READ ME File For 'Dataset Statistical Modelling of Temporal and Spatial Causal Effects with Application to Policy Evaluation'

Dataset DOI: 10.5258/SOTON/D3905

ReadMe Author: Yan Zhang, University of Southampton ORCID ID

This dataset supports the thesis entitled 'Dataset Statistical Modelling of Temporal and Spatial Causal Effects with Application to Policy Evaluation'
AWARDED BY: University of Southampton
DATE OF AWARD: 2026

Geographic location of data collection: University of Southampton, U.K.


Date of data collection: 2022-06-01-2024-12-30

--------------------
DATA & FILE OVERVIEW
--------------------

This dataset contains:
1. /Figures: the figures that demonstrated in the thesis, which visualizes the collected data and experimental results (the model outputs). \FTSE includes the figures for Chapter 3 of the thesis and others are for the other chapters. 
2. /modified synthetic control FTSE: raw data and processed data including the stock index, GDP and interest rate data for different countries.
3./STPSEM Kansas: raw and processed GDP datasets for the states in US stored in STPSEM Kansas/KansasData folder. Other Rdata are prepared for empirical study(if there is not 'simulation' in the file name) and simulation studies as described in the file name (including different experiment settings).
And Data versions are distinguished by the date in the filename.  These Rdata can be directly loaded by R containing a series of data frames.
4. /vary_coef_STPSEM data/simulation data: this inculdes the simulation datasets that are generated according to the statement in the thesis.


If there are there multiple versions of the dataset, list the file updated, when and why update was made: Data versions are distinguished by the date in the filename when the RData are updated. The RData are updated as the coding was built including updated model details and etc..



--------------------------
METHODOLOGICAL INFORMATION
--------------------------

Description of methods used for collection/generation of data: The FTSE data is collected from Yahoo Finance via python package'yfinance'. Raw American GDP comes from 'augsynth' R package through 'data(Kansas)'  

Methods for processing the data: the stock index data and GDP data are trasferred into stationary return data and merged into a whole dataset.

Software- or Instrument-specific information needed to interpret the data, including software and hardware version numbers: Python/R in all versions can read the raw data. RData files can be interpreted by R.

People involved with sample collection, processing, analysis and/or submission: Yan Zhang