The chapter provides an overview of duration analysis, focusing on specification, identification, and multiple durations. It discusses reduced-form duration models, particularly the Mixed Proportional Hazard (MPH) model and its multivariate extensions. The MPH model is used to describe the relationship between the exit rate and background variables, and to estimate the effect of explanatory variables on duration. However, since applications often interpret results in terms of economic-theoretical models, the chapter examines how deep structural parameters of these models can be related to reduced-form parameters. It also examines the specification and identification of the MPH model in detail, providing intuition on what drives identification and inferring the extent of biases due to misspecifications. The chapter compares different functional forms for the unobserved heterogeneity distribution. The chapter also examines models for multiple durations, noting that the range of different models is not very large. These models allow for dependence between duration variables through their unobserved determinants, with each duration following its own MPH model. Additionally, the model may allow for a causal effect of one duration on another, as motivated by economic theory. The chapter examines the conditions for identification of these models, noting that some are closely linked to particular estimation strategies. The Multivariate Mixed Proportional Hazard (MMPH) model is discussed, where the marginal duration distributions each satisfy an MPH specification, and durations can only be dependent through their unobserved determinants. The chapter addresses the dimensionality of the heterogeneity distribution and compares the flexibility of different parametric heterogeneity distributions. The chapter incorporates recent insights from the biostatistical literature on duration analysis and contrasts points of view in this literature with those in the econometric literature. It discusses the importance of the possible collection of additional data. The chapter also discusses the importance of the possible collection of additional data. The chapter provides an overview of duration analysis, focusing on specification, identification, and multiple durations. It discusses reduced-form duration models, particularly the Mixed Proportional Hazard (MPH) model and its multivariate extensions. The MPH model is used to describe the relationship between the exit rate and background variables, and to estimate the effect of explanatory variables on duration. However, since applications often interpret results in terms of economic-theoretical models, the chapter examines how deep structural parameters of these models can be related to reduced-form parameters. It also examines the specification and identification of the MPH model in detail, providing intuition on what drives identification and inferring the extent of biases due to misspecifications. The chapter compares different functional forms for the unobserved heterogeneity distribution.The chapter provides an overview of duration analysis, focusing on specification, identification, and multiple durations. It discusses reduced-form duration models, particularly the Mixed Proportional Hazard (MPH) model and its multivariate extensions. The MPH model is used to describe the relationship between the exit rate and background variables, and to estimate the effect of explanatory variables on duration. However, since applications often interpret results in terms of economic-theoretical models, the chapter examines how deep structural parameters of these models can be related to reduced-form parameters. It also examines the specification and identification of the MPH model in detail, providing intuition on what drives identification and inferring the extent of biases due to misspecifications. The chapter compares different functional forms for the unobserved heterogeneity distribution. The chapter also examines models for multiple durations, noting that the range of different models is not very large. These models allow for dependence between duration variables through their unobserved determinants, with each duration following its own MPH model. Additionally, the model may allow for a causal effect of one duration on another, as motivated by economic theory. The chapter examines the conditions for identification of these models, noting that some are closely linked to particular estimation strategies. The Multivariate Mixed Proportional Hazard (MMPH) model is discussed, where the marginal duration distributions each satisfy an MPH specification, and durations can only be dependent through their unobserved determinants. The chapter addresses the dimensionality of the heterogeneity distribution and compares the flexibility of different parametric heterogeneity distributions. The chapter incorporates recent insights from the biostatistical literature on duration analysis and contrasts points of view in this literature with those in the econometric literature. It discusses the importance of the possible collection of additional data. The chapter also discusses the importance of the possible collection of additional data. The chapter provides an overview of duration analysis, focusing on specification, identification, and multiple durations. It discusses reduced-form duration models, particularly the Mixed Proportional Hazard (MPH) model and its multivariate extensions. The MPH model is used to describe the relationship between the exit rate and background variables, and to estimate the effect of explanatory variables on duration. However, since applications often interpret results in terms of economic-theoretical models, the chapter examines how deep structural parameters of these models can be related to reduced-form parameters. It also examines the specification and identification of the MPH model in detail, providing intuition on what drives identification and inferring the extent of biases due to misspecifications. The chapter compares different functional forms for the unobserved heterogeneity distribution.