t测试结果（统计=nan，pvalue=nan）错误

Question

我有以下命令：

Townames = []
Notowns = [] 
def run_ttest():
    for key,value in enumerate(data['RegionName']):
                 if value in stateslist:
                    indexing = data['differ'].iloc[key]
                    Townames.append(indexing) 
                 else:
                    indexing = data['differ'].iloc[key]
                    Notowns.append(indexing)
    Unitowns = pd.DataFrame(columns = ['Unitownvalues'])
    Notunitowns = pd.DataFrame(columns = ['Notunitownvalues'])
    Unitowns['Unitownvalues'] = Townames      
    Notunitowns['Notunitownvalues'] = Notowns 
    Unitowns = Unitowns.dropna(subset=['Unitownvalues'])
    Notunitowns = Notunitowns.dropna(subset=['Notunitownvalues'])
    return 
run_ttest()
from scipy import stats 
stats.ttest_ind(Unitowns['Unitownvalues'],Notunitowns['Notunitownvalues'])

但是，我的输出是：

Ttest_indResult(statistic=nan, pvalue=nan)

我不明白这是为什么

I删除了上面的NAN值：Unitowns['Unitownvalues']和Notunitowns['Notunitownvalues'].

有谁能帮我一把吗

Answer 1

确保添加最后一个参数（假设比较的两个数据集的方差将相等）：

stats.ttest_ind(Unitowns['Unitownvalues'],Notunitowns['Notunitownvalues'],equal_var=True)

而不是：

stats.ttest_ind(Unitowns['Unitownvalues'],Notunitowns['Notunitownvalues'])

这给了我一个输出：

Ttest_indResult(statistic=0.38697667088831, pvalue=0.69878181110717441)