Looking for:
Spss survival manual 6th edition download |
Welcome to the SPSS Survival Manual website.Welcome to the SPSS Survival Manual website
(PDF) SPSS SURVIVAL MANUAL | SHAHRIL IZWAN - .
Both of these factors can influence the quality of the data you obtain. When reviewing possible scales to use, you should collect information on the reliability and validity of each of the scales. No matter how good the reports are concerning the reliability and validity of your scales, it is important to pilot-test them with your intended sample. Sometimes scales are reliable with some groups e. Reliability The reliability of a scale indicates how free it is from random error.
The test-retest reliability of a scale is assessed by administering it to the same people on two different occasions, and calculating the correlation between the two scores obtained. High test-retest correlations indicate a more reliable scale. You need to take into account the nature of the construct that the scale is measuring when considering this type of reliability.
A scale designed to measure current mood states is not likely to remain stable over a period of a few weeks. The test-retest reliability of a mood scale, therefore, is likely to be low. You would, however, hope that measures of stable personality characteristics would stay much the same, showing quite high test-retest correlations.
The second aspect of reliability that can be assessed is internal consistency. This is the degree to which the items that make up the scale are all measuring the same underlying attribute i. Internal consistency can be measured in a number of ways. This statistic provides an indication of the average correlation among all of the items that make up the scale. Values range from 0 to 1, with higher values indicating greater reliability.
While different levels of reliability are required, depending on the nature and purpose of the scale, Nunnally recommends a minimum level of. Cronbach alpha values are dependent on the number of items in the scale. When there are a small number of items in the scale fewer than 10 , Cronbach alpha values can be quite small. In this situation it may be better to calculate and report the mean inter-item correlation for the items. Optimal mean inter-item correlation values range from.
Validity The validity of a scale refers to the degree to which it measures what it is supposed to measure.
The validation of a scale involves the collection of empirical evidence concerning its use. The main types of validity you will see discussed are content validity, criterion validity and construct validity. Content validity refers to the adequacy with which a measure or scale has sampled from the intended universe or domain of content. Criterion validity concerns the relationship between scale scores and some specified, measurable criterion.
Construct validity involves testing a scale not against a single criterion but in terms of theoretically derived hypotheses concerning the nature of the underlying variable or construct. The construct validity is explored by investigating its relationship with other constructs, both related convergent validity and unrelated discriminant validity.
An easy-to-follow summary of the various types of validity is provided in Streiner and Norman If you intend to use scales in your research, it would be a good idea to read further on this topic: see Kline for information on psychological tests, and Streiner and Norman for health measurement scales. Bowling also has some great books on health and medical scales. This may involve obtaining demographic information from participants prior to exposing them to some experimental manipulation.
Alternatively, it may involve the design of an extensive survey to be distributed to a selected sample of the population. A poorly planned and designed questionnaire will not give good data with which to address your research questions. In preparing a questionnaire, you must consider how you intend to use the information; you must know what statistics you intend to use. Depending on the statistical technique you have in mind, you may need to ask the question in a particular way, or provide different response formats.
Some of the factors you need to consider in the design and construction of a questionnaire are outlined in the sections that follow. This section only briefly skims the surface of questionnaire design, so I would suggest that you read further on the topic if you are designing your own study.
A really great book for this purpose is De Vaus Question types Most questions can be classified into two groups: closed or open-ended. A closed question involves offering respondents a number of defined response choices. They are asked to mark their response using a tick, cross, circle, etc. For example: What is the highest level of education you have completed?
Primary school 2. Some secondary school 3. Completed secondary school 4. Trade training 5. Undergraduate university 6. For example, Yes can be coded as a 1, No can be coded as a 2; Males as 1, Females as 2. In the education question shown above, the number corresponding to the response ticked by the respondent would be entered. For example, if the respondent ticked Undergraduate university, this would be coded as a 5.
Numbering each of the possible responses helps with the coding process. For data entry purposes, decide on a convention for the numbering e. Sometimes you cannot guess all the possible responses that respondents might make—it is therefore necessary to use open-ended questions.
The advantage here is that respondents have the freedom to respond in their own way, not restricted to the choices provided by the researcher. For example: What is the major source of stress in your life at the moment? These categories are usually identified after looking through the range of responses actually received from the respondents.
Some possibilities could also be raised from an understanding of previous research in the area. Each of these response categories is assigned a number e. More details on this are provided in the section on preparing a codebook in Chapter 2.
Sometimes a combination of both closed and open-ended questions works best. This involves providing respondents with a number of defined responses, and also an additional category other that they can tick if the response they wish to give is not listed. A line or two is provided so that they can write the response they wish to give. This combination of closed and open-ended questions is particularly useful in the early stages of research in an area, as it gives an indication of whether the defined response categories adequately cover all the responses that respondents wish to give.
Response format In asking respondents a question, you also need to decide on a response format. The type of response format you choose can have implications when you come to do your statistical analysis.
Some analyses e. If you had asked respondents to indicate their age by giving them a category to tick e. So, if you intend to explore the correlation between age and, say, self-esteem, you will need to ensure that you ask respondents for their actual age in years. Try to provide as wide a choice of responses to your questions as possible. You can always condense things later if you need to see Chapter 8.
You will need to make a decision concerning the number of response steps e. DeVellis has a good discussion concerning the advantages and disadvantages of different response scales. Whatever type of response format you choose, you must provide clear instructions. Do you want your respondents to tick a box, circle a number, make a mark on a line?
For some respondents, this may be the first questionnaire that they have completed. Give clear instructions, provide an example if appropriate, and always pilot-test on the type of people that will make up your sample. Iron out any sources of confusion before distributing hundreds of your questionnaires. In designing your questions, always consider how a respondent might interpret the question and all the possible responses a person might want to make.
For example, you may want to know whether people smoke or not. You might ask the question: Do you smoke? Is knowing whether they smoke enough? The message here is to consider each of your questions, what information they will give you and what information might be missing. Wording the questions There is a real art to designing clear, well-written questionnaire items. Although there are no clear-cut rules that can guide this process, there are some things you can do to improve the quality of your questions, and therefore your data.
For further suggestions on writing questions, see De Vaus and Kline The flow chart shown on the next page outlines the main steps that are needed. In this chapter I will lead you through the process of creating a data file and entering the data. The first step is to check and modify, where necessary, the options that IBM SPSS uses to display the data and the output that is produced. The final step is to enter the data—that is, the values obtained from each participant or respondent for each variable.
To illustrate these procedures I have used the data file survey. The codebook used to generate these data is also provided in the Appendix. You can set up a basic data file on Excel and enter the data at home. The instructions for using Excel to enter the data are provided later in this chapter. The options allow you to define how your variables will be displayed, the type of tables that will be displayed in the output and many other aspects of the program. Some of this will seem confusing at first, but once you have used the program to enter data and run some analyses you may want to refer back to this section.
If you are sharing a computer with other people e. Sometimes other students will change these options, which can dramatically influence how the program appears. It is useful to know how to change things back to the way you want them. To open the Options screen, click on Edit from the menu at the top of the screen and then choose Options. The screen shown in Figure 4. I have described the key ones below, organised by the tab they appear under.
To move between the various tabs, just click on the one you want. General tab When you come to do your analyses, you can ask for your variables to be listed in alphabetical order or by the order in which they appear in the file.
I always use the file order, because this is consistent with the order of the questionnaire items and the codebook. To keep the variables in file order, just make sure the option File in the Variable Lists section is selected. Figure 4. This will stop you getting some very strange numbers in your output for the statistical analyses. Data tab Click on the Data tab to make changes to the way that your data file is displayed. If your variables do not involve values with decimal places, you may like to change the display format for all your variables.
This means that all new variables will not display any decimal places. This reduces the size of your data file and simplifies its appearance. Output tab The options in this section allow you to customise how you want the variable names and value labels displayed in your output. In the very bottom section under Variable values in labels are shown as: choose Values and Labels from the dropdown options.
This will allow you to see both the numerical values and the explanatory labels in the tables that are generated in the Viewer window. In the section labelled Output Display choose Pivot tables and charts. Under the Pivot Tables tab you can choose the format of these tables from an extensive list. It is a matter of experimenting to find a style that best suits your needs. I use a style called CompactBoxed as this saves space and paper when printing. One other option you might find useful is at the bottom of the Pivot Tables tab—labelled Copying wide tables to the clipboard in rich text form.
Click on the drop-down box and select Shrink width to fit. This is useful when you are pasting output from IBM SPSS to Microsoft Word and the results are too wide for the page a common problem in some of the statistical procedures presented later in the book. You can change the table styles as often as you like—just remember that you have to change the style before you run the analysis. You cannot change the style of the tables after they appear in your output, but you can modify many aspects e.
This can be activated by double-clicking on the table that you wish to modify. Once you have made all the changes you wish to make on the various Options tabs, click on OK. You can then proceed to define your variables and enter your data.
You will do this in the Data Editor window see Figure 4. You can move between these two views using the little tabs at the bottom left-hand side of the screen. You will notice that in the Data View window each of the columns is labelled var see Figure 4.
These will be replaced with the variable names that you listed in your codebook. Down the side you will see the numbers 1, 2, 3 and so on. These are not the same as your ID numbers, and these case numbers change if you sort your file or split your file to analyse subsets of your data.
Procedure for defining your variables To define each of the variables that make up your data file, you first need to click on the Variable View tab at the bottom left of your screen. In this view see Figure 4. Your job now is to define each of your variables by specifying the required information for each variable listed in your codebook.
Some of the information you will need to provide yourself e. These default values can be changed if necessary. The key pieces of information that are needed are described below. The headings I have used correspond to the column headings displayed in the Variable View. I have provided the simple step-by-step procedures below; however, there are a number of shortcuts that you can use once you are comfortable with the process.
You should become familiar with the basic techniques first. Keep these variable names as short as possible, not exceeding 64 characters. Each variable name must be unique, must start with a letter, and cannot contain spaces or symbols. For ideas on how to label your variables, have a look at the codebooks provided in the Appendix.
These list the variable names used in data files that accompany this book see p. Type The default value for Type that will appear automatically as you enter your first variable name is Numeric. For most purposes, this is all you will need to use. There are some circumstances where other options may be appropriate. For example, if you need to enter text information e. A Date option is also available if your data includes dates.
To change the variable type, click in the cell and a box with three dots should appear giving you the options available. You can also use this window to adjust the width of the variable and the number of decimal places.
Width The default value for Width is 8 unless this has been changed using the Options instructions presented earlier in this section. This is usually sufficient for most data. If your variable has very large values or you have requested a string variable , you may need to change this default value; otherwise, leave it as is. Decimals The default value for Decimals is usually 2 however, this can be changed using the Options facility described earlier in this chapter.
If your variable has decimal places, adjust this to suit your needs. Label The Label column allows you to provide a longer description for your variable than used in the Name column. Values In the Values column you can define the meaning of the values you have used to code your variables. I will demonstrate this process for the variable Sex. Click in the cell under the heading Values for the variable you wish to specify. A box with three dots should appear on the right-hand side of the cell.
This opens the Value Labels dialogue box. Click in the box marked Value. Type in 1. Click in the box marked Label.
Type in Male. Click on Add. Repeat for females: Value: enter 2, Label: enter Female. When you have finished defining all the possible values as listed in your codebook , click on OK. Missing Sometimes researchers assign specific values to indicate missing values for their data. So if you intend to leave a blank when a piece of information is not available, it is not necessary to do anything with this Variable View column.
If you do intend to use specific missing value codes e. Click in the cell and then on the shaded box with three dots that appears. Choose the option Discrete missing values and type the value e. Up to three values can be specified. Click on OK.
If you are using these special codes, it is also a good idea to go back and label these values in the Values column. Columns The default column width is usually set at 8, which is sufficient for most purposes. Change it only if necessary to accommodate your values or long variable names.
There is no need to change this. Measure The column heading Measure refers to the level of measurement of each of your variables. The default is Scale, which refers to continuous data measured at interval or ratio level of measurement.
If your variable consists of categories e. Choose Nominal for categorical data and Ordinal if your data involve rankings or ordered values e. It is important that you set the measurement levels of your variables correctly otherwise SPSS will stop you using some of the procedures e.
Role There is no need to make any changes to this section. Just leave as the default, Input. Optional shortcuts The process described above can be rather tedious if you have a large number of variables in your data file. There are a number of shortcuts you can use to speed up the process. Copying variable definition attributes to one other variable 1.
In Variable View, click on the cell that has the attribute you wish to copy e. From the menu, click on Edit and then Copy.
Click on the same attribute cell for the variable you wish to apply this to. From the menu, click on Edit and then Paste. Copying variable definition attributes to a number of other variables 1.
Click on the same attribute cell for the first variable you wish to copy to and then, holding your left mouse button down, drag the cursor down the column to highlight all the variables you wish to copy to.
Setting up a series of new variables all with the same attributes If your data consists of scales made up of a number of individual items, you can create the new variables and define the attributes of all of these items in one go. The procedure is detailed below, using the six items of the Optimism Scale as an example optim1 to optim6.
If you want to practise this as an exercise, you should start a new data file File, New, Data. In Variable View, define the attributes of the first variable optim1 following the instructions provided earlier. With the Variable View selected, click on the row number of this variable this should highlight the whole row. From the menu, select Edit and then Copy. Click on the row number of the next empty row.
From the menu, select Edit and then Paste Variables. In the dialogue box that appears, enter the number of additional variables you want to add in this case, 5.
Enter the prefix you wish to use optim and the number you wish the new variables to start on in this case, 2. This will give you five new variables optim2, optim3, optim4, optim5 and optim6. To set up all of the items in other scales, just repeat the process detailed above e. Remember, this procedure is suitable only for items that have all the same attributes; it is not appropriate if the items have different response scales e.
Make sure you have your codebook ready. Procedure for entering data 1. To enter data, you need to have the Data View active. Click on the Data View tab at the bottom left-hand side of the screen of the Data Editor window. A spreadsheet should appear with your newly defined variable names listed across the top. Click on the first cell of the data set first column, first row. Type in the number if this variable is ID, this should be 1.
Press the right arrow key on your keyboard; this will move the cursor into the second cell, ready to enter your second piece of information for case number 1. Move across the row, entering all the information for case 1, making sure that the values are entered in the correct columns. To move back to the start, press the Home key on your keyboard on some computers you may need to hold the Ctrl key or the Fn key down and then press the Home key. Press the down arrow to move to the second row, and enter the data for case 2.
If you make a mistake and wish to change a value, click in the cell that contains the error. Type in the correct value and then press the right arrow key. After you have defined your variables and entered your data, your Data Editor window should look something like that shown previously in Figure 3. If you have entered value labels for some of your variables e.
To do this, click on View from the menu and select the option Value Labels. This option can also be activated during the data entry process so that you can choose an option from a drop-down menu, rather than typing a number in each cell.
This is slower, but does ensure that only valid numbers are entered. To turn this option off, go to View and click on Value Labels again to remove the tick.
Make sure you have the Data Editor window open on the screen, showing Data View. Delete a case Move down to the case row you wish to delete. Position your cursor in the shaded section on the left-hand side that displays the case number. Click once to highlight the row. Press the Delete button on your computer keyboard. You can also click on the Edit menu and click on Clear. Insert a case between existing cases Move your cursor to a cell in the case row immediately below where you would like the new case to appear.
Click on the Edit menu and choose Insert Cases. An empty row will appear in which you can enter the data of the new case. Delete a variable Position your cursor in the shaded section which contains the variable name above the column you wish to delete.
Click once to highlight the whole column. Press the Delete button on your keyboard. Insert a variable between existing variables Position your cursor in a cell in the column variable to the right of where you would like the new variable to appear.
Click on the Edit menu and choose Insert Variable. An empty column will appear in which you can enter the data of the new variable. Highlight the variable you wish to move by clicking in the left-hand margin. Click and hold your left mouse button and then drag the variable to the new position a red line will appear as you drag.
Release the left mouse button when you get to the desired spot. Excel usually comes as part of the Microsoft Office package.
If you intend to use this option you should have at least a basic understanding of Excel, as this will not be covered here. Step 1: Set up the variable names Set up an Excel spreadsheet with the variable names in the first row across the page. Step 2: Enter the data 1. Enter the information for the first case on one line across the page, using the appropriate columns for each variable.
Repeat for each of the remaining cases. Remember to save your file regularly. Click on File, Save. Type in an appropriate file name. After you have entered the data, save and close your file.
In the section labelled Files of type, choose Excel. Excel files have a. Find the file that contains your data. Click on it so that it appears in the File name section.
Click on the Open button. A screen will appear labelled Opening Excel Data Source. Make sure there is a tick in the box Read variable names from the first row of data. The data will appear on the screen with the variable names listed across the top.
Choose File, and then Save As from the menu at the top of the screen. The SPSS Survival Manual throws a lifeline to students and researchers grappling with this powerful data analysis software. In her bestselling guide, Julie Pallant guides you through the entire research process, helping you choose the right data analysis technique for your project. From the formulation of research questions, to the design of the study and analysis of data, to reporting the results, Julie discusses basic and advanced statistical techniques.
She outlines each technique clearly, with step-by-step procedures for performing the analysis, a detailed guide to interpreting data output and an example of how to present the results in a report. Once you have made all the changes you wish to make on the various options tabs, click on OK. You can then proceed to define your variables and enter your data. You will do this in the Data Editor window see Figure 4. You can move between these two views using the little tabs at the bottom left-hand side of the screen.
The Variable View is a new SPSS feature, designed to make it easier to define your variables initially and to make changes later as necessary. You will notice that in the Data View window each of the columns is labelled var see Figure 4. These will be replaced with the variable names that you listed in your codebook.
Down the side you will see the numbers 1, 2, 3 and so on. These are the case numbers that SPSS assigns to each of your lines of data. These are NOT the same as your ID numbers, and these case numbers may change if, for example, you sort your file or split your file and analyse subsets of your data.
In this view see Figure 4. Some of the information you will need to provide yourself e. These default values can be changed if necessary. The key pieces of information that are needed are described below.
The headings I have used correspond to the column headings displayed in the Variable View. I have provided the simple step-by-step procedures below; however, there are a number of shortcuts that you can use once you are comfortable with the process. You should become familiar with the basic techniques first. Name In this column, type in the variable name that will be used to identify each of the variables in the data file.
These should be listed in your codebook. Each variable name must be unique. For ideas on how to label your variables, have a look at the codebooks provided in the Appendix. These list the variable names used in the two data files that accompany this book see p. Type The default value for Type that will appear automatically as you enter your first variable name is Numeric.
For most purposes this is all you will need to use. There are some circumstances where other options may be appropriate. If you do need to change this, click on the right-hand side of the cell, where there are three dots. This will display the options available. If your variable can take on values including decimal places, you may also need to adjust the number of decimal places displayed. Width The default value for Width is 8. This is usually sufficient for most data.
If your variable has very large values you may need to change this default value, otherwise leave it as is. Decimals The default value for Decimals which I have set up using the Options facility described earlier in this chapter is 0. If your variable has decimal places, change this to suit your needs.
If all your variables require decimal places, change this under Options using the Data tab. This will save you a lot of time manually changing each of the variables. Label The Label column allows you to provide a longer description for your variable than the eight characters that are permitted under the Variable name. Values In the Values column you can define the meaning of the values you have used to code your variables.
Click on the three dots on the right-hand side of the cell. This opens the Value Label dialogue box. Click in the box marked Value. Type in 1. Click in the box marked Value Label. Type in Male. Click on Add. When you have finished defining all the possible values as listed in your codebook , click on Continue. Missing Sometimes researchers assign specific values to indicate missing values for their data.
This is not essential—SPSS will recognise any blank cell as missing data. So if you intend to leave a blank when a piece of information is not available, it is not necessary to do anything with this Variable View column. Columns The default column width is usually set at 8.
This is sufficient for most purposes— change it only if necessary to accommodate your values. To make your data file smaller to fit more on the screen , you may choose to reduce the column width. Just make sure you allow enough space for the width of the variable name. There is no real need to change this.
Measure The column heading Measure refers to the level of measurement of each of your variables. The default is Scale, which refers to an interval or ratio level of measurement. If your variable consists of categories e. Choose Nominal for categorical data, and Ordinal if your data involve rankings, or ordered values. Chapter 4 Creating a data file and entering data 33 Optional shortcuts The process described above can be rather tedious if you have a large number of variables in your data file.
There are a number of shortcuts you can use to speed up the process. Copying variable definition attributes to one other variable 1. In Variable View click on the cell that has the attribute you wish to copy e. From the menu, click on Edit and then Copy. Click on the same attribute cell for the variable you wish to apply this to.
From the menu, click on Edit and then Paste. Copying variable definition attributes to a number of other variables 1. Click on the same attribute cell for the first variable you wish to copy to and then, holding your left mouse button down, drag the cursor down the column to highlight all the variables you wish to copy to. Setting up a series of new variables all with the same attributes If your data consist of scales made up of a number of individual items, you can create the new variables and define the attributes of all of these items in one go.
The procedure is detailed below, using the six items of the Optimism scale as an example op1 to op6 : 1. In Variable View define the attributes of the first variable op1 following the instructions provided earlier.
With the Variable View selected, click on the row number of this variable this should highlight the whole row. From the menu, select Edit and then Copy. Click on the next empty row. From the menu, select Edit and then Paste Variables. In the dialogue box that appears enter the number of additional variables you want to add in this case 5.
Enter the prefix you wish to use op and the number you wish the new variables to start on in this case 2. Click on OK. This will give you five new variables op2, op3, op4, op5 and op6.
To set up all of the items in other scales, just repeat the process detailed above for example, to create the items in the Self-esteem scale I would repeat the same process to define sest1 to sest Remember this procedure is suitable only for items that have all the same attributes; it is not appropriate if the items have different response scales e. Entering data Once you have defined each of your variable names and given them value labels where appropriate , you are ready to enter your data.
Make sure you have your codebook ready see Chapter 2. Procedure for entering data 1. To enter data you need to have the Data View active. Click on the Data View tab at the bottom left-hand side of the screen. A spreadsheet should appear with your newly defined variable names listed across the top. Click on the first cell of the data set first column, first row.
A dark border should appear around the active cell. Type in the number if this variable is ID this should be 1, that is case or questionnaire number 1. Press the right arrow key on your keyboard; this will move the cursor into the second cell, ready to enter your second piece of information for case number 1.
Chapter 4 Creating a data file and entering data 35 5. Move across the row, entering all the information for case 1, making sure that the values are entered in the correct columns. To move back to the start, press the Home key on your keypad. Press the down arrow to move to the second row, and enter the data for case 2. If you make a mistake and wish to change a value: Click in the cell that contains the error. The number will appear in the section above the table.
Type the correct value in and then press the right arrow key. After you have defined your variables and entered your data, your Data Editor window should look something like that shown in Figure 4. There are also situations When entering data, where you may need to sort a data file into a specific order, or to split your file remember to save your data to analyse groups separately.
Instructions for each of these actions is given below. To save, Move down to the case row you wish to delete. Position your cursor in the just click on the F i l e menu shaded section on the left-hand side that displays the case number.
Click once and choose S a v e or click on to highlight the row. Press the Delete button on your computer keypad.
You can the icon that looks like a also click on the Edit menu and click on Clear. Click on the Data menu and choose Insert Case. An empty row will appear in which you can enter the data of the new case. To delete a variable Position your cursor in the shaded section which contains the variable name above the column you wish to delete. Click once to highlight the whole column. Press the Delete button on your keypad.
You can also click on the Edit menu and click on Clear. To insert a variable between existing variables Position your cursor in a cell in the column variable to the right of where you would like the new variable to appear. Click on the Data menu and choose Insert Variable. An empty column will appear in which you can enter the data of the new variable. To move an existing variable Create a new empty variable column follow the previous instructions. Click once on the variable name of the existing variable you wish to move.
This should highlight it. Click on the Edit menu and choose Cut. Highlight the new empty column that you created click on the name , then click on the Edit menu and choose Paste. This will insert the variable into its new position. To sort the data file You can ask SPSS to sort your data file according to values on one of your variables e.
Click on the Data menu, choose Sort Cases and specify which variable will be used to sort by. To split the data file Sometimes it is necessary to split your file and to repeat analyses for groups e. Please note that this procedure does not physically alter your file in any permanent manner.
It is an option you can turn on and off as it suits your purposes. You can return the data file to its original order by ID by using the Sort Cases command described above. To split your file 1. Make sure you have the Data Editor window open on the screen. Click on the Data menu and choose the Split File option. Click on Compare groups and specify the grouping variable e. For the analyses that you perform after this split file procedure, the two groups in this case, males and females will be analysed separately.
When you have finished the analyses, you need to go back and turn the Split File option off. To turn the Split File option off 1.
Click on the first dot Analyze all cases, do not create groups. To select cases For some analyses you may wish to select a subset of your sample e. To select cases 1. Click on the Data menu and choose the Select Cases option.
Click on the If condition is satisfied button. Click on the button labelled IF. Choose the variable that defines the group that you are interested in e. Click on the arrow button to move the variable name into the box.
Type in the value that corresponds to the group you are interested in check with your codebook. For example, males in this sample are coded 1, therefore you would type in 1. Click on Continue and then OK. For the analyses e. When you have finished the analyses, you need to go back and turn the Select Cases option off.
To turn the select cases option off 1. Click on the Data menu and choose Select Cases option. Click on the All cases option. If you intend to use this option, you should have at least a basic understanding of Excel, as this will not be covered here.
Step 1: Set up the variable names Set up an Excel spreadsheet with the variable names in the first row across the page. Chapter 4 Creating a data file and entering data 39 Step 2: Enter the data Enter the information for the first case on one line across the page, using the appropriate columns for each variable. Repeat for each of the remaining cases. Remember to save your file regularly.
Click on File, Save. Type in an appropriate file name. In the section labelled Files of Type choose Excel. Excel files have a.
Find the file that contains your data. Click on it so that it appears in the File name section. Click on the Open button. A screen will appear labelled Opening Excel Data Source. Make sure there is a tick in the box: Read variable names from the first row of data. The data will appear on the screen with the variable names listed across the top.
You will, however, need to go ahead and define the Variable labels, Value labels and the type of Measure. The instructions for these steps are provided earlier in this chapter. Choose File, and then Save As from the menu at the top of the screen. Type in a suitable file name.
When you wish to open this file later to analyse your data using SPSS, make sure you choose the file that has a. It is very easy to make mistakes when entering data, and unfortunately some errors can completely mess up your analyses.
For example, entering 35 when you mean to enter 3 can distort the results of a correlation analysis. So it is important to spend the time checking for mistakes initially, rather than trying to repair the damage later. Although boring, and a threat to your eyesight if you have large data sets, this process is essential and will save you a lot of heartache later! First, you need to check each of your variables for scores that are out of range i. Second, you need to find where in the data file this error occurred i.
Finally, you need to correct the error in the data file itself. To demonstrate these steps, I have used an example taken from the survey data file survey. To follow along you will need to start SPSS and open the survey. This file can be opened only in SPSS. In working through each of the steps on the computer, you will become more familiar with the use of SPSS menus, interpreting the output from SPSS analyses and manipulating your data file.
Step 1: Checking for errors When checking for errors you are primarily looking for values that fall outside the range of possible values for a variable.
To check for errors you will need to inspect the frequencies for each of your variables. This includes all of the individual items that make up the scales. Errors must be corrected before total scores for these scales are calculated. There are a number of different ways to check for errors using SPSS. I will illustrate two different ways, one which is more suitable for categorical variables e.
The reason for the difference in the approaches is that some statistics are not appropriate for categorical variables e. Checking categorical variables In this section the procedure for checking categorical variables for errors is presented. In the example shown below I will check the survey. Procedure for checking categorical variables 1.
From the main menu at the top of the screen click on: Analyze, then click on Descriptive Statistics, then Frequencies. Choose the variables that you wish to check e. Click on the arrow button to move these into the variable box. Click on the Statistics button.
Tick Minimum and Maximum in the Dispersion section. Click on Continue and then on OK. The output generated using this procedure is displayed below only selected output is displayed. The first table provides a summary of each of the variables you requested.
The remaining tables give you a break-down, for each variable, of the range of responses these are listed using the value label, rather than the code number that was used. Are they within the range of possible scores on that variable? You can see from the first table labelled Statistics that, for the variable Sex, the minimum value is 1 and the maximum is 2, which is correct.
For Marital status the scores range from 1 to 8. Checking this against the codebook, these values are appropriate. Have you made errors in entering the data e. If this occurs, open your Data Editor window, move down to the empty case row, click in the shaded area where the case number appears and press Delete on your keypad. Rerun the Frequencies procedure again to get the correct values.
In these tables you can see how many cases fell into each of the categories e. Percentages are also presented. This information will be used in the Method section of your report when describing the characteristics of the sample once any errors have been corrected, of course! Checking continuous variables Procedure for checking continuous variables 1. From the menu at the top of the screen click on Analyze, then click on Descriptive statistics, then Descriptives.
Chapter 5 Screening and cleaning the data 43 2. Click on the variables that you wish to check. Click on the arrow button to move them into the Variables box e. Click on the Options button. You can ask for a range of statistics, the main ones at this stage are mean, standard deviation, minimum and maximum. Click on the statistics you wish to generate. Click on Continue, and then on OK. The output generated from this procedure is shown below. Descriptive Statistics Std. Do these make sense? In this case the ages range from 18 to If the variable is the total score on a scale, is the mean value what you expected from previous research on this scale?
Is the mean in the middle of the possible range of scores, or is it closer to one end? This sometimes happens when you are measuring constructs such as anxiety or depression.
How can you find out where the mistake is in your data set? I will illustrate two approaches. Procedures for identifying the case where an error has occurred Method 1 1. Make sure that the Data Editor window is open and on the screen in front of you with the data showing.
Click on the variable name of the variable in which the error has occurred e. Click once to highlight the column. Click on Edit from the menu across the top of the screen. Click on Find. In the Search for box, type in the incorrect value that you are looking for e. Click on Search Forward. SPSS will scan through the file and will stop at the first occurrence of the value that you specified. Take note of the ID number of this case from the first row.
You will need this to check your records or questionnaires to find out what the value should be. Click on Search Forward again to continue searching for other cases with the same incorrect value.
You may need to do this a number of times before you reach the end of the data set. Method 2 1. From the menu at the top of the screen click on: Analyze, then click on Descriptive Statistics, then Explore.
In the Display section click on Statistics. Click on the variables that you are interested in e. In the Label cases section choose ID from your variable list.
In the Statistics section choose Outliers. To save unnecessary output you may also like to remove the tick from Descriptives just click once. Click on Continue. In the Options section choose Exclude cases pairwise.
The output generated from Explore Method 2 is shown below. Only a partial list of cases with the value 2 are shown in the table of upper extremes. Only a partial list of cases with the value 1 are shown in the table of lower extremes.
Chapter 5 Screening and cleaning the data 45 Note: The data file has been modified for this procedure to illustrate the detection of errors.
In the above example this is a 3. In this printout the person with the ID number of 9 has a value of 3 for Sex. Make sure you refer to the ID number, not the Case number. Now that we have found which person in the data set has the error, we need to find out what the correct value should be, then go back to the data set to correct it.
Step 3: Correcting the error in the data file There are a number of steps in this process of correcting an error in the data file. Procedure for correcting the error in the data file 1. To correct the error, it will be necessary to go back to your questionnaires or the records from your experiment.
Find the questionnaire or record with the ID number that was identified as an extreme value. Check what value should have been entered for that person e. Open the Data Editor window if it is not already open in front of you.
In the data file, find the variable column labelled ID. It should be the first one. Move down to the case that has the ID number with the error. Remember that you must use the variable ID column, not the case number on the side of the screen. Once you have found the person with that ID number, move across the row until you come to the column of the variable with the error e. Place the cursor in the cell, make sure that it is highlighted and then just type in the correct value.
Press one of the arrow keys and you will see the correct value appear in the cell. After you have corrected your errors it is a good idea to repeat Frequencies to double-check. Sometimes, in correcting one error, you will have accidentally caused another error. Although this process is tedious it is very important that you start with a clean, error-free data set. The success of your research depends on it!
Reference For additional information on the screening and cleaning process, I would strongly recommend you read Chapter 4 in: Tabachnick, B. Using multivariate statistics 4th edn.
New York: HarperCollins. Part Three Preliminary analyses Once you have a clean data file, you can begin the process of inspecting your data file and exploring the nature of your variables. This is in readiness for conducting specific statistical techniques to address your research questions.
There are five chapters that make up Part Three of this book. In Chapter 6 the procedures required to obtain descriptive statistics for both categorical and continuous variables are presented. This chapter also covers checking the distribution of scores on continuous variables in terms of normality and possible outliers.
Graphs can be useful tools when getting to know your data. Sometimes manipulation of the data file is needed to make it suitable for specific analyses. This may involve calculating the total score on a scale, by adding up the scores obtained on each of the individual items.
It may also involve collapsing a continuous variable into a smaller number of discrete categories. These data manipulation techniques are covered in Chapter 8. In Chapter 9 the procedure used to check the reliability internal consistency of a scale is presented.
This is particularly important in survey research, or in studies that involve the use of scales to measure personality characteristics, attitudes, beliefs etc. Also included in Part Three is a chapter that helps you through the decision- making process in deciding which statistical technique is suitable to address your research question.
In Chapter 10 you are provided with an overview of some of the statistical techniques available in SPSS and led step by step through the process of deciding which one would suit your needs.
Important aspects that you need to consider e. Descriptive statistics have a number of uses. The two procedures outlined in Chapter 5 for checking the data will also give you information for describing your sample in the Method section of your report. In studies involving human subjects, it is useful to collect information on the number of people or cases in the sample, the number and percentage of males and females in the sample, the range and mean of ages, education level, and any other relevant background information.
Prior to doing many of the statistical analyses e. Testing of assumptions usually involves obtaining descriptive statistics on your variables. These descriptive statistics include the mean, standard deviation, range of scores, skewness and kurtosis. Descriptive statistics can be obtained a number of different ways, using Frequencies, Descriptives or Explore. These are all procedures listed under the Analyze, Descriptive Statistics drop-down menu.
There are, however, different procedures depending on whether you have a categorical or continuous variable. Some of the statistics e. The different approaches to be used with categorical and continuous variables are presented in the following two sections. Categorical variables To obtain descriptive statistics for categorical variables you should use Frequencies.
This will tell you how many people gave each response e. From the menu at the top of the screen click on: Analyze, then click on Descriptive Statistics, then Frequencies.
Choose and highlight the categorical variables you are interested in e. Move these into the Variables box. In the Dispersion section tick Minimum and Maximum. It is important to take note of the number of respondents you have in different subgroups in your sample. For some analyses e. ANOVA it is easier to have roughly equal group sizes. If you have very unequal group sizes, particularly if the group sizes are small, it may be inappropriate to run some analyses.
Continuous variables For continuous variables e. Just transfer all the variables you are interested in into the box labelled Variables. If you have a lot of variables, however, your output will be extremely long. Sometimes it is easier to do them in chunks and tick off each group of variables as you do them. Procedure for obtaining descriptive statistics for continuous variables 1. From the menu at the top of the screen click on: Analyze, then click on Descriptive Statistics, then Descriptives.
Click on all the continuous variables that you wish to obtain descriptive statistics for. Click on mean, standard deviation, minimum, maximum, skewness, kurtosis. Click on Continue, and then OK. Error Statistic Std. Error AGE 18 82 For example, concerning the variable age, we have information from respondents, the range of ages is from 18 to 82 years, with a mean of This information may be needed for the Method section of a report to describe the characteristics of the sample.
Descriptives also provides some information concerning the distribution of scores on continuous variables skewness and kurtosis. This information may be needed if these variables are to be used in parametric statistical techniques e. The skewness value provides an indication of the symmetry of the distribution. Positive skewness values indicate positive skew scores clustered to the left at the low values.
Negative skewness values indicate a clustering of scores at the high end right-hand side of a graph. Positive kurtosis values indicate that the distribution is rather peaked clustered in the centre , with long thin tails. Kurtosis values below 0 indicate a distribution that is relatively flat too many cases in the extremes.
While there are tests that you can use to evaluate skewness and kurtosis values, these are too sensitive with large samples.
Comments
Post a Comment