linear regression (2) robust linear regression (1) outliers (1) visualization (2) machine learning (2) statistics (5) TheilSen regression (1) RANSAC regression (1) Huber regression (1) OLS (1) L1 norm (1) L2 norm (1) L2 norm squared (1) spatial median (1) mean (1) median (1) central tendency (2) robustness (1) euclidean distance (1) absolute loss (1) squared loss (1) least-squares (1) oil-and-gas (2) oil (2) gas (2) DUC (2) drilling (2) horizontals (2) verticals (2) completion (2) production (2) recent-trend (2) energy-shortage (2) EIA (2) DrillingInfo (2) Enverus (2) DPR (2) dead-duc (1) Anadarko (1) Appalachia (1) Bakken (1) Eagle Ford (1) Niobrara (1) Hanyesville (1) Permian (1) correlation (1) multiple linear regression (1) multicollinearity (1) regression (1) feature ranking (1) permutation feature ranking (1) r-squared (1) model (1) 3d (2) features (1) data exploration (1) confidence interval (3) uncertainty (1) non-normal (2) normal (2) non-Gaussian (2) Gaussian (2) normality test (2) hypotheses testing (2) bootstrap (1) t-test (1) f-test (1) box-cox (1) non-parametric (3) parametric (1) lognormal (1) exponential (1) heavy-tails (1) skewness (1) kurtosis (1) data-mining (4) nlp (3) word2vec (3) word vectors (3) window size (3) skip-gram (2) neural network (2) negative sampling (2) stochastic gradient descent (2) learning rate (2) sigmoid (1) softmax (1) algorithm complexity (1) noise distribution (1) co-occurrence matrix (2) vector space model (2) dimensional reduction (1) svd (1) tf-idf (1) nltk (1) tokenization (1) pdf (1) tabula (1) web-dev (1) pelican (1) jupyter (1) bootstrap(stats) (1) monte-carlo-simulation (1) uncertainty-modeling (1) prediction-interval (1)