Table Of Contents
  • Least Square Models
  • Analysis of Discrete Data
  • Likelihood Methods
  • Statistical Computing
  • Spatial Data Analysis

Least Square Models

The least-square models identify the best fit for a set of data points. These statistical procedures minimize the sum of the offsets or residuals of points from the plotted curve. The least-square models assume that the curve that has the least sum of deviations is the best fit of a given type. These models strive to find the solution with the minimum residual error. The Least square method which is also known as linear or ordinary is a method of regression analysis. Analysts normally use this method to generate a line of best fit which explains if there is a relationship between dependent and independent variables.

Analysis of Discrete Data

Discrete data can only take certain values. They are countable in a finite amount of time. For example, you can count the number of push-ups you do in a day. Discrete variables require researchers to use statistical assessment tests that are quite different from those used to assess continuous variables. Several statistical methods can be used to analyze discrete variables. Since discrete events do not follow a normal distribution, experts recommend the Poisson and probability distribution methods. These techniques are based on key discrete probability distributions.

Likelihood Methods

Likelihood methods are used to estimate unknown parameters. From given values, a likelihood method can be used to estimate the goodness of fit of a statistical model. Likelihood ratios are powerful inference tools used to measure the strength of statistical evidence. The likelihood function has been generalized and extended to non-parametric and semi-parametric models. Also, experts have proposed a variety of pseudo-likelihood functions for more complex models.

Statistical Computing

Statistical computing is the use of computer software to perform statistical tasks. Traditional statistics modeling methods and data analysis techniques can be complicated for even the most experienced data analysts. These methods also limit the types of analyses that a user can perform. For this reason, there was a need to develop computer software that can aid in the analysis of large data sets and provide accurate results. Today, computational analysis is a vital part of modern statistics. Statisticians are not only required to know how statistical programs run but also understand the key principles that they are based on.

Spatial Data Analysis

Spatial data analysis is the process of geographically modeling problems, processing data in a computer to get results, and then exploring those results. This type of analysis is often used for several purposes including evaluating the suitability of geographic locations, identifying hidden patterns in information, interpreting change, etc. There are two ways of performing spatial data analysis. The first method is vector-based while the other is a raster-based analysis. Spatial data analysis uses geometry and mathematics to try and explain patterns of human behavior and its spatial expression. Some of the new methodologies of spatial analysis that have been introduced include spatial statistical theory and computation.