Hello,
im currently working on my master thesis and i have the problem that the r² value of my dependent variable is too low (0,410).
But due to the predictive research in my master thesis i want to increase the r² value of my dependent variable to 0,710.
But how?
Thanks for any advices!
how to improve r square?
- Diogenes
- PLS Super-Expert
- Posts: 899
- Joined: Sat Oct 15, 2005 5:13 pm
- Real name and title:
- Location: São Paulo - BRAZIL
- Contact:
Hi,
1st idea) With more predictive LV, maybe the R2 will increase.
For instance, in ECSI studies:
2 predictors --> 44% < R2 (mean) < 52%
3 or 4 predictors --> 67% < R2 (mean) < 79%
FORNELL, C. A National Customer Satisfaction Barometer: The Swedish Experience. Journal of Marketing, v.56, n.1, p.6-21, jan.1992.
FORNELL, C. et al. The American Customer Satisfaction Index: Nature, Purpose, and Findings. Journal of Marketing, v.60, n.4, p.7-18, out.1996.
KRISTENSEN, K.; MARTENSEN, A.; GRØNHOLDT, L. Customer Satisfaction Measurement at Post Denmark: results of application of the European Customer Satisfaction Index Methodology. Total Quality Management, v.11, n.7, p.S1007-S1015.
TENENHAUS, M.; VINZI, V. E.; CHATELIN, Y.; LAURO, C. PLS path modeling. Computational Statistics & Data Analysis, v.48, p.159-205, 2005.
2nd idea) Using AMOS or LISREL (covariance based) there is a tendency of structural results to be bigger than PLS-PM.
Best regards,
Bido
1st idea) With more predictive LV, maybe the R2 will increase.
For instance, in ECSI studies:
2 predictors --> 44% < R2 (mean) < 52%
3 or 4 predictors --> 67% < R2 (mean) < 79%
FORNELL, C. A National Customer Satisfaction Barometer: The Swedish Experience. Journal of Marketing, v.56, n.1, p.6-21, jan.1992.
FORNELL, C. et al. The American Customer Satisfaction Index: Nature, Purpose, and Findings. Journal of Marketing, v.60, n.4, p.7-18, out.1996.
KRISTENSEN, K.; MARTENSEN, A.; GRØNHOLDT, L. Customer Satisfaction Measurement at Post Denmark: results of application of the European Customer Satisfaction Index Methodology. Total Quality Management, v.11, n.7, p.S1007-S1015.
TENENHAUS, M.; VINZI, V. E.; CHATELIN, Y.; LAURO, C. PLS path modeling. Computational Statistics & Data Analysis, v.48, p.159-205, 2005.
2nd idea) Using AMOS or LISREL (covariance based) there is a tendency of structural results to be bigger than PLS-PM.
Best regards,
Bido