#### Week #25 – Nearest Neighbor Clustering

The single linkage clustering method (or the nearest neighbor method) is a method of calculating distance between clusters in hierarchical cluster analysis .

The Weekly Briefing has current articles, Word of the Week, historical notes, spotlights on jobs and industries, student profiles and more.

The single linkage clustering method (or the nearest neighbor method) is a method of calculating distance between clusters in hierarchical cluster analysis .

Comments Off on Week #25 – Nearest Neighbor Clustering

June 11, 2015

In a network analysis context, "edge" refers to a link or connection between two entities in a network

Comments Off on Week # 24 – Edge

June 4, 2015

The 2006 Netflix Contest has come to convey the idea of crowdsourced predictive modeling, in which a dataset and a prediction challenge are made publicly available. Individuals and teams then compete to develop the best performing model.

Comments Off on Week #23 – Netflix Contest

June 4, 2015

The linear model is ubiquitous in classical statistics, yet real-life data rarely follow a purely linear pattern.

Comments Off on Week #22 – Splines

May 26, 2015

Association rules, also called "market basket analysis," is a data mining method applied to transaction data.

Comments Off on Week # 21 – Association Rules

May 26, 2015

This week's word is actually a letter. R is a statistical computing and programming language and program, a derivative of the commercial S-PLUS program, which, in turn, was an offshoot of S from Bell Labs.

Comments Off on Week #20 – R

May 19, 2015

With the advent of Big Data and data mining, statistical methods like regression and CART have been repurposed to use as tools in predictive modeling.

Comments Off on Week #19 – Prediction vs. Explanation

April 28, 2015

The Netflix prize was a famous early application of crowdsourcing to predictive modeling.

Comments Off on Week #18 – Netflix Prize

April 28, 2015

An A-B test is a classic statistical design in which individuals or subjects are randomly split into two groups and some intervention or treatment is applied.

Comments Off on Week #17 – A-B Test

April 28, 2015

In time series forecasting, a moving average is a smoothing method in which the forecast for time t is the average value for the w periods ending with time t-1.

Comments Off on Week #16 – Moving Average

March 9, 2015

In regression models, an interaction term captures the joint effect of two variables that is not captured in the modeling of the two terms individually.

Comments Off on Week #15 – Interaction term

March 9, 2015

A naive forecast or prediction is one that is extremely simple and does not rely on a statistical model (or can be expressed as a very basic form of a model).

Comments Off on Week #14 – Naive forecast

March 9, 2015

RMSE is root mean squared error. In predicting a numerical outcome with a statistical model, predicted values rarely match actual outcomes exactly.

Comments Off on Week #13 – RMSE

March 9, 2015

A label is a category into which a record falls, usually in the context of predictive modeling. Label, class and category are different names for discrete values of a target (outcome) variable.

Comments Off on Week #12 – Label

March 9, 2015

A strip transect is a small subsection of a geographically-defined study area, typically chosen randomly.

Comments Off on Week #7.5 – Strip transect

February 20, 2015

Spark is a second generation computing environment that sits on top of a Hadoop system, supporting the workflows that leverage a distributed file system.

Comments Off on Week #11 – Spark

February 20, 2015

Bandits refers to a class of algorithms in which users or subjects make repeated choices among, or decisions in reaction to, multiple alternatives.

Comments Off on Week #10 – Bandits

February 20, 2015

In discrete response models, overdispersion occurs when there is more correlation in the data than is allowed by the assumptions that the model makes.

Comments Off on week #9 – Overdispersion

January 30, 2015

In a classification model, the confusion matrix shows the counts of correct and erroneous classifications. In a binary classification problem, the matrix consists of 4 cells.

Comments Off on Week #8 – Confusion matrix

January 30, 2015

In a classic statistical experiment, treatment(s) and placebo are applied to randomly assigned subjects, and, at the end of the experiment, outcomes are compared.

Comments Off on Week #7 – Multiple looks

January 16, 2015

Classification and regression trees, applied to data with known values for an outcome variable, derive models with rules like "If taxable income <$80,000, if no Schedule C income, if standard deduction taken, then no-audit."

Comments Off on Week #6 – Pruning the tree

January 16, 2015

The predictors in a predictive model are sometimes given different terms by different disciplines. Traditional statisticians think in terms of variables.

Comments Off on Week #5 – Features vs. Variables

January 16, 2015

In logistic regression, we seek to estimate the relationship between predictor variables Xi and a binary response variable. Specifically, we want to estimate the probability p that the response variable will be a 0 or a 1.

Comments Off on Week #4 – Logistic Regression

January 16, 2015

Bayesian statistics typically incorporates new information (e.g. from a diagnostic test, or a recently drawn sample) to answer a question of the form "What is the probability that..."

Comments Off on Week #3 – Prior and posterior

January 16, 2015

Consider two (or more) samples subjected to different treatments. A permutation test assesses whether,

Comments Off on Week #2 – Permutation test

January 9, 2015

One avid reader took issue with a recent definition of "quasi experiment." I had defined it

Comments Off on Week #1 – Quasi-experiment (revisited)

January 9, 2015

In social science research, particularly in the qualitative literature on program evaluation, the term "quasi-experiment" refers to studies that do not involve the application of treatments via random assignment of subjects.

Comments Off on Week # 52 – Quasi-experiment

December 5, 2014

In survey research, curb-stoning refers to the deliberate fabrication of survey interview data by the interviewer.

Comments Off on Week #51 – Curb-stoning

December 5, 2014

Bag-of-words is a simplified natural language processing concept.

Comments Off on Week #50 – Bag-of-words

November 7, 2014

In language processing, stemming is the process of taking multiple forms of the same word and reducing them to the same basic core form.

Comments Off on Week #49 – Stemming

November 7, 2014

Structured data is data that is in a form that can be used to develop statistical or machine learning models (typically a matrix where rows are records and columns are variables or features).

Comments Off on Week #48 – Structured vs. unstructured data

November 7, 2014

In predictive modeling, a key step is to turn available data (which may come from varied sources and be messy) into an orderly matrix of rows (records to be predicted) and columns (predictor variables or features).

Comments Off on Week #47 – Feature engineering

November 7, 2014

A full Bayesian classifier is a supervised learning technique that assigns a class to a record by finding other records with attributes just like it has, and finding the most prevalent class among them.

Comments Off on Week #46 – Naive bayes classifier

November 7, 2014

In computer science, MapReduce is a procedure that prepares data for parallel processing on multiple computers.

Comments Off on Week #45 – MapReduce

November 7, 2014

Likert scales are categorical ordinal scales used in social sciences to measure attitude. A typical example is a set of response options ranging from "strongly agree" to "strongly disagree."

Comments Off on Week #44 – Likert scales

October 10, 2014

A node is an entity in a network. In a social network, it would be a person. In a digital network, it would be a computer or device.

Comments Off on Week #43 – Node

October 10, 2014

Latent variable models postulate some relationship between the statistical properties of observable variables.

Comments Off on Week #42 – Latent Variable Models

October 1, 2014

K-nearest-neighbor (K-NN) is a machine learning predictive algorithm that relies on calculation of distances between pairs of records.

Comments Off on Week #41 – K-nearest neighbor

October 1, 2014

The kappa statistic measures the extent to which different raters or examiners differ when looking at the same data and assigning categories.

Comments Off on Word #40 – Kappa Statistic

September 19, 2014

Censoring in time-series data occurs when some event causes subjects to cease producing data for reasons beyond the control of the investigator, or for reasons external to the issue being studied.

Comments Off on Word #39 – Censoring

September 19, 2014

Survival analysis is a set of methods used to model and analyze survival data, also called time-to-event data.

Comments Off on Word #38 – Survival Analysis

September 18, 2014

The probability distribution for X is the possible values of X and their associated probabilities. With two separate discrete random variables, X and Y, the joint probability distribution is the function f(x,y)

Comments Off on Word #37 – Joint Probability Distribution

September 18, 2014

With a sample of size N, the jackknife involves calculating N values of the estimator, with each value calculated on the basis of the entire sample less one observation.

Comments Off on Word #36 – The Jackknife

September 18, 2014

In the interim monitoring of clinical trials, multiple looks are taken at the accruing patient results - say, response to a medication.

Comments Off on Word #35 – Interim Monitoring

September 18, 2014

A NoSQL database is distinguished mainly by what it is not -

Comments Off on Word #34 – NoSQL

July 28, 2014

A similarity matrix shows how similar records are to each other.

Comments Off on Word #33 – Similarity matrix

July 28, 2014

Predictive modeling is the process of using a statistical or machine learning model to predict the value of a target variable (e.g. default or no-default) on the basis of a series of predictor variables (e.g. income, house value, outstanding debt, etc.).

Comments Off on Work #32 – Predictive modeling

July 28, 2014

A hold-out sample is a random sample from a data set that is withheld and not used in the model fitting process. After the model...

Comments Off on Word #31 – Hold-out sample

July 28, 2014

Heteroscedasticity generally means unequal variation of data, e.g. unequal variance. More specifically,

Comments Off on Week #30 – Heteroscedasticity

July 28, 2014

Goodness-of-fit measures the difference between an observed frequency distribution and a theoretical probability distribution which

Comments Off on Week #29 – Goodness-of-fit

July 15, 2014

The geometric mean of n values is determined by multiplying all n values together, then taking the nth root of the product. It is useful in taking averages of ratios.

Comments Off on Week #28 – Geometric Mean

July 15, 2014

Hierarchical linear modeling is an approach to analysis of hierarchical (nested) data - i.e. data represented by categories, sub-categories, ..., individual units (e.g. school -> classroom -> student).

Comments Off on Week #27 – Hierarchical Linear Models

June 6, 2014

In medical statistics, the hazard function is a relationship between a proportion and time.

Comments Off on Week #26 – Hazard Function

June 6, 2014

The Fleming procedure (or *O´Brien-Fleming multiple testing procedure *) is a simple multiple testing procedure for comparing two treatments when the response to treatment is dichotomous . This procedure...

Comments Off on Week #25 – Fleming multiple testing procedure

May 30, 2014

In a directed network, connections between nodes are directional. For example..

Comments Off on Week #24 – Directed vs. Undirected Network

May 30, 2014

An adjacency matrix describes the relationships in a network. Nodes are listed in the top..

Comments Off on Week #23 – Adjacency Matrix

May 30, 2014

The exponential distribution is a model for the length of intervals between two consecutive random events in time or

Comments Off on Week #22 – Exponential Distribution

May 30, 2014

Error is the deviation of an estimated quantity from its true value, or, more precisely,

Comments Off on Week #21 – Error

May 29, 2014

Step-wise regression is one of several computer-based iterative variable-selection procedures.

Comments Off on Week #20 – Step-wise Regression

May 16, 2014

Regularization refers to a wide variety of techniques used to bring structure to statistical models in the face of data size, complexity and sparseness.

Comments Off on Week #19 – Regularization

May 9, 2014

SQL stands for structured query language, a high level language for querying relational databases, extracting information.

Comments Off on Week #18 – SQL

March 28, 2014

A Markov chain is a probability system that governs transition among states or through successive events.

Comments Off on Week #17 – . Markov Chain Monte Carlo (MCMC)

March 14, 2014

MapReduce is a programming framework to distribute the computing load of very large data and problems to multiple computers.

Comments Off on Week #16 – MapReduce

March 14, 2014

As data processing requirements grew beyond the capacities of even large computers, distributed computing systems were developed to spread the load to multiple computers.

Comments Off on Week #15 – Hadoop

March 14, 2014

The curse of dimensionality is the affliction caused by adding variables to multivariate data models.

Comments Off on Week #14 – Curse of Dimensionality

March 14, 2014

A data product is a product or service whose value is derived from using algorithmic methods on data, and which in turn produces data to be used in the same product, or tangential data products.

Comments Off on Week #13 – Data Product

February 21, 2014

Statistical models normally specify how one set of variables, called dependent variables, functionally depend on another set of variables, called independent variables.

Comments Off on Week #12 – Dependent and Independent Variables

February 12, 2014

Statistical distance is a measure calculated between two records that are typically part of a larger dataset, where rows are records and columns are variables. To calculate...

Comments Off on Week #11 – Distance

February 5, 2014

In predictive modeling, the goal is to make predictions about outcomes on a case-by-case basis: an insurance claim will be fraudulent or not, a tax return will be correct or in error, a subscriber...

Comments Off on Week #10 – Decile Lift

February 5, 2014

In the machine learning community, a decision tree is a branching set of rules used to classify a record, or predict a continuous value for a record. For example

Comments Off on Week #9 – Decision Trees

February 5, 2014

In predictive modeling, feature selection, also called variable selection, is the process (usually automated) of sorting through variables to retain variables that are likely...

Comments Off on Week #8 – Feature Selection

February 5, 2014

In predictive modeling, bagging is an ensemble method that uses bootstrap replicates of the original training data to fit predictive models.

Comments Off on Week #7 – Bagging

February 5, 2014

In predictive modeling, boosting is an iterative ensemble method that starts out by applying a classification algorithm and generating classifications.

Comments Off on Week #6 – Boosting

February 5, 2014

In predictive modeling, ensemble methods refer to the practice of taking multiple models and averaging their predictions.

Comments Off on Week #5 – Ensemble Methods

February 5, 2014

The expected value of a random variable, in a simple sense, is nothing but the arithmetic mean.

Comments Off on Week #4 – Expected value

December 9, 2013

Exact tests are hypothesis tests that are guaranteed to produce Type-I error at or below the nominal alpha level of the test when conducted on samples drawn from a null model.

Comments Off on Week #3 – Exact Tests

December 9, 2013

In statistical models, error or residual is the deviation of the estimated quantity from its true value: the greater the deviation, the greater the error.

Comments Off on Week #2 – Error

December 9, 2013

Endogenous variables in causal modeling are the variables with causal links (arrows) leading to them from other variables in the model.

Comments Off on Week #1 – Endogenous variable

December 9, 2013

In a study or experiment with two groups (usually control and treatment), the investigator typically has in mind the magnitude of the difference between the two groups that he or she wants to be able to detect in a hypothesis test.

Comments Off on Week #53 – Effect size

December 9, 2013

Comments Off on Week #52 – Alpha spending function

November 22, 2013

In a test of significance (also called a hypothesis test), Type I error is the error of rejecting the null hypothesis when it is true -- of saying an effect or event is statistically significant when it is not.

Comments Off on Week #51 – Type 1 error

November 22, 2013

A time series x(t); t=1,... is considered to be stationary if its statistical properties do not depend on time t .

Comments Off on Week #50 – Stationary time series

October 25, 2013

Data partitioning in data mining is the division of the whole data available into two or three non-overlapping sets: the training set (used to fit the model), the validation set (used to compared models), and the test set (used to predict performance on new data).

Comments Off on Week #49 – Data partitioning

October 25, 2013

Data mining is concerned with finding latent patterns in large databases.

Comments Off on Week #48 – Data Mining

October 25, 2013

An observation´s z-score tells you the number of standard deviations it lies away from the population mean (and in which direction).

Comments Off on Week #47 – Z-score

October 25, 2013

In multivariate analysis, cluster analysis refers to methods used to divide up objects into similar groups, or, more precisely, groups whose members are all close to one another on various dimensions being measured.

Comments Off on Week #46 – Cluster Analysis

October 21, 2013

In psychology, a construct is a phenomenon or a variable in a model that is not directly observable or measurable - intelligence is a classic example.

Comments Off on Week #45 – Construct validity

October 7, 2013

Collaborative filtering algorithms are used to predict whether a given individual might like, or purchase, an item.

Comments Off on Week # 44 – Collaborative filtering

October 7, 2013

Longitudinal data records multiple observations over time for a set of individuals or units. A typical..

Comments Off on Week #43 – Longitudinal data

August 20, 2013

Cross-sectional data refer to observations of many different individuals (subjects, objects) at a given time, each observation belonging to a different individual. A simple...

Comments Off on Week #42 – Cross-sectional data

August 20, 2013

Tokenization is an initial step in natural language processing. It involves breaking down a text into a series of basic units, typically words. For example...

Comments Off on Week #41 – Tokenization

August 20, 2013

A natural language is what most people outside the field of computer science think of as just a language (Spanish, English, etc.). The term...

Comments Off on Week #40 – Natural Language

August 20, 2013

White Hat Bias is bias leading to distortion in, or selective presentation of, data that is considered by investigators or reviewers to be acceptable because it is in the service of righteous goals.

Comments Off on Week # 39 – White Hat Bias

August 20, 2013

An edge is a link between two people or entities in a network that can be

Comments Off on Week # 38 – Edge

July 24, 2013

Stratified sampling is a method of random sampling.

Comments Off on Week #37 – Stratified Sampling

July 24, 2013

When probabilities are quoted without specification of the sample space, it could result in ambiguity when the sample space is not self-evident.

Comments Off on Week #36 – Conditional Probability

July 24, 2013

A discrete distribution is one in which the data can only take on certain values, for example integers. A continuous distribution is one in which data can take on any value within a specified range (which may be infinite).

Comments Off on Week #35 – Continuous vs. Discrete Distributions

July 24, 2013

The central limit theorem states that the sampling distribution of the mean approaches Normality as the sample size increases, regardless of the probability distribution of the population from which the sample is drawn.

Comments Off on Week # 34 – Central Limit Theorem

July 24, 2013

Classification and regression trees (CART) are a set of techniques for classification and prediction.

Comments Off on Week #33 – Classification and Regression Trees (CART)

July 24, 2013

CHAID stands for Chi-squared Automatic Interaction Detector. It is a method for building classification trees and regression trees from a training sample comprising already-classified objects.

Comments Off on Week #32 – CHAID

July 23, 2013