Problem Calling Data While Using Linear Regression Model 'fitlm'

4 次查看（过去 30 天）
Onur Sen
Onur Sen 2020-11-8
评论： Onur Sen 2020-11-8
Hello
Hope you are swell.
Now, as the title suggests, I'm having trouble using the function 'fitlm'. Now in various examples avaliable in Matlab, they can call a column of data by specifying the title of that column.
I have imported my table (called Fish1) in which the first column includes the species of Fish (as a string) while other 6 columns have the properties of the fish such as weight, length and so on. Now my problem arises when I'm trying to set 'Species' column as a dependent variable (or response variable) while I set others as independent variables.
Now this is [p]ossibly due to the Species column being a string column but how can I make this work exactly? I'm considerably new to this stuff,
Thank you. Have a nice day!

请先登录，再回答此问题。

回答（1 个）

dpb
dpb 2020-11-8
"this is [p]ossibly due to the Species column being a string column..."
That's exactly the problem. See
Coding systems for categorical variables in regression analysis for nice exposition.
  1 个评论
Onur Sen
Onur Sen 2020-11-8
I manually assigned numbers to each fish and proceeded that way and it seems I was using 'Dummy Variables' in some way. I see there is an option creating dummy variables in Matlab. I'll try to use those for better organized script.
Thank you very much that was very helpful!

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Tables 的更多信息

标签

产品


版本

R2019b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by