python - Errors in the post-hoc analysis in pymer4: Variable is not in the dataset - Stack Overflow

admin管理员组

文章数量:1201168

I am performing a post-hoc analysis after a GLM analysis:

model = Lmer(formula='latency~ C(Velocity) + (1|subject)', data=df)
model.fit(factors={"Velocity": ["16","24","32","40"]}, ordered=True,summarize=True)

The post-hoc analysis based on marginal estimates:

marginal_estimates, comparisons = model.post_hoc(marginal_vars="ln_Latency", grouping_vars="Velocity",p_adjust='bonf')
print(marginal_estimates)
print("comparisons:","\n",comparisons)

the output returns:

RRuntimeError: Error in emtrends(model, pairwise ~ Velocity, var = "latency", adjust = "bonf",  : 
  Variable 'latency' is not in the dataset

more information:
...miniconda\envs\pyR\lib\site-packages\pymer4\models\Lmer.py:1231, in Lmer.post_hoc(self, marginal_vars, grouping_vars, p_adjust, summarize, dof_asymptotic_at, verbose)
   1228         raise ValueError("marginal_vars are not in model!")
   1230 func = robjects.r(rstring)
-> 1231 res = func(self.model_obj)
   1232 emmeans = importr("emmeans")
   1234 # Marginal estimates

...miniconda\envs\pyR\lib\site-packages\rpy2\robjects\functions.py:208, in SignatureTranslatedFunction.__call__(self, *args, **kwargs)
    206         v = kwargs.pop(k)
    207         kwargs[r_k] = v
--> 208 return (super(SignatureTranslatedFunction, self)
    209         .__call__(*args, **kwargs))

...miniconda\envs\pyR\lib\site-packages\rpy2\robjects\functions.py:131, in Function.__call__(self, *args, **kwargs)
    129     else:
    130         new_kwargs[k] = cv.py2rpy(v)
--> 131 res = super(Function, self).__call__(*new_args, **new_kwargs)
    132 res = cv.rpy2py(res)
...
    818 return res

Can someone help me?

sample data:

   Velocity subject latency
0         16    A5      224.32
1         16    A1      171.43
2         16    A2      300.00
3         16    A4      400.00

本文标签： pythonErrors in the posthoc analysis in pymer4 Variable is not in the datasetStack Overflow