python实现参数估计

1.导入数据

import numpy as np
import pandas as pd
from scipy import stats
path = 'D:\数据\data.xlsx'
data = pd.read_excel(path)
age = data['Age']
print(age.mean) #输出值为：29.64209269662921

2.抽取100个样本

age_sam = age.sample(100)
age_sam.describe()

3.计算置信区间

# 正态分布下的置信区间
def norm_conf(data,confidence = 0.95):
	sample_mean = np.mean(data)
	# numpy.std() 求标准差的时候默认是除以 n 的，即是有偏的，np.std无偏样本标准差方式为加入参数 ddof = 1；
	# pandas.std() 默认是除以n-1 的，即是无偏的
	sample_std = np.std(data,ddof = 1)
	conf_interval = scipy.satas.norm.interval(confidence,loc = sample_name,scale = sample_std)

# T分布下的置信区间
def ttest_conf(data,confidence = 0.95):
	sample_mean = np.mean(data)
	sample_std = np.std(data,ddof = 1)
	sample_size = len(data)
	conf_interval = scipy.satas.norm.interval(confidence, df = (sample_size - 1), loc = sample_name, scale = sample_std)

4.重复抽取数据

age_means = []
for i in range (1000):
	age_sample = age.sample(100, replace = True)
	sam_mean = age_sample.mean()
	age.means.append(sam_mean)
norm_conf(age_means)
ttest_conf(age_means)

5.绘制图像

import seaborn as sns 
from matplotlib import pyplot as plt

sns.set_palette("hls") #设置所有图的颜色，使用hls色彩空间
sns.distplot(scale_means,color="r",bins=10,kde=True)
plt.title('Age')
plt.xlim(25,35)
plt.grid(True)
plt.show()

参考链接：
https://blog.csdn.net/qq_43315928/article/details/103658733