When the dependent variables are more than 10 and independent variable is 1, which type of analysis be used in SPSS.
Dear Kriti,
You could try a MANOVA but it depends upon the data types of your variables. You might also consider a dimension reduction technique before running another test.
I have 1 independent variable named quality circles which is affecting 13 dependent variables. I prepared 5-point Likert scale 48 item-questionnaire. Sample size is 272. Now I need to know which type of analysis should I do.
Sample was divided into three groups of participants- top, middle and lower level management
Hello Agrawal
1. Your question is not clear, and what is your problem?
2. What is the relation between the random variables, i.e. related or not.
3. Selecting any kind of statistical measures or any analysis technique should be based on your hypotheses and research questions and the statistical requirements.
4. The first possible analysis: Multiple regression analysis
. Regression analysis also required a linear relationship between the independent random variables and the dependent random variable,
. Multivariate normality,
. No or little multicollinearity,
. No auto-correlation and
. Homoscedasticity.
. Linear regression model/analysis is a technique used to predict the value of one quantitative variable by using its relationship with one or more additional quantitative variables.
. The applications/calculations of multiple regression analysis can be done using SAS. Please see, Willam Mendenhall and Terry Sincich (2003).Chapter 4, pages:182-185.
. In SPSS, the calculations can be also developed . See,
Landau, S. and Everitt, B. S.(2004). A Handbook of Statistical analyses using SPSS. Chapter 4, pages:92-126.
To be continued
5. The second choice: ANOVA
ANOVA Assumptions
. The experimental errors of your data are normally
distributed
. Equal variances between treatments
. Homogeneity of variances
. Homoscedasticity.
6. Specific test: A mixed analysis of variance
- A mixed analysis of variance design is merely a two-way (or three-way, etc.) research design which contains both unrelated and related independent variables.
- Mixed designs generate rather more complex measures of error estimates compared to other forms of the ANOVA. This means that special care needs to be taken when producing appropriate summary tables.
- Apart from that, concepts from related and unrelated ANOVAs apply.
7. Please refer to:
William G. Cochran, Gertrude M. Cox (1977). Experimental Design, Wiley.
Snedecor, W.G. and Cochran,W.G. (1989). Statistical Methods, Blackwell.
Geoffrey Keppel and Thomas D. Wickens (2004). Design and Analysis: A Researcher's Handbook (4th Edition). International Edition.
Regards,
Zuhair
Your sample size are big so I suggest you it will bebetter using SEM Analysis
( Structural Equation Modeling)
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS