A regression analysis is an approach tosorting variables out using a mathematical approach to see which variables door do not have an impact (Gallo, Davenport, Kim, 2017).
A regression analysishelps us to answer which factors from these variables are going to matter mostand which will matter least. It measures interaction between the factors of thevariables. The most important measurement benefitted from a regression analysiswould be the certainty of all these factors (Gallo, Davenport, Kim, 2017).The first part inconducting a regression analysis is to ask the right questions and design thestudy that will help answer those questions (“The 13 Steps,” n.
d.). Once theresearch questions are clearly defined the study needs to be designed to obtainthe answers for those very questions. The design of the study may be one of thehardest parts since it involves randomization and sampling to find the rightstudy to answer the right questions (“The 13 Steps,” n.d.).
After the study isdesigned the data needs to be gathered on the variables in question. Theregression analysis will consist of at least two variables, a dependentvariable and an independent variable. The dependent variable is the part of theanalysis that is predicted beforehand, the one that needs further understanding(Gallo, Davenport, Kim). The independent variable is the factor that is assumedto have impact on the dependent variable (Gallo, Davenport, Kim, 2017). Thedata is then gathered from these variables. This data can be based on nominal, ordinal,or interval measurements (“The 13 Steps,” n.d.).
The second part ofthe regression analysis is preparing and exploring the data. When the data thatwill be measured is decided upon then it will be time to collect and enter theobtained data. Depending on the model used for the analysis, the next steps mayvary when it comes to entering the data in. An analysis plan should be createdprior to entering in the data, and that plan will determine which model is usedfor entering the variables (“The 13 Steps,” n.d.
). The model should then be ranaccording to the analysis plan. While this model may not be the final model, itshould closely resemble the right kind of model to best fit the variables,design, and the research question (“The 13 Steps,” n.d.).The third part of theregression analysis is to edit any predictors and make sure the model used isthe best fit for the analysis. There are a variety of stepwise approaches thatcan be used to best determine predictors for models set up for predictingpurposes. If the model is set up to answer theoretical research questions thenthe model may need to be refined.
If a model needs tobe refined it can be done in a number ways. Interactions and quadratic can betested and if need-be, dropped, to explore non-linearity types of models (“The13 Steps,” n.d.). Control variables that are not obviously significant can alsobe dropped (“The 13 Steps,” n.
d.). Hierarchical modeling can be produced sothat the results from the predictors can be seen by themselves or in groups(“The13 Steps,” n.d.
). Over-dispersion should be checked and random effects can betested (“The 13 Steps,” n.d.).After refining themodels, data issues need to be checked for and resolved.
This will be checkingfor data issues that are within the models, but are not classified as dataassumptions. Data issues can include: multicollinearity, outliers andinfluential points, data that is missing, truncation and censoring (“The 13Steps,” n.d.). None of these issues will show up until the selected variableshave been chosen and inputted into the model.
Finally, the resultsare interpreted. The results are then used by companies to make smarterbusiness decisions (Gallo, Davenport, Kim, 2017). The results may be used forfinding ways to increase sales (Gallo, Davenport, Kim, 2017). Employeeretention or recruitment can also benefit from regression analysis (Gallo,Davenport, Kim, 2017).
Generally, businesses use it to gain explanations forspecific occurrences that they may not be able to understand or to predict thingsconcerning future outcomes for their business (Gallo, Davenport, Kim, 2017).