Posts filed under '3a. Analysing your data'
This week Eamonn send us the following question about the Compute function:
When using transfor/compute – say to create a construct from a set of Likert
Scale items – does SPSS save the formula used to create the new variable, or
is it lost once you compute?
SPSS does not save the formula in your data file. It does keep the formula in mind if you keep SPSS open. So if you want to use the same formula again, but than with different variables for example, you can open the Compute screen again, and there your old formula is. But if you close SPSS and open it again, the formula will be gone.
January 19th, 2007
Many visitors of our blog are searching for information about the one sample t-test.
From the menus choose: Analyze>Compare Means>Means
Select one or more dependent variables.Use one of the following methods to select categorical independent variables:
Select one or more independent variables. Separate results are displayed for each independent variable.
Select one or more layers of independent variables. Each layer further subdivides the sample. If you have one independent variable in Layer 1 and one independent variable in Layer 2, the results are displayed in one crossed table, as opposed to separate tables for each independent variable.
May 8th, 2006
This weekend we got a question from Kat, who is desperately looking for our help. She is working on a project with a lot of data in Excel:
“I am in the middle of a project for which I have constructed a large table in Microsoft Excel.
The table consists of variables going across the top, and cases down the side. The cells contain numbers (ie. the frequency of each variable within each case). Many of the cells have no number or the variable has zero frequency in that case.
I want to look for patterns with in the data, that is , similarities between cases. It has been suggested that I do this visually, however the table is so big it would take forever. I am wondering if you know of an application within SPSS which looks for patterns in this way. It would be an enormous help to my work if there is such a thing.”
Well Kat, to begin, of course you should always use SPSS, and never Excel for analysing your data.
There are two ways to solve your problem:
1. Do it the hard way by comparing all answers withÂ a correlationÂ test. This means you would have to compare all the questions (and their answers) to see if there is a correlation between them. Doing this, you will in the end have found all relationships and be able to find the patterns.
2. There is an easy way, but for this you need an extra piece of software from SPSS, called “SPSS Categories“. In the software you can put in ratings and categories, and the software will display graphically (and in figures) the possible relationships in your data.
Good luck analysing your data!
April 19th, 2006
We got a question from Tom:
“I’m doing research. In this research I had interviews with 20 different
persons. The interviews were open questions (so not only yes/no answers,
but also yes/no/sometimes/only when.. etc)
I am looking for a way to translate the answers into SPSS, so I can make
graphs and percentages for each question (For example: 25% answered yes, 30%
answered no, 2 % answered only when etc.)
Is there an easy way to deal with my problem?”
To begin, SPSS is not meant for analyzing open answers. You can not easily make graphs out of this kind of data. SPSS maximum character input for string fields (used for open answers) is 255. This means you cannot input long pieces of code in the SPSS file.
The only way to create graphs and tables (with counts, percentages etc.) is to categorise the answers the respondents gave you. If you have for example a question with the answers:
Q: Do you you use product 3?
- Yes, I have used it for three years now, mainly for purpose X, Y and Z
- No, I have no idea what product you are talking about. But for purpose Z and B I often use product 4 from this and this supplier….
- Yes, I hate to admit it, but I use it
- Yes, I use it all day, for purpose Z
- Yes, for purpose Z
- No, but would like to use it
You could categorise it into the following variables:
1 = Yes, often
2 = Yes, sometimes
3 = No, but I am interested
4 = No, and not interest to use it
April 7th, 2006
Sometimes you want to split your data file in separate groups for analysis
Its a easy thing to do in SPSS. From the menus choose:
Data > Split File
This opens the Split File dialog box.
Select Compare groups or Organize output by groups. The examples following these steps show the differences between these two options.
Select Gender (gender) to split the file into separate groups for these variables. You can use numeric, short string, and long string variables as grouping variables. A separate analysis is performed for each subgroup defined by the grouping variables. If you select multiple grouping variables, the order in which they appear on the Groups Based On list determines the manner in which cases are grouped.
If you select Compare groups and run the Frequencies procedure, a single pivot table is created.
If you select Organize output by groups and run the Frequencies procedure, two pivot tables are created: one for females and one for males.
March 22nd, 2006