For $200$ completed projects, they recorded the programmer team$$s synchronicity and distribution, the project manager$$s experience, the project$$s stability and requirements complexity, and its base and allocated programming time. Each project$$s outcome is classified as either a success or failure based on whether it met the required scope, budget, and schedule. Mrs$.$ Wren hopes to utilize this data to create a model that will allow them to better select projects.

Assignment Questions:

$1)$ Conduct basic exploratory analysis on the raw data.

a$)$ Create a new variable, Allocated Time Raio, that is equal to each project's Allocated Coding Time divided by its Base Coding Time.

Note: Allocated Time and Base Coding Time should not be used directly in the rest of the analysis.

b$)$ Determine the mean, median, standard deviation and range for each numerical variable.

c$)$ Create a histogram for each numerical variable.

$-$ Select column, Insert $>$ Charts $>$ Statistic Chart $>$Histogram

$-$ Note: You may need to right$-$click on the horizontal axis, select "Format axis $..."$ and then choose either a narrower "Bin width" or more "Number of bins" to see the shape better.

d$)$ Does anything stand out in $($b$)$ or $($b$)?$

$2)$ Consider a model for the success $($or not$)$ of a project based on the programming team's synchronicity and distribution, the project manager's experience, the project's stability and requirements complexity, and the allocated time ratio.

Note: Linear regression is not appropriate for this case.

a$)$ What are your dependent and independent variables $($raw or created$)?$

b$)$ Provide the equation for the $($assumed$)$ actual model. $3)$ Check the data for multicollinearity.

a$)$ Calculate the appropriate measures.

b$)$ What, if anything, should be removed from the model?

c$)$ Repeat $($a$)$ and $($b$),$ as needed.

Note: Part $($a$)$ can be shortcut by calling the Real$-$Statistic function VIF$()$ in any cell $($type it like any other Excel function$)$ and selecting the independent variable columns $($no headers$).$ This will generate a list of VIF measures in the same order as the columns in the data selected.

$4)$ Estimate and interpret the model in $(2)($less any variable$($s$)$ removed in $(3)).$

a$)$ Provide the estimated regression equation based on the provided sample.

b$)$ Interpret the estimated coefficients $($intercept$,$ slopes$)$ generated.

c$)$ Assess the fit of the model to the data and its overall significance.

d$)$ Assess the individual significance of each independent variable within your multivariate model $($not in a separate univariate model for each.$)$

$5)$ Based on the output in $(4),$ should the feature set $($independent variables$)$ be reduced?

a$)$ Determine if$/$which variable should be removed and re$-$estimate without it$.$

b$)$ Reassess and repeat, if necessary.

Note: Just provide the independent variable table $($variables$,$ coefficients, Wald Statistics, p$-$values$)$ at each step, as well as your justification for selecting each variable to remove.