不是continuous variable的话，能做什么correlation分析么？

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

RT.

如果是那种1或0的proxy indicator，能做类似pearson correlation的分析么？

pearson是用在连续性变量的。如果要看非连续性变量和连续性变量有什么关系，我们要怎么做呢？

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：correlation Continuous Variable relation ATION Continuous Variable correlation

大家有谁知道么？

还是我没问清楚？

谢谢啦~~~

Not sure if this is the best way to do it but this is what I would try:
First, categorize your continuous variable into some ordered categories (for example, 1,2,3,etc...).  Number of categories may depends on your sample size and the attributes of your data.

Then build a contingency table.  Now you can use Kruskal-Wallis statistic to get a sense of the degree of correlation between two variables.

yisung真好啊，谢谢了！

I'll try. Just wondering why we should rank the data.

PS: find there is so much to learn. Need to know the econometric theory and the application. Both are not easy; and there is also a big gap between the two.
__________________________________________
The power of dream.

polychoric