Mathematical transformation of data, fit, and graphic representation of regression curves through computer programming (original) (raw)
Related papers
A Graphical Method for Assessing the Fit of a Regression Model
Before a regression model is used to address questions about the relationship between a response variable and predictors, the fit of the model to the data should be assessed. For example, consider a logistic regression model for explaining the dependence of a binary out- come variable on a set of predictor variables or for pre- dicting the outcome variable based on the predictors. Checking the fit of the model before it is used in a prac- tical setting is of critical importance. If a model is found to be deficient, the nature of the deficiency may indicate a need for some aspect of the model to be reformulated or that poorly fitting observations need to be considered separately. I propose graphical methodology based on a Bayesian framework to help address issues such as this. Plots can be constructed quickly and easily for any model of interest, and goodness of fit assessed. These plots are more intuitive and easy-to-use than traditional graphical diagnostic methods for regression s...
PetroPlot: A plotting and data management tool set for Microsoft Excel
Geochemistry Geophysics Geosystems, 2003
1] PetroPlot is a 4000-line software code written in Visual Basic for the spreadsheet program Excel that automates plotting and data management tasks for large amount of data. The major plotting functions include: automation of large numbers of multiseries XY plots; normalized diagrams (e.g., spider diagrams); replotting of any complex formatted diagram with multiple series for any other axis parameters; addition of customized labels for individual data points; and labeling flexible log scale axes. Other functions include: assignment of groups for samples based on multiple customized criteria; removal of nonnumeric values; calculation of averages/standard deviations; calculation of correlation matrices; deletion of nonconsecutive rows; and compilation of multiple rows of data for a single sample to single rows appropriate for plotting. A cubic spline function permits curve fitting to complex time series, and comparison of data to the fits. For users of Excel, PetroPlot increases efficiency of data manipulation and visualization by orders of magnitude and allows exploration of large data sets that would not be possible making plots individually. The source codes are open to all users.
A Simple Introduction to Regression Modeling using R
2023
In statistical modeling, regression analysis is a group of statistical processes used in R programming and statistics to determine the relationship between dataset variables. It is a solid technique for determining the factors that affect an issue of interest. You can confidently establish which elements are most important, which ones can be ignored, and how these factors interact when you do a regression. It can be used to simulate the long-term link between variables and gauge how strongly the relationships between them are related. Regression analysis is typically used to ascertain the relationship between the dataset's dependent and independent variables. Generally, regression analysis is used to determine the relationship between the dependent and independent variables of the dataset. Understanding how dependent variables change when one of the independent variables changes while the other independent variables remain constant is made easier with the use of regression analysis. As a result, it is easier to create a regression model and forecast values in response to changes in one of the independent variables. Based on the categories of dependent variables, the quantity of independent variables, and the contour of the regression line. In this paper, we use the R programming language to present various empirical investigations in statistics and econometrics. We next consider problems involving modeling the relationship between response and explanatory variables for linear and non-liner regression models.
PlotS: web-based application for data visualization and analysis
BackgroundData visualisation technique has greatly improved as technology has advanced. While representing the data through graph, it has made the underlying data structure become more transparent and interpretable. However, the informational scope of freely available generic visualisation tools is still limited since they only support descriptive statistics as well as no metainformation can be incorporated. Additionally, there is a need to promote the use of accepted scientific standards when performing and reporting statistical analysis.ResultPlotS is a visualization centric web-based application that allows the integration of statistical analysis into a single workflow. The current version has eight types of graphs (bar, box, density, frequency polygon, histogram, line, scatter and violin plot) and four statistical methods (T-test, ANOVA, Wilcoxon test and Krushkal-Wallis test). It is an interactive application that provide many useful customization options for data analysis-focu...
The following technical paper presents two case studies pertaining to Linear Regression analysis. Case study 1 presents the use regression analysis in the form of simple regression and multiple regression and elaborates the practical use of regression analysis in the decision making process of which predictor variables should be used in the analysis. Case study 2 presents the use of linear regression techniques in studying the September Sea Ice extent in the Arctic Ocean from year 1979 – 2012. This case study also shows the use of quadratic regression to represent the data with a continuously variable slopes in the regression equation.
A Multivariable Regression Algorithm
1983
>A BASIC algorithm has been developed that is capable of fitting a user-defined regression equation to a set of data. This best-fit-curve algorithm is unique in that it allows multiple variables and multiple forms (exponential, trigonometric, logarithmic, etc.) to be present in a single regression equation. The least-squares regression performed determines the constants for each of the regression equation terms to provide a best-fit curve. Other programs within the algorithm set allow for data entry, editing and print-out, and plotting of the raw data and their best-fit regression curve.
mlrv.ua.edu
The World Wide Web provides an excellent resource of real data that can be used by research methods instructors. Using this data in class allows more time for students to spend learning how to write appropriate statistical equations. This paper provides two ezamples of multiple linear regression equations that were written based on data available on the World Wide Web. It also provides a number of Internet references for instructors that would be helpful for obtaining real data that can be applied in a statistics course.