hcistats:multilevellinear

This shows you the differences between two versions of the page.

Both sides previous revision Previous revision | |||

hcistats:multilevellinear [2014/07/23 07:56] Koji Yatani |
hcistats:multilevellinear [2014/08/14 05:26] (current) Koji Yatani |
||
---|---|---|---|

Line 1: | Line 1: | ||

======Multilevel Linear Model====== | ======Multilevel Linear Model====== | ||

+ | \\ | ||

=====Introduction===== | =====Introduction===== | ||

[[HCIstats:LinearRegression|Linear Models]] and [[HCIstats:GLM|Generalized Linear Models (GLM)]] are a very useful tool to understand the effects of the factor you want to examine. These models are also used for prediction: Predicting the possible outcome if you have new values on your independent variables (and this is why independent variables are also called predictors). | [[HCIstats:LinearRegression|Linear Models]] and [[HCIstats:GLM|Generalized Linear Models (GLM)]] are a very useful tool to understand the effects of the factor you want to examine. These models are also used for prediction: Predicting the possible outcome if you have new values on your independent variables (and this is why independent variables are also called predictors). | ||

Line 253: | Line 254: | ||

It is probably acceptable that you simply report the direction of each significant effect (positive or negative) if you do not really care about the actual value of the coefficient. But I think you should report at least whether each significant effect contributes to the dependent variable in a positive or negative way. | It is probably acceptable that you simply report the direction of each significant effect (positive or negative) if you do not really care about the actual value of the coefficient. But I think you should report at least whether each significant effect contributes to the dependent variable in a positive or negative way. | ||

+ | |||

+ | \\ | ||

+ | ~~DISCUSSION:open~~ | ||

hcistats/multilevellinear.txt ยท Last modified: 2014/08/14 05:26 by Koji Yatani