Personalized medicine -- the tailoring of care based on individual characteristics -- has grown rapidly in recent years, particularly for cancer treatment. There is significant variability within cancer types, and with tumour testing many new therapies can be targeted to the patients most likely to respond to the drug. However, the cost of these drugs and of the testing required is a significant obstacle to their use. A challenge facing health care systems is how to evaluate the effectiveness and cost-effectiveness of personalized therapies. Data from clinical trials can be limited, and may not reflect how the drug is used in practice. The real-world effectiveness and costs of a drug can be evaluated using comparative effectiveness research methods, using data from patients being treated with the drug in real clinical settings. However, these methods have a limited ability to account for variability between patients, and in the case of personalized medicines understanding this variability is essential to understanding the effectiveness and cost-effectiveness of the drug. This project will look at analytic methods to compare the benefits and costs of personalized medicine, using data on advanced colorectal cancer treatment as a case study. Two drugs, cetuximab and panitumumab, targeted to colorectal cancer patients with a specific gene, were adopted in British Columbia in 2009. This study will use real-world data for patients treated for advanced colorectal cancer at the BC Cancer Agency to calculate the cost-effectiveness of these two drugs, and compare conventional evaluation methods to methods that account for the personalized nature of this therapy. These research methods can be used to generate better evidence for policy decisions around personalized medicines, ultimately improving health at the individual and population levels while using scarce healthcare resources more efficiently