Survey Data Analytics
Public data collected through surveys are widely used in marketing, social science, public health, economics, political and many other research areas. Different from unstructured data cumulated through Internet, survey data are deliberately collected through well-designed complex surveys usually by big organization such as Census Bureau, Bureau of Labor Statistics and National Opinion Research Center. Every data point is targeted and sampled through probability sampling, which allows the surveys to represent the whole population accurately. But for most researchers, it takes days even months to understand the survey data, the major problem could be:
· How to figure out the survey design to calculate the right estimates, like what do these sampling stratifications, clusters, survey weights, imputation flags stand for and how to use them in my models.
· How to identify and extrapolate the interested subset and variables
· How to interpret the survey questionnaire correctly
· How to analyze the survey data using survey specific statistical models.
We are a team of professional survey statisticians and big data analysts. We could solve your problems of survey data related problems with the shortest time and the most economic solution. Please write to us at email@example.com with any questions. Thanks for visiting our webpage!
Fang Wang Resume
National Opinion Research Center, at the University of Chicago
Survey Statistician III Dec, 2014-Present
Survey Statistician II Dec, 2011 – Dec, 2014
Survey Statistician I Dec, 2009 – Dec, 2011
· Applied text mining and machine learning methods to analyze and visualize text open-ended survey answers.
· Served as Primary Statistician of Medicare Current Beneficiary Survey (MCBS) imputation and weighting; analyzed, imputed and weighted incomplete medical claim data, insurance payment data and patient demographic data; developed internal and external reports.
· Served as PI of the NORC research project “Improving NORC missing data imputation procedure”: developed NORC SAS missing data imputation macro; implemented hot-deck and Bayesian model-based multiple imputations.
· Conducted disclosure risk analysis for National Immunization Survey; generated public use file and reports to CDC.
· Developed SAS macros for complex survey linear and logistic model selection; built complex logistic models.
· Developed R and SAS programs of sampling, predictive modeling, variance estimation, data cleaning and data quality control for Survey of Doctorate Recipient (SDR).
· Participated in the International Survey of Doctorate Recipient survey questionnaire design.
National Opinion Research Center, at the University of Chicago Jul, 2009 – Dec, 2009
Graduate Research Assistant II
· Predicted US number of children in a household using multinomial logistic model for 2008 NIS.
· Developed 2008 NIS R, SAS and SUDAAN data read-in programs and data analysis sample code.
Computational Institute, University of Chicago & Argonne National Lab May, 2009 – Dec, 2009
Graduate Research Assistant
· Modeled yearly global population and urban rural classification using time series models.
· Predicted and visualized US land use change using generalized probit models and Bayesian methods.
· Predicted the 2012 Presidential Election results using a Hierarchy Bayesian model and MCMC simulation, Oct, 2012
· Teaching Assistant, Department of Statistics, University of Chicago, Jan, 2009 – Jun, 2009
· Teaching Assistant, Department of Mathematics, USTC, Sep, 2006 – Jan, 2007
· Conference Coordinator, Pacific Rim Complex Geometry Conference, USTC, May, 2006– Aug, 2006
University of Chicago, Chicago, IL
M.S. in Statistics Dec, 2009
University of Science and Technology of China (USTC), Hefei, China
B.S. in Computational Mathematics July, 2006
SAS Midwest User’s Group Jr Professional Award (First Class), 2011
NORC CESR Research Award 2010, 2011; NORC Excellent Employee Award 2012; NORC Idea Lab Research Award, 2014
l Survey Skills: Sampling Design, Questionnaire Design, Weighting, Complex Survey Data Analysis, Survey Management, Multiple Imputation, Total Survey Error Control
l Statistical Skills: Regression, Design of Experiments, Categorical Data Analysis, Time Series, Machine learning
l Computer Skills: SAS (Macro), R, SQL, Excel, ArcGIS, SUDAAN, SPSS, Python(basic)