Two stage least squares with time-varying instruments: An application to an evaluation of treatment intensification for type-2 diabetes

Stat Methods Med Res. 2026 Feb;35(2):346-369. doi: 10.1177/09622802251404064. Epub 2025 Dec 15.

Abstract

As routinely collected longitudinal data becomes more available in many settings, policy makers are increasingly interested in the effect of time-varying treatments (sustained treatment strategies). In settings such as this, many commonly used statistical approaches for estimating treatment effects, such as g-methods, often adopt the 'no unmeasured confounding' assumption. Instrumental variable (IV) methods aim to reduce biases due to unmeasured confounding, but have received limited attention in settings with time-varying treatments. This paper extends and critically evaluates a commonly used IV estimating approach, Two Stage Least Squares (2SLS), for evaluating time-varying treatments. Using a simulation study, we found that, unlike standard 2SLS, the extended 2SLS performs relatively well across a wide range of circumstances, including certain model misspecifications. We illustrate the methods in an evaluation of treatment intensification for Type-2 Diabetes Mellitus, exploring the exogeneity in prescribing preferences to operationalise a time-varying instrument.

Keywords: Instrumental variable; diabetes; physician preference; time-varying; two stage least squares.

MeSH terms

  • Computer Simulation
  • Diabetes Mellitus, Type 2* / drug therapy
  • Diabetes Mellitus, Type 2* / therapy
  • Humans
  • Hypoglycemic Agents / therapeutic use
  • Least-Squares Analysis
  • Models, Statistical
  • Time Factors

Substances

  • Hypoglycemic Agents