In Chapter 1, we provide conditions for the synthetic control estimator to be asymptotically unbiased when the outcome is nonlinear, and propose a flexible and data-driven method to choose the synthetic control weights. In the empirical application, we illustrate the method by estimating the impact of the 2019 anti-extradition law amendments bill protests on Hong Kong's economy, and find that the year-long protests reduced real GDP per capita in Hong Kong by 11.27% in the first quarter of 2020, which was larger in magnitude than the economic decline during the 1997 Asian financial crisis or the 2008 global financial crisis. In Chapter 2, we generalise the conventional synthetic control method to a multiple-outcome framework, where the time dimension is supplemented with the extra dimension of related outcomes. As a result, the synthetic control method can now be used even if only a small number of pretreatment periods are available or if we worry about structural breaks over a longer time span. We show that the bound on the bias of the multiple-outcome synthetic control estimator is of a smaller stochastic order than that of the single-outcome synthetic control estimator, provided that the unit of interest can be closely approximated by the synthetic control in terms of the observed predictors and the multiple related outcomes before the treatment. In the empirical application, we illustrate our method by estimating the effects of non-pharmaceutical interventions on various outcomes in Sweden in the first 3 quarters of 2020. Our results suggest that if Sweden had implemented stricter NPIs like the other European countries by March, then (1) there would have been about 70% fewer cumulative COVID-19 infection cases and deaths by July, and 20% fewer weekly deaths from all causes in early May; (2) temporary absence from work would increase by 76% and total hours worked would decrease by 12% among the employed in the second quarter, but the impact would vanish in the third quarter, and there would be no discernable effect on the employment rate throughout; (3) the volume of retail sales would shrink by 5%-13% from March to May, while the other economic outcomes including GDP, import, export, industrial production, and CPI would not be affected. In Chapter 3, we propose a method based on the interactive fixed effects model to estimate treatment effects at the individual level, which allows both the treatment assignment and the potential outcomes to be correlated with the unobserved individual characteristics. This method is suitable for panel datasets where multiple related outcomes are observed for a large number of individuals over a small number of time periods. To illustrate our method, we provide an example of estimating the effect of health insurance coverage on individual usage of hospital emergency departments using the Oregon Health Insurance Experiment data.