l\left| {0,1, \ldots ,j} \right.}}^{ - 1} \), \( a_{{j\left| {0,1, \ldots ,j - 1} \right.}} = {{\left( { - 1} \right)^{{y_{j} }} \phi \left( {Z_{{j\left| {0,1, \ldots ,j - 1} \right.}} } \right)} \mathord{\left/ {\vphantom {{\left( { - 1} \right)^{{y_{j} }} \phi \left( {Z_{{j\left| {0,1, \ldots ,j - 1} \right.}} } \right)} {\Upphi \left( {( - 1)^{{\left( {1 - y_{j} } \right)}} Z_{{j\left| {0,1, \ldots ,j - 1} \right.}} } \right)}}} \right. \kern-\nulldelimiterspace} {\Upphi \left( {( - 1)^{{\left( {1 - y_{j} } \right)}} Z_{{j\left| {0,1, \ldots ,j - 1} \right.}} } \right)}} \), \( \sigma_{{k\left| {0,1, \ldots ,i} \right.}} = \sqrt {1 - r_{{ik\left| {0,1, \ldots ,i} \right. - 1}}^{2} a_{{i\left| {0,1, \ldots ,i} \right. - 1}} \left( {a_{{i\left| {0,1, \ldots ,i} \right. - 1}} - Z_{{i\left| {0,1, \ldots ,i} \right. - 1}} } \right)} \), and \( r_{{mn\left| {0,1, \ldots ,j} \right.}} = \left( {r_{{mn\left| {0,1, \ldots ,j - 1} \right.}} - r_{{jm\left| {0,1, \ldots ,j - 1} \right.}} r_{{jn\left| {0,1, \ldots ,j - 1} \right.}} a_{{j\left| {0,1, \ldots ,j} \right. - 1}} \left( {a_{{j\left| {0,1, \ldots ,j - 1} \right.}} - Z_{{j\left| {0,1, \ldots ,j - 1} \right.}} } \right)} \right)\sigma_{{m\left| {0,1, \ldots ,j} \right.}}^{ - 1} \sigma_{{n\left| {0,1, \ldots ,j} \right.}}^{ - 1} \).
Note that \( Z_{l\left| 0 \right.} = q_{l} \), \( r_{lm\left| 0 \right.} = \rho_{lm} \).
Appendix 5: Calculation of a marginal covariance
The PROBBNRM function in SAS was used to compute \( \Upphi_{2} \left( {q_{i} ,q_{j} ,\rho \left| {\eta_{k}^{(s)} } \right.} \right) \) and η (s) k was sampled from a N(0, \( \hat{\Upomega } \)) distribution
Computation of the marginal variance
where \( E\left( {Y_{i}^{2} } \right) = E\left( {Y_{i} } \right) \) and \( E\left( {Y_{i} } \right) = P\left( {Y_{i} } \right). \)
Rights and permissions
About this article
Cite this article
Hutmacher, M.M., French, J.L. Extending the latent variable model for extra correlated longitudinal dichotomous responses. J Pharmacokinet Pharmacodyn 38, 833–859 (2011). https://doi.org/10.1007/s10928-011-9222-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10928-011-9222-4