Assignment 2 – Descriptive Statistics, Correlation Analysis, Regression Analysis

In assignment 1, you familiarized yourself with SPSS and reminded yourself of descriptive statistics analysis and correlation analysis. In this assignment, I’m asking that you add multiple regression analysis. You covered multiple regression in your QA classes. If you don’t remember anything about multiple regression analysis, do some reviewing.

Your purpose in this assignment is to investigate the impact of Just-in-Time (JIT), Total Quality Management (TQM), and Agile Manufacturing (AM) strategies on the operational performance (OP) of manufacturing organizations. In other words, can manufacturing managers expect to improve OP by implementing JIT, TQM, and AM? You’ve all had an operations management course that discussed the three strategies. If you don’t remember them, do a little reviewing.

1. Access the Assignment_2_Data_OM_OP.sav database.
2. Create a descriptive statistics table by following the command sequence [analyze, descriptive statistics, descriptive, block all variables and move them to the variables box, options, check kurtosis and skewness, continue, OK] . You should now see a descriptive statistics table containing minimums, maximums, means, standard deviations, skewness, and kurtosis statistics. These values are all statistics since you are dealing with a sample (n=320) rather than a population. Copy the descriptive statistics table to a Word file and identify any potential problems associated with non-normality.
   Note: Generally, with the descriptive statistics table we are trying to determine if the variables are normally distributed (skewness and kurtosis values equal to zero). Skewness and kurtosis values between -2.00 and +2.00 indicate that a variable is sufficiently normally distributed.
3. Create a correlation matrix by following this command sequence [analyze, correlate, bivariate, block all variables and move them to the variables box, okay]. Copy the correlation matrix from SPSS to your Word file and interpret each of the correlation coefficients (JIT and OP, TQM and OP, AM and OP) in terms of type, strength, and significance level based on the information in the note below .
   Note: A correlation coefficient (R) measures the relationship between two variables. It can have values f rom -1 to +1. A coefficient with a value of zero means that the two variables are not related. A coefficient with a negative value means that the two variables are inversely related (as one goes up, the other goes down). A coefficient with a positive value means that the two variables are positively related (as one goes up, the other goes up). The closer the coefficient’s value to -1 or +1 the stronger the relationship between the variables. Absolute coefficients with values less than or equal to .25 are weak, between .26 and .50 are moderate , between .51 and .75 are strong, and between .76 and 1.00 are very strong. Because you are trying to determine whether the coefficient is significantly different from zero, you need to know the significance level. Note that SPSS tells you if the coefficient is significant at either the .01 level (**) or .05 level (*). If a coefficient is not significantly different from zero, SPSS displays no asterisks.
4. Conduct a multiple regression analysis for the multiple regression model with JIT, TQM, and A M as independent variables and OP as the dependent variable using the following command sequence [analyze, regression, linear, move OP to the dependent variable block, move JIT and TQM and AM to the independent variable block, OK ]. You are conducting multiple linear regression analysis. This means that there are multiple independent variables. Note that four tables are generated. Only the model summary table and coefficients table are of interest. Copy the model summary table to the Word document and interpret the R ² value according to the information provide in note below .
   Note: The coefficient of determination (R ² ) can have values from 0 to +1 (the closer to +1, the stronger the relationship). It can be more easily interpreted, however. For example, if the R ² for the relationship between variables X and Y is .64, the interpretation would be "The variation is X explains 64% of the variation in Y." In this case there are three independent variables JIT , TQM , and AM .
   So, your interpretation will go like this "JIT, TQM , and AM combine to explain __% of the variation in OP."
5. Copy the coefficients table to the Word document. Formulate the regression equation from the unstandardized regression coefficients (in the B column) using the information provided in note below .
   
   Note : The multiple linear regression formula takes this general form: OP = b0 + b1* JIT + b2* TQM + b3* AM , where OP is the dependent variable, b0 is the Y-intercept (constant) ; b1, b2, and b3 are the unstandardized regression coefficients; and JIT , TQM , and AM are values of the independent variable s . Look in the B column of the coefficients table to find the values for b0 , b1, b2, and b3. There is no calculation required in this step. Just replace b0, b1, b2, and b3 in the general form with the values from the B column.
   Interpret the significance levels for the regression coefficients using the information provided in note below .
   Note: Look to the far right in the coefficients table to the significance column (Sig.) . You are trying to determine if the regression coefficients are significantly different from 0. Here are the decision rules:
   1. If the computed significance level (Sig.) in the significance column is .01 or less, the regression coefficient is significantly different at the .01 level.
   2. If the computed significance level (Sig.) is greater than .01 but less than or equal to .05, the regression coefficient is significantly different at the .05 level.
   3. If the computed significance level (Sig.) is greater than .05, conclude that the regression coefficient is not significantly different from zero.
6. Use the regression formula to predict OP if JIT is 1 .0 , TQM is 1 .0 , and AM is 1 .0 . Now, predict OP if JIT, TQM, and AM are 7 .0. In other words, what i s the organization’s performance level if they have relatively low levels ( 1 .0) of JIT, TQM , and AM versus relatively high levels ( 7 .0) ?
7. Answer this question: " What do you conclude from the results of the correlation and regression analyses of the relationship between OP and JIT, TQM , and AM ? "

This is the most important step! Managers are constantly trying to identify strategies that improve the performance of their organizations. Are managers wise to implement JIT , TQM , and AM for their organizations? Support your answer with the results of the statistical analysis.

Price: $20.68

Solution: The downloadable solution consists of 6 pages, 1468 words.
Deliverable: Word Document