应《网络安全法》要求，自2017年10月1日起，未进行实名认证将不得使用互联网跟帖服务。为保障您的帐号能够正常使用，请尽快对帐号进行手机号验证，感谢您的理解与支持！

24小时热门版块排行榜    

小木虫论坛-学术科研互动平台 » 专业学科区 » 数学 » 概率论与统计 » 论文投稿，主编关于统计的意见我不明白，请帮我看一看。
11/1返回列表
查看: 595  |  回复: 0
只看楼主 @他人 存档 新回复提醒 (忽略) 收藏    在APP中查看

fdc

铜虫 (小有名气)

[求助] 论文投稿，主编关于统计的意见我不明白，请帮我看一看。

主编的第一次意见
Table 2 - there is no description of correlation having been undertaken. Further to this the use of simple correlation analysis is fraught with danger and the authors should consult Hassleer & Thadewald (2003) - The Statistician 52(3) 367-379 for detail on multivariate linear modelling.
我们的修改如下：
Statistical analyses
-------------------------------。Pearson's correlation coefficients were computed to quantify linear associations between physicochemical and structural parameters of MP.

Table 2. Pearson correlation coefficient between sodium nitrite and physicochemical and structural parameters of MP.
        CA        FA        SH        S-S        HY        TU        SO        3-NT        TABRS
FA        -0.636**                                                               
SH        0.815**        -0.623**                                                       
S-S        -0.771**        0.584**        -0.967**                                               
HY        0.768**        -0.508*        0.699**        -0.759**                                       
TU        0.637**        -0.184        0.539*        -0.538*        0.492*                               
SO        0.525*        -0.259        0.486*        -0.557*        0.719**        0.495*                       
3-NT        -0.425        0.334        -0.557*        0.468*        -0.152        -0.397        -0.138               
TABRS        0.620**        -0.532*        0.674**        -0.581**        0.373        0.756**        0.293        -0.753**       
SN        -0.636**        0.628**        -0.790**        0.733**        -0.489*        -0.492*        -0.214        0.812**        -0.829**
Note: *means significant difference (P < 0.05), **means significant difference (P < 0.01). Abbreviations in the table: CA, carbonyl; FA, free amine; SH, sulfydryl; S-S, disulfide; HY, hydrophobicity; TU, turbidity; SO, solubility; 3-NT, 3-nitrotyrosine; SN, sodium nitrite.

我们实在不明白主编关于相关分析的意思，他是想我们使用多元线性模型分析Table2的参数之间的相关性吗？于是就给了主编写信咨询，主编的第二次回信是这样的：

第二次去信
Dear -------,
Thank you for your help to improve our manuscript. In your last letter, you mentioned ‘correlation analysis in table 2’. We are sorry for our unclear description. Pearson's correlation coefficients have been computed to quantify linear associations between physicochemical and structural parameters of MP. We send table 2 to you to see if we understand you.
Again, thank you for taking the time and energy to help us improve the paper. We will do further modifications if you think we should make more modifications on table 2.

主编的第二次回信：
Anyway the point I made was that in the use of correlation analysis you need to be very careful.  This only tells the level of association, not causation and to overcome this as pointed out in the reference I sent you should undertake a GLM analysis that accounts for the variance from the treatment structure which will indicate the correlation between traits once the structure is accounted for.
Please also note that if you applied replicates then this needs to be taken account of in the analysis.


请问主编到底是什么意思，多元线性模型分析参数之间的相关性不知道该如何进行？此外主编第二次回信中的‘treatment structure’是什么意思？谢谢！
回复此楼

» 猜你喜欢
1楼 2015-12-10 11:56:38
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖
相关版块跳转 我要订阅楼主 fdc 的主题更新
11/1返回列表
普通表情 龙 兔 虎 猫
信息提示
关闭
请填处理意见
关闭