Regression and correlation analysis

 

Regression and correlation analysis

Regression analysis involves identifying the relationship between a dependent variable and one or more independent variables. A model of the relationship is hypothesized, and estimates of the parameter values are used to develop an estimated regression equation. Various tests are then employed to determine if the model is satisfactory. If the model is deemed satisfactory, the estimated regression equation can be used to predict the value of the dependent variable given values for the independent variables.

Regression model

In simple linear regression, the model used to describe the relationship between a single dependent variable y and a single independent variable x is y = β0 + β1x + ε. β0 and β1 are referred to as the model parameters, and ε is a probabilistic error term that accounts for the variability in y that cannot be explained by the linear relationship with x. If the error term were not present, the model would be deterministic; in that case, knowledge of the value of x would be sufficient to determine the value of y.

In multiple regression analysis, the model for simple linear regression is extended to account for the relationship between the dependent variable y and p independent variables x1, x2, . . ., xp. The general form of the multiple regression model is y = β0 + β1x1 + β2x2 + . . . + βpxp + ε. The parameters of the model are the β0, β1, . . ., βp, and ε is the error term.

Least squares method

Either a simple or multiple regression model is initially posed as a hypothesis concerning the relationship among the dependent and independent variables. The least squares method is the most widely used procedure for developing estimates of the model parameters. For simple linear regression, the least squares estimates of the model parameters β0 and β1 are denoted b0 and b1. Using these estimates, an estimated regression equation is constructed: ŷ = b0 + b1x . The graph of the estimated regression equation for simple linear regression is a straight line approximation to the relationship between y and x.

scatter diagram with estimated regression equation
scatter diagram with estimated regression equation

As an illustration of regression analysis and the least squares method, suppose a university medical centre is investigating the relationship between stress and blood pressure. Assume that both a stress test score and a blood pressure reading have been recorded for a sample of 20 patients. The data are shown graphically in Figure 4, called a scatter diagram. Values of the independent variable, stress test score, are given on the horizontal axis, and values of the dependent variable, blood pressure, are shown on the vertical axis. The line passing through the data points is the graph of the estimated regression equation: ŷ = 42.3 + 0.49x. The parameter estimates, b0 = 42.3 and b1 = 0.49, were obtained using the least squares method.

A primary use of the estimated regression equation is to predict the value of the dependent variable when values for the independent variables are given. For instance, given a patient with a stress test score of 60, the predicted blood pressure is 42.3 + 0.49(60) = 71.7. The values predicted by the estimated regression equation are the points on the line in Figure 4, and the actual blood pressure readings are represented by the points scattered about the line. The difference between the observed value of y and the value of y predicted by the estimated regression equation is called a residual. The least squares method chooses the parameter estimates such that the sum of the squared residuals is minimized.

Analysis of variance and goodness of fit

A commonly used measure of the goodness of fit provided by the estimated regression equation is the coefficient of determination. Computation of this coefficient is based on the analysis of variance procedure that partitions the total variation in the dependent variable, denoted SST, into two parts: the part explained by the estimated regression equation, denoted SSR, and the part that remains unexplained, denoted SSE.

The measure of total variation, SST, is the sum of the squared deviations of the dependent variable about its mean: Σ(y − ȳ)2. This quantity is known as the total sum of squares. The measure of unexplained variation, SSE, is referred to as the residual sum of squares. For the data in Figure 4, SSE is the sum of the squared distances from each point in the scatter diagram (see Figure 4) to the estimated regression line: Σ(y − ŷ)2. SSE is also commonly referred to as the error sum of squares. A key result in the analysis of variance is that SSR + SSE = SST.

The ratio r2 = SSR/SST is called the coefficient of determination. If the data points are clustered closely about the estimated regression line, the value of SSE will be small and SSR/SST will be close to 1. Using r2, whose values lie between 0 and 1, provides a measure of goodness of fit; values closer to 1 imply a better fit. A value of r2 = 0 implies that there is no linear relationship between the dependent and independent variables.

When expressed as a percentage, the coefficient of determination can be interpreted as the percentage of the total sum of squares that can be explained using the estimated regression equation. For the stress-level research study, the value of r2 is 0.583; thus, 58.3% of the total sum of squares can be explained by the estimated regression equation ŷ = 42.3 + 0.49x. For typical data found in the social sciences, values of r2 as low as 0.25 are often considered useful. For data in the physical sciences, r2 values of 0.60 or greater are frequently found.

Significance testing

In a regression study, hypothesis tests are usually conducted to assess the statistical significance of the overall relationship represented by the regression model and to test for the statistical significance of the individual parameters. The statistical tests used are based on the following assumptions concerning the error term: (1) ε is a random variable with an expected value of 0, (2) the variance of ε is the same for all values of x, (3) the values of ε are independent, and (4) ε is a normally distributed random variable.

The mean square due to regression, denoted MSR, is computed by dividing SSR by a number referred to as its degrees of freedom; in a similar manner, the mean square due to error, MSE, is computed by dividing SSE by its degrees of freedom. An F-test based on the ratio MSR/MSE can be used to test the statistical significance of the overall relationship between the dependent variable and the set of independent variables. In general, large values of F = MSR/MSE support the conclusion that the overall relationship is statistically significant. If the overall model is deemed statistically significant, statisticians will usually conduct hypothesis tests on the individual parameters to determine if each independent variable makes a significant contribution to the model.

Residual analysis

The analysis of residuals plays an important role in validating the regression model. If the error term in the regression model satisfies the four assumptions noted earlier, then the model is considered valid. Since the statistical tests for significance are also based on these assumptions, the conclusions resulting from these significance tests are called into question if the assumptions regarding ε are not satisfied.

The ith residual is the difference between the observed value of the dependent variable, yi, and the value predicted by the estimated regression equation, ŷi. These residuals, computed from the available data, are treated as estimates of the model error, ε. As such, they are used by statisticians to validate the assumptions concerning ε. Good judgment and experience play key roles in residual analysis.

Graphical plots and statistical tests concerning the residuals are examined carefully by statisticians, and judgments are made based on these examinations. The most common residual plot shows ŷ on the horizontal axis and the residuals on the vertical axis. If the assumptions regarding the error term, ε, are satisfied, the residual plot will consist of a horizontal band of points. If the residual analysis does not indicate that the model assumptions are satisfied, it often suggests ways in which the model can be modified to obtain better results.

Model building

In regression analysis, model building is the process of developing a probabilistic model that best describes the relationship between the dependent and independent variables. The major issues are finding the proper form (linear or curvilinear) of the relationship and selecting which independent variables to include. In building models it is often desirable to use qualitative as well as quantitative variables.

Comments

Post a Comment

Popular posts from this blog

Topological data analysis

Image
  Topological data analysis 5 languages Article Talk Read Edit View history From Wikipedia, the free encyclopedia In  applied mathematics ,  topological based data analysis  ( TDA ) is an approach to the analysis of datasets using techniques from  topology . Extraction of information from datasets that are high-dimensional, incomplete and noisy is generally challenging. TDA provides a general framework to analyze such data in a manner that is insensitive to the particular  metric  chosen and provides  dimensionality reduction  and robustness to noise. Beyond this, it inherits  functoriality , a fundamental concept of modern mathematics, from its topological nature, which allows it to adapt to new mathematical tools. [ citation needed ] The initial motivation is to study the shape of data. TDA has combined  algebraic topology  and other tools from pure mathematics to allow mathematically rigorous study of "shape". The main tool is  persistent homology , an adaptation of  homol
Read more

Structure theorem

Image
  Structure theorem [ edit ] The structure theorem is of central importance to TDA; as commented by G. Carlsson, "what makes homology useful as a discriminator between topological spaces is the fact that there is a classification theorem for finitely generated abelian groups." [3]  (see the  fundamental theorem of finitely generated abelian groups ). The main argument used in the proof of the original structure theorem is the standard  structure theorem for finitely generated modules over a principal ideal domain . [9]  However, this argument fails if the indexing set is  ( � , ≤ ) . [3] In general, not every persistence module can be decomposed into intervals. [70]  Many attempts have been made at relaxing the restrictions of the original structure theorem. [ clarification needed ]  The case for pointwise finite-dimensional persistence modules indexed by a locally finite subset of  �  is solved based on the work of Webb. [71]  The most notable result is done by Crawley-Boeve
Read more