| 查看: 2433 | 回复: 3 | ||||
| 当前只显示满足指定条件的回帖，点击这里查看本话题的所有回帖 | ||||
niexianling铜虫 (初入文坛)
|
[求助]
matlab中std2函数计算矩阵的标准差时，分母是除以了n-1还是n？
|
|||
|
matlab中std2函数计算矩阵的标准差时，分母是除以了n-1还是n？ 这是如下代码 function s = std2(a) %STD2 Standard deviation of matrix elements. % B = STD2(A) computes the standard deviation of the values in % A. % % Class Support % ------------- % A can be numeric or logical. B is a scalar of class double. % % Example % ------- % I = imread('liftingbody.png'); % val = std2(I) % % See also CORR2, MEAN2, MEAN, STD. % Copyright 1992-2010 The MathWorks, Inc. % $Revision: 5.19.4.6 $ $Date: 2010/09/13 16:14:04 $ % validate that our input is valid for the IMHIST optimization fast_data_type = isa(a,'logical') || isa(a,'int8') || isa(a,'uint8') || ... isa(a,'uint16') || isa(a,'int16'); % only use IMHIST for images of sufficient size big_enough = numel(a) > 300000; if fast_data_type && isequal(ndims(a),2) && ~issparse(a) && big_enough % compute histogram if islogical(a) num_bins = 2; else data_type = class(a); num_bins = double(intmax(data_type)) - double(intmin(data_type)) + 1; end [bin_counts bin_values] = imhist(a, num_bins); % compute standard deviation total_pixels = numel(a); sum_of_pixels = sum(bin_counts .* bin_values); mean_pixel = sum_of_pixels / total_pixels; bin_value_offsets = bin_values - mean_pixel; bin_value_offsets_sqrd = bin_value_offsets .^ 2; offset_summation = sum( bin_counts .* bin_value_offsets_sqrd); s = sqrt(offset_summation / total_pixels); else % use simple implementation if ~isa(a,'double') a = double(a); end s = std(a(  );end |
回复此楼» 猜你喜欢
澳门大学IAPME李海峰教授常年招收博士研究生
已经有0人回复
-
澳门大学IAPME李海峰教授常年招收博士研究生
已经有0人回复
-
物理学I论文润色/翻译怎么收费?
已经有181人回复
-
深圳大学应用技术学院招聘凝聚态物理博士后
已经有123人回复
-
求助中医院临床中医中标的青年标书学习，谢谢
已经有5人回复
-
浙大物院表面物理课题组长期招收普博及直博学生
已经有259人回复
-
【征稿】Springer Nature热电专题 Discover Materials / Discover Chemistry
已经有47人回复
-
25届硕士申请，材料计算方向
已经有2人回复
-
课题组招1-2名硕士
已经有1人回复
-
机时越来越贵之后，我把一部分 DFT 流程搬到了 AI 计算平台上
已经有0人回复
niexianling
铜虫 (初入文坛)
- 应助: 0 (幼儿园)
- 金币: 20
- 红花: 2
- 帖子: 50
- 在线: 23.4小时
- 虫号: 1661372
- 注册: 2012-03-03
- 性别: MM
- 专业: 化学计量学与化学信息学
3楼2013-06-27 11:00:36
月只蓝
主管区长 (职业作家)
-
专家经验: +1059 - 计算强帖: 8
- 应助: 1712 (讲师)
- 贵宾: 8.888
- 金币: 68178.7
- 散金: 1938
- 红花: 443
- 沙发: 4
- 帖子: 4373
- 在线: 3292.4小时
- 虫号: 1122189
- 注册: 2010-10-14
- 专业: 宇宙学
- 管辖: 计算模拟区
【答案】应助回帖
★
感谢参与，应助指数 +1
csgt0: 金币+1, 谢谢 2013-06-28 11:32:57
感谢参与，应助指数 +1
csgt0: 金币+1, 谢谢 2013-06-28 11:32:57
|
默认的是N-1吧，以下是MATLAB 帮助文档的说明： STD Standard deviation. For vectors, Y = STD(X) returns the standard deviation. For matrices, Y is a row vector containing the standard deviation of each column. For N-D arrays, STD operates along the first non-singleton dimension of X. STD normalizes Y by (N-1), where N is the sample size. This is the sqrt of an unbiased estimator of the variance of the population from which X is drawn, as long as X consists of independent, identically distributed samples. Y = STD(X,1) normalizes by N and produces the square root of the second moment of the sample about its mean. STD(X,0) is the same as STD(X). Y = STD(X,FLAG,DIM) takes the standard deviation along the dimension DIM of X. Pass in FLAG==0 to use the default normalization by N-1, or 1 to use N. |
2楼2013-06-27 10:34:09
4楼2013-06-27 14:43:54
