Statistical Analyst Resume Example

• Hard-working Statistician, with strong knowledge in statistical theories and formulations, and proficiency in statistical modeling process
• Two years experience in developing analytical research studies and business projects for data insights and decision making
• Proficient in data preparation, including compiling, sampling, cleaning, transformation, etc.
• Proficient in statistical programming with R, SAS and matlab, with advanced SAS programmer for SAS 9 certification
• Strong passion and commitment in risk management and financial industry

Statistical techniques-

• Data management: querying, filtering, extraction, visualization, managing unstructured dataset and dataset with missing values
• Regression and classification: linear/non-linear regression, logistic regression, mixed-effect models, robust analysis
• Multivariate analysis: PCA/LDA, model selection with regularization
• Data mining and Machine learning algorithms for 'Big data': cluster, decision tree, artificial neural with multilayer perceptrons, kernel machine, hidden Markov model
• Time series analysis: SARIMA/ARIMA, VAR, GARCH and other state-space models, spectral and frequency analysis

Programming-

• Statistical programming: SAS, R, S-plus, Matlab, Python
• Database management system: Oracle SQL

Language-

• Bilingual: read, write and speak with both English and Mandarin Chinese

Dissertation: "Robust estimation of parameters for standardizing neuropsychological tests with applications to data from the SMART study"  

continued Professor Birgit Grund's SMART study on neurocognitive performance of HIV-positive patients and tried to find out the best approach to standardize the data. Robust analysis was performed and the difference of OLS, M-estimator, S-estimator and MM-estimator were compared and studied. Statistical significance and effect size were combined to find the best model. High-leverage points were investigated using simulation study

Dissertation: "An exploratory study on potential risk factors of heart disease"  

developed logistic regression and statistical techniques in model selection such as cross validation regularizations to study the risk factors of heart disease. In addition, the paper proposed several insightful suggestions based on the analysis.