Computer Problem Set #2Tables, Covariances and CorrelationsWe will be using the 20% sub-sample of the Manager and Professional data set that you used inyour last computer problem set. You will also want to refer to the UNICON codebook as thisprovides definitions of the variables we will be using in this problem set.1. Creating Tables. Minitab has the capacity to create complex tables and summarize datawithin the categories in the tables. Consider the distribution of managers and professionals bymarital status and by type of employer.a. Marital status is coded as 1 married2 married (spouse absent)3 widowed4 divorced5 separated6 single never marriedRecode this data into married (combine present & absent), previously married(widowed, divorced, separated) and single never married. (Call this nevermarried) Code these as text variables (Data < code, < numeric to text) Title thisvariable marital status MarStat. You will need to associate each number with atext description even if it is repetitive. b. Next we are interested in recoding workcls1 into private, federal, state, localemployer or self employed using numeric to text (Data < code, < numeric totext). The coding for this variable is1 Federal worker2 State worker3 Local worker4 Private for profit5 Private non-profit6 Self Employed7 Self Employed8 Without payBefore doing this, use the tally command (Statistics < Table <Tally) to get thenumber of observations for each of the outcomes. Note that we are a group,“without pay” that is very small and that we likely don’t care much about. Wewould like to remove this group from our data and to do that, we are going to do atwo stage recode; first converting workcls1 variable so that the “without pay”code is missing data ( ‘*’), and then taking the new variable and recoding it intotext data for type of employer. First, using the code command (Data < code, <numeric to numeric) we will recode from workcls1 to temp. Do a numeric tonumeric recode with “8" as the original value and “*” – missing data, as the newvalue. Note that no other values of workclas1 will change. Next do a numeric totext recode placing appropriate names in for the federal, state, local, private andself-employed values. Don’t do anything with the missing data, leave that blank.By the way, you can place 4:5 in the original value position for private and bothwill be coded as private. Similarly for 6:7 for self-employed.c. Now create a table with the number of observations in each of these categories. To do this, go to Stat < Tables < cross-tabs and chi-square. Make the classification variables so that EmpType are the rows and MarStat arethe columns and check off counts. Your table should be organized so that therows are federal, local, private, and self employed state and the columns aremarried, never married and previouslymarried. The ordering of the outcomesdoesn’t really matter but, as usual, MINITAB reverts to alphabetical ordering. Also, although the tables display missing data, it is not included in any of thecalculations.How many private managers were married? How many federal managers andprofessionals were never married?How many private managers are self employed?What is the most common joint status (marital and employment sector)?What is the number for self-employed in the bottom row (labeled all)? How doyou interpret this? What is the number for married in the right hand column(labeled all)? How do you interpret this? d. Now calculate distributional statistics. Uncheck the count box and check the totalpercent box.How do you interpret the percentages which are produced? What is thepercentage for married private sector employees? What does this mean? What isthe percentage for never married federal employees? What does this mean? What is the number for married in the right hand column (labeled all)? How doyou interpret this? What is the number for self-employed in the bottom row Allcolumn? How do you interpret this?e. Uncheck the total percentage box and check the column percentage box. What isthe percentage for married federal managers? What is the percentage for marriedlocal managers? What is the percentage for married private sector managers? What is the percentage for married self employed managers? For married statemangers? What is the sum of these percentages? What is the interpretation of thepercentage for married private sector managers? Why is this called a conditionalprobability?What is the percentage for married in the bottom row (ALL)? What is themeaning of this percentage? Why do we call it an unconditional percentage? Why is it called a marginal percentage? f. Now uncheck the column percentage box and check the row percentage box. What is the percentage for married private sector managers? For previouslymarried private sector managers? For never married private sector managers? How do you interpret the percentage for married private sector managers? Why isit referred to as a conditional probability? Why is it different from the percentagein the private sector married cell in part (e). Why do the percentages for married,previously married and never married private sector managers sum to 100%?What is the percentage for married in the bottom row (ALL)? What is themeaning of this percentage? Why do we call it an unconditional probability ? Why is it called a marginal percentage? g. Now lets learn about how to use tables to get conditional information about othervariables. We are interested in managers and professionals earnings by maritalstatus and employment type. Go toStat < Tables < descriptive statistics. Put employment status in as the row variable and marital status in as the columnvariable. Next go to associated variablesand put in weekearn (usual weekly earnings). Under display check both the meanand median boxes. Create your table. How does mean and median pay formarried federal managers compare with that of married private sector managers? How does mean and median pay for divorced federal managers compare with thatof married federal managers?Now consider the marginals. Turning first to the right hand column, how doesfederal pay compare with private sector pay? Why are these means and mediansdifferent from those of married federal and private sector managers?Continuing with the marginals, compare the weekly earnings of married anddivorced managers. Why are these different from the comparison of the