PART ONE : SPSS PROCEDURES A scale on a questionnaire consists of a set of items. In this part of the
PART ONE : SPSS PROCEDURES
A scale on a questionnaire consists of a set of items. In this part of the assignment you will be constructing an internet addiction scale utilize the COMPUTE procedure in SPSS. This is exactly the procedure that you will utilize within your group research project.
On the Code Sheet, there are four items that measure Internet Addiction. They are: i17 thru i20 . You are going to combine these four items to create one scale.
PROCEDURE
- Click the TRANSFORM pull down. Then click COMPUTE.
- In the box that says TARGET VARIABLE, type in IA (that stands for internet addiction).
- Then, from the variable list, transfer each addiction item separately into the
- NUMERIC EXPRESSION box. You will be adding each of the addiction items
- as follow: i17+i18+i19+i20. Thus, the internet addiction scale now equals the
- sum of these four items.
- Click OK.
- Look at the last variable on the data view setting and you will see the newly created variable.
Run a frequency analyses on this newly created variable. Briefly describe the range of scores, the mean and the median.
Regression analysis represents a much more powerful statistical procedure than correlation. Once again, correlation simply allows us to determine whether or not two variables are related to one another. However, correlation and regression operates hand in hand. Correlation is an indication of how well the data fits the least squares equation. Simply stated, the correlation coefficient describes the extent to which a regression analysis would be useful. A very small or zero correlation would indicate that the two variables are not related and it would therefore not make any sense to utilize a regression procedure. Regression allows us to determine the extent to which the X factor "causes" a change in the Y factor. The most important coefficient within the regression procedure is "beta" or the slope. It describes the amount of change in Y cause by a certain change in X. For example, if we regressed education on income, a beta of 1500 would indicate that for every incremental change in education, income would increase $1500. As you can see, this has a lot of practical appeal.
Deliverable: Word Document
