Data & Analysis

Data Management and Analysis

I love data. Really, I do. I find data management and analysis to be very satisfying work. I prefer to work in R and write scripts in TextWrangler, but can also use MS Access/Excel, ArcGIS, and RStudio. I have also dabbled in Python, Perl, HTML, and SQL. Rest assured, if I don’t know something, I will learn it!

  • data entry
  • QAQC (quality assurance and control) procedures
  • data formatting (R/Access)
  • database creation (Access)
  • statistical analysis
    • regression (linear, polynomial, multiple linear, binomial, multinomial, K-nearest neighbors, linear/quadratic discriminant analysis, local/loess)
    • Generalized Linear Models (GLMs)
    • Generalized Additive Models (GAMs)
    • step functions
    • regression (linear, cubic, natural) and smoothing splines
    • survival analysis
    • detection probability
    • abundance estimation
    • AIC model comparison, maximum likelihood
    • variable selection (forward, backward, mixed)
    • resampling (cross-validation, K-fold CV, LOOCV, validation set)
    • bootstrap
    • subset selection (best, forward stepwise, backward stepwise, hybrid)
    • shrinkage/regularization methods (ridge regression, lasso)
    • dimension reduction methods (principal components regression (PCA), partial least squares (PLS))
    • regression and classification trees (bagging, Random Forests, boosting)
    • support vector machines (with linear, polynomial, and radial kernels)
    • unsupervised learning (PCA, K-means clustering, hierarchical clustering)
  • reporting: My background in graphic design and layout ensures that any graphics I produce are pleasing to the eye and arranged for ease of interpretation. Combined with extensive experience in scientific writing, you can be assured that any reports I produce will be detailed, complete, and well-organized.