BUSINESS ANALYTICS

1)  In the Airline Baggage Complaint Case Study, your team calculated Baggage%.  Explain why it was necessary to introduce this as a variable into the original data set.  How was it calculated (provide a formula)?

It was crucial to introduce baggage to the original data set so that it will be easier to access the exact amount of the customer complaints

Formula, Baggage % = {(Hand baggage – checked baggage)/cost} x 100

2)  a) Describe/define time series analysis.  b) Go to Google.com and type in the phrase “DJIA today” and write down the closing value of the Dow Jones Industrial Average on the day you submit this test.  DJIA is a “real world” average.

Time series analysis refers to the gathering of quantitative observations which are timely spaced and measured successfully. Its objective is to identify trends or seasonal variations, predicting any short-term drifts from the preceding patterns, data modeling, quality control, and so on. This is to say that time series are mainly analyzed so as to understand the nature and structure which produces such observations.

Moreover, in order to make sound investment, time series analysis assist in tracking the movement of data points, for instance security price for certain duration of time. Thus, there is no single minimum or maximum duration which ought to be included.

Dow Jones Industrial Average (closing) = $ 20,949.89

3) Explain the statistical procedure called “multiple regression.”  Use the handout on multiple regression to help you answer this question.

Multiple regression is basically an extension of linear regression through which several independent variables (X) are used for the purpose of predicting single dependent variable (Y). The variable to be predicted is regarded as being a linear transformation of the independent variables. The reason for that is to ensure that the square deviations of its sum of the value to be predicted are minimal. Moreover, the interrelationship which exists amongst these variables, it is essential to take them into consideration in terms of the weights which are assigned to each one of them.  Conversely, in some restricted situations, multiple regression is used for the purpose of inferring causal correlation between the dependent and the independent variable.

4) What is multicollinearity?  Use the handout on multiple regression to help you answer this question.

Multicollinearity is a type of regression which mainly occur the independent variable or the predictor variable in the model correlates more highly with the predictor variables as compared to the dependent variable. This regression does not impact the regression formula in case the purpose of the research was aimed at predicting the dependent variables from the independent ones. In addition to that, multicollinearity exists only when more than two predictor variables in the regression model are highly or reasonably interrelated.

5)  In the Housing Prices Case Study, the summaries for each of the simple regression models for the variable, Price, are presented at the bottom of page 2.  List the summaries for Price for each of the models.

            Bedroom @ $77,200

            Bathroom @ $106,900

            Individual squire foot $135

On page 3, comparing the multiple regression model to the three simple regression models reveals that the coefficients have changed. List the coefficients of the new model:

            In the multiple regression model, each bedroom rose from $77200 to $1785

            The price for each bathroom rose from $106,900 to 79900

            In the multiple regression was noted that the value of each squire foot was $21 while in the simple             regression model, its value was $135 per square foot.