Directions: Answer each question completely, showing all your work. Refer to the SPSS tutorials as needed (see all attachments). Copy and Paste the SPSS output into the word document for the calculati
S P S S Tu t o r i a l 01 Chi-Square Goodness-of-Fit Te s t The chi-square goodness-of-fit test is used to determine if a distri- bution of scores for one nominal variable meets expectations. The data collected is counts or frequency of occurrence at a particu- lar level of the nominal variable. To explore this test, consider the following example.Example:
Sickness is claimed to be a random event, thus one would expect that the proportion of sick days taken would be equally spread throughout the work week. We would like to test this claim for a particular company in Phoenix, Arizona. The following is a sam- ple of the number of individuals who called in on the different days last year. The analysis can be performed in SPSS. To do this, first we must enter the data into the data editor. You will need two columns.
One for the nominal variable, Day, and one for the count, Call_Ins. When frequencies are entered into SPSS such as the case here with the number of call_ins per day of the week, you must tell SPSS that are being entered rather than raw data. To do this the Weight Case command must be used. Click on Data then Weight Cases . 02 In the pop up window, select weight cases by and then move the Call_Ins variable over to Frequency variable . Then click OK. 03 Now the analysis can begin by selecting Analysis – Nonparametric Tests – One Sample. There are three tabs in the One-sample Nonparametric Tests window. Select the Fields tab. Ensure that Day is in the Test Fields box and then select the Settings tab. 04 Select Customize tests. Choose Compare observed probabilities to hypothesized (Chi-Square test) . Then click on the options box. The default is All categories have equal probability . This is what is needed for this test, as we are interested in determining if the number of call-ins is the same for each day of the week. Click OK and then Run. 05 The output window will populate with the results of the test. Double click on the Hypothesis Test Sum- mary to get a more detailed output. 06 The chi-square test statistic is 6.662 with a p-value of .156. Since this p-value is greater than the assumed level of significance of 0.05, this is not a significant result. This suggest there is not a statistically signifi- cant difference in the number of call_ins on the different days of the week at a level of significance of 0.05.
