GenAI Powered Dynamic Causal Inference with Unstructured Data
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917473140342784 |
|---|---|
| author | Nakamura, Kentaro Imai, Kosuke |
| author_facet | Nakamura, Kentaro Imai, Kosuke |
| contents | A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07834 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GenAI Powered Dynamic Causal Inference with Unstructured Data Nakamura, Kentaro Imai, Kosuke Methodology Applications A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text. |
| title | GenAI Powered Dynamic Causal Inference with Unstructured Data |
| topic | Methodology Applications |
| url | https://arxiv.org/abs/2605.07834 |