Ch.

12
Analysis and Interpretation of
Data
Novpreti Maharani
Rahadian R. Purnama

Topics Discussed GETTING DATA READY FOR ANALYSIS • Editing Data • Handling Blank Responses • Coding • Categorizing • Entering Data DATA ANALYSIS • Basic Objectives in Data Analysis • Feel for the Data • Testing Goodness of Data • Hypothesis Testing DATA ANALYSIS AND INTERPRETATION • Use of Several Data-Analytic Techniques • Descriptive Statistics • Inferential Statistics .

301/ pg.Flow Diagram of Data Analysis Process pg. 169 .

they need to be edited. the data coded. and a categorization scheme has to be set up. Each of these stages of data preparation is discussed below. • The data will then have to be keyed in. and some software program used to analyze them.Getting Data Ready For Analysis • After data are obtained through questionnaires. . or through secondary sources. • The blank responses. if any. observation. have to be handled in some way. interviews.

tematically in its entirety. especially when they relate to responses to openended questions of interviews and questionnaires. Lack of clarity at this stage will result later in confusion. or researcher in a hurry must be clearly deciphered so that it may be coded sys. information that may have been noted down by the interviewer.Getting Data Ready For Analysis • Editing Data • Data have to be edited. In other words. . observer. or unstructured observations.

say. assign the midpoint in the scale as the response 2. 30 or more items.Getting Data Ready For Analysis • Handling Blank Responses • If a substantial number of ques. • a way to handle a blank response : 1.tions—say. In this event. we need to decide how these blank responses are to be handled. only two or three items are left blank in a questionnaire with. 3. allow the computer to ignore the blank responses when the analyses are done. however. it may be a good idea to throw out the questionnaire and not include it in the data set for analysis. 4. it is important to mention the number of Returned but unused responses due to excessive missing data in the final report submitted to the sponsor of the study. If. give the missing response a random number within the range for that scale. 25% of the items in the questionnaire—have been left unanswered. give the item the mean of the responses of this particular respondent to all other questions measuring this variable. .

Getting Data Ready For Analysis • Coding • Coding the Serakan Co. Data (Case) • In the Serakan Co. we have 5 demographic variables and 16 items measuring involvement and satisfaction as shown in Table 12.1. . questionnaire.

Getting Data Ready For Analysis • Coding .

Work shift can be coded 1 to 3.Getting Data Ready For Analysis • Coding • • • The responses to the demographic variables can be coded from 1 to 5 for age. If. it would be easy to transfer them to the code sheet. Items numbered 6 to 21 on the questionnaire can be coded by using the actual number circled by the respondents. we would code it as 4. for instance. since numbers were given within the boxes for all the above items (instead of simply putting a box for marking the appropriate one). depending on which box in the columns was checked by the respondent. if 4 was circled. . and 1 to 6 for the variables of education and job level. For example. and so on. or directly key in the data. Sex can be coded as 1 or 2 depending on whether the response was from a male or a female. 3 had been circled for the first question. coding can become simple. It is easy to see that when some thought is given to coding at the time of designing the questionnaire. and employment status as either 1 or 2. then the response will be coded as 3.

a response of 7 on a 7-point scale. data. 6 as 2. and 1 as 7. . which actually is a 1 on the 7-point scale. items 16 to 21 will have to be recoded such that scores of 7 are read as 1. 2 as 6. 3 as 5.‖ really means ―strongly disagree. This can be done on the computer through a Transform and RECODE statement. Thus the item has to be reversed so as to be in the same direction as the positively worded questions. 5 as 3. • In the Serakan Co.Getting Data Ready For Analysis • Categorization • Note that with respect to negatively worded questions. with 7 denoting ―strongly agree.

Raw data can be entered through any soft.ware program. edit. It is possible to add. which looks like a spread. Once the missing values. can enter. It is also easy to compute the new variables that have been categorized earlier. the recodes. All missing val. the SPSS Data Editor. . the data are ready for analysis.ables are taken care of. using the Compute dialog box. which can be directly entered into the computer as a data file. or delete values easily after the data have been entered. Each row of the editor represents a case. change.Getting Data Ready For Analysis • Entering Data • • If questionnaire data are not collected on scanner answer sheets. which opens when the Transform icon is chosen. and view the contents of the data file. the raw data will have to be manually keyed into the computer. For instance. and each column represents a variable. and the computing of new vari.sheet.ues will appear with a period (dot) in the cell.