Problem with running anova

Question

Aitana Grasso 2021-12-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1606345-problem-with-running-anova

评论： Aitana Grasso 2021-12-15

采纳的回答： Adam Danz

在 MATLAB Online 中打开

Hi everyone,

I have a question.

Turns out that when a create a linear model (using fitlm) and than I want to run an anova to that model I get this error:

Error using gather
Too many input arguments.
Error in classreg.regr.CompactLinearModel/componentanova (line 824)
[ss,df,ms,f,pval] = gather(ss,df,ms,f,pval);
Error in classreg.regr.CompactLinearModel/anova (line 319)
tbl = componentanova(model,sstype);

I had checked with colleagues and they don't have a "gather" function in line 824

Line 824: [ss,df,ms,f,pval] = gather(ss,df,ms,f,pval)

Does anyone knows what it could be?

4 个评论
显示 2更早的评论隐藏 2更早的评论

Aitana Grasso 2021-12-8

在 MATLAB Online 中打开

Thank you so much for your answer!

Here is my code:

y = [10.3	10.3	10.2	16.4	18.8	19.7	15.6	18.2	22.6	19.9	24.2	21 21.4	21.3	19.1	22.2	33.8	27.4	25.7	24.9	34.5	31.7	36.3	38.3	42.6	55.4	55.7	58.3	51.5	51	77]
y = 1×31
   10.3000   10.3000   10.2000   16.4000   18.8000   19.7000   15.6000   18.2000   22.6000   19.9000   24.2000   21.0000   21.4000   21.3000   19.1000   22.2000   33.8000   27.4000   25.7000   24.9000   34.5000   31.7000   36.3000   38.3000   42.6000   55.4000   55.7000   58.3000   51.5000   51.0000
x =  [70	65	63	72	81	83	66	75	80	75	79	76	76	69	75	74	85	86	71	64	78	80	74	72	77	81	82	80	80	80	87]
x = 1×31
    70    65    63    72    81    83    66    75    80    75    79    76    76    69    75    74    85    86    71    64    78    80    74    72    77    81    82    80    80    80
mdl = fitlm(x,y) % this runs without problem
mdl = 
Linear regression model:
    y ~ 1 + x1

Estimated Coefficients:
                   Estimate      SE        tStat       pValue  
                   ________    _______    _______    __________

    (Intercept)    -87.124      29.273    -2.9762     0.0058347
    x1              1.5433     0.38387     4.0205    0.00037838


Number of observations: 31, Error degrees of freedom: 29
Root Mean Squared Error: 13.4
R-squared: 0.358,  Adjusted R-Squared: 0.336
F-statistic vs. constant model: 16.2, p-value = 0.000378
p = anova(mdl) % here is the error. (I have try with all posible anova functions -anova1, anova2, anovan-).
p = 2×5 table
             SumSq     DF    MeanSq      F         pValue  
             ______    __    ______    ______    __________

    x1       2901.2     1    2901.2    16.164    0.00037838
    Error    5204.9    29    179.48                        

When I run the last line I got the error showed before.

I'm using R2021a

Adam Danz 2021-12-15

I applied the run feature to your code so we can see the results.

Aitana Grasso 2021-12-15

Hello Adam,

Thank you so much for your help.

Apparently de problem was in my MATLAB, so I had to uninstall and install again.

Now everything is running perfectly!

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Adam Danz 2021-12-8

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1606345-problem-with-running-anova#answer_850795

在 MATLAB Online 中打开

It looks like you've shadowed matlab's gather function with a function or script of the same name.

To see a list of functions named gather,

which gather -all
/MATLAB/toolbox/matlab/bigdata/gather.m
/MATLAB/toolbox/matlab/bigdata/@tall/gather.m              % Shadowed tall method
/MATLAB/toolbox/nnet/deep/@dlarray/gather.m                % Shadowed dlarray method
/MATLAB/toolbox/parallel/gpu/@gpuArray/gather.m            % Shadowed gpuArray method
/MATLAB/toolbox/parallel/parallel/@distributed/gather.m    % Shadowed distributed method
/MATLAB/toolbox/parallel/parallel/@codistributed/gather.m  % Shadowed codistributed method

Then remove your shadowed file from the Matlab path or rename the file.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Problem with running anova

4 个评论
显示 2更早的评论隐藏 2更早的评论

采纳的回答

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

更多回答（0 个）

另请参阅

类别

标签

Community Treasure Hunt

Problem with running anova

4 个评论 显示 2更早的评论隐藏 2更早的评论

采纳的回答

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

更多回答（0 个）

另请参阅

类别

标签

Community Treasure Hunt

4 个评论
显示 2更早的评论隐藏 2更早的评论

0 个评论
显示 -2更早的评论隐藏 -2更早的评论