Template:Rank Regression/Least Squares PE - Revision history

Lisa Hacker: Redirected page to Parameter Estimation

2012-08-09T10:09:12Z

← Older revision		Revision as of 10:09, 9 August 2012
Line 1:		Line 1:
	[[~~Category: For Deletion~~]]		#REDIRECT [[Parameter Estimation]]

Lisa Hacker: Replaced content with 'Category: For Deletion'

2012-07-20T12:28:02Z

Replaced content with 'Category: For Deletion'

← Older revision		Revision as of 12:28, 20 July 2012
Line 1:		Line 1:
	~~=== Least Squares Parameter Estimation ===~~		[[Category: For Deletion]]

	Using the idea of probability plotting, regression analysis mathematically fits the best straight line to a set of points, in an attempt to estimate the parameters. Essentially, this is a mathematically based version of the probability plotting method discussed previously.

	~~==== Background Theory ====~~

	The method of linear least squares is used for all regression analysis performed by Weibull++, except for the cases of the three-parameter Weibull, mixed Weibull, gamma and generalized gamma distributions, where a non-linear regression technique is employed. The terms '''linear regression''' and '''least squares''' are used synonymously in this reference. In Weibull++, the term ''rank regression'' is used instead of least squares, or linear regression, because the regression is performed on the rank values, more specifically, the median rank values (represented on the y-axis). The method of least squares requires that a straight line be fitted to a set of data points, such that the sum of the squares of the distance of the points to the fitted line is minimized. This minimization can be performed in either the vertical or horizontal direction. If the regression is on <span class="texhtml">''X''</span>, then the line is fitted so that the horizontal deviations from the points to the line are minimized. If the regression is on Y, then this means that the distance of the vertical deviations from the points to the line is minimized. This is illustrated in the following figure.

	~~<br>~~[[~~Image~~:~~minimizingdistance.png\|center\|250px]]~~

	~~==== Rank Regression on <span class="texhtml">''Y''</span> ====~~

	Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced (<math>\hat{ }</math>) symbol indicates that this value is an estimate) such that:

	~~<center> <math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math> </center>~~

	and where <math>\hat{a}</math> and <math>\hat b</math> are the ''least squares estimates'' of <span class="texhtml">''a''</span> and <span class="texhtml">''b''</span>,and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:

	~~::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}=\bar{y}-\hat{b}\bar{x}</math>~~

	~~and:~~

	::<math>\hat{b}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}{{y}_{i}}-\tfrac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}}{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,x_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}} \right)}^{2}}}{N}}</math>

	~~==== Rank Regression on X ====~~

	Assume that a set of data pairs .., <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>) </span>were obtained and plotted, and that the y-values are known exactly. The same least squares principle is applied, but this time, minimizing the horizontal distance between the data points and the straight line fitted to the data. The best fitting straight line to these data is the straight line <math>x=\widehat{a}+\widehat{b}y</math> such that:

	~~::<math>\underset{i=1}{\overset{N}{\mathop \sum }}\,{{(\widehat{a}+\widehat{b}{{y}_{i}}-{{x}_{i}})}^{2}}=min(a,b)\underset{i=1}{\overset{N}{\mathop \sum }}\,{{(a+b{{y}_{i}}-{{x}_{i}})}^{2}}</math>~~

	Again, <math>\widehat{a}</math> and <math>\widehat b</math> are the least squares estimates of and <span class="texhtml">''b'',</span> and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:

	~~::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}=\bar{x}-\hat{b}\bar{y}</math>~~

	~~:and:~~

	::<math>\widehat{b}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}{{y}_{i}}-\tfrac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}}{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,y_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}} \right)}^{2}}}{N}}</math>

	~~The corresponding relations for determining the parameters for specific distributions (i.e''.'', Weibull, exponential, etc.), are presented in the chapters covering that distribution.~~

	~~==== The Correlation Coefficient ====~~

	The correlation coefficient is a measure of how well the linear regression model fits the data and is usually denoted by <span class="texhtml">ρ</span>. In the case of life data analysis, it is a measure for the strength of the linear relation (correlation) between the median ranks and the data. The population correlation coefficient is defined as follows:

	~~::<math>\rho =\frac{{{\sigma }_{xy}}}{{{\sigma }_{x}}{{\sigma }_{y}}}</math>~~

	where <span class="texhtml">σ<sub>''x''''y'''</sub> = </span>covariance of <span class="texhtml">''x''</span> and <span class="texhtml">''y''</span> , <span class="texhtml">σ<sub>''x''</sub> = </span>standard deviation of <span class="texhtml">''x''</span>, and <span class="texhtml">σ<sub>''y''</sub> = </span>standard deviation of <span class="texhtml">''y''</span>.

	~~The estimator of <span class="texhtml">ρ</span> is the sample correlation coefficient, <math>\hat{\rho }</math>, given by,~~

	::<math>\hat{\rho }=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}{{y}_{i}}-\tfrac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}}{\sqrt{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,x_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}} \right)}^{2}}}{N} \right)\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,y_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}} \right)}^{2}}}{N} \right)}}</math>

	~~The range of <math>\hat \rho </math> is <math>-1\le \hat{\rho }\le 1.</math>~~

	~~[[Image:correlationcoeffficient.png\|center\|250px]]~~

	The closer the value is to <math>\pm 1</math>, the better the linear fit. Note that +1 indicates a perfect fit (the paired values ( <span class="texhtml">''x''<sub>''i''</sub>,''y''<sub>''i''</sub></span> ) lie on a straight line) with a positive slope, while -1 indicates a perfect fit with a negative slope. A correlation coefficient value of zero would indicate that the data are randomly scattered and have no pattern or correlation in relation to the regression line model.

	~~<br>~~

	~~==== '''ReliaSoft's Alternate Ranking Method (RRM)''' ====~~

	When analyzing interval data, it is commonplace to assume that the actual failure time occurred at the midpoint of the interval. To be more conservative, you can use the starting point of the interval or you can use the end point of the interval to be most optimistic. Weibull++ allows you to employ ReliaSoft's ranking method (RRM) when analyzing interval data. Using an iterative process, this ranking method is an improvement over the standard ranking method (SRM). For more details on this method see [[ReliaSoft's Alternate Ranking Method]].

	~~==== '''Comments on the Least Squares Method''' ====~~

	~~The least squares estimation method is quite good for functions that can be linearized.<sup></sup>~~ For these distributions, the calculations are relatively easy and straightforward, having closed-form solutions which can readily yield an answer without having to resort to numerical techniques or tables. Furthermore, this technique provides a good measure of the goodness-of-fit of the chosen distribution in the correlation coefficient. Least squares is generally best used with data sets containing complete data, that is, data consisting only of single times-to-failure with no censored or interval data. The chapter [[Life Data Classification]] details the different data types, including complete, left censored, right censored (or suspended) and interval data.

	~~''See also''~~

	*[[Least Squares/Rank Regression Equations]]
	*Discussion on using grouped data with regression methods at [[Grouped Data Parameter Estimation]].

Nicolette Young: /* The Correlation Coefficient */

2012-04-25T17:21:52Z

The Correlation Coefficient

← Older revision		Revision as of 17:21, 25 April 2012
Line 53:		Line 53:
	The range of <math>\hat \rho </math> is <math>-1\le \hat{\rho }\le 1.</math>		The range of <math>\hat \rho </math> is <math>-1\le \hat{\rho }\le 1.</math>

	[[Image:correlationcoeffficient.png\|center\|~~500px~~]]		[[Image:correlationcoeffficient.png\|center\|250px]]

	The closer the value is to <math>\pm 1</math>, the better the linear fit. Note that +1 indicates a perfect fit (the paired values ( <span class="texhtml">''x''<sub>''i''</sub>,''y''<sub>''i''</sub></span> ) lie on a straight line) with a positive slope, while -1 indicates a perfect fit with a negative slope. A correlation coefficient value of zero would indicate that the data are randomly scattered and have no pattern or correlation in relation to the regression line model.		The closer the value is to <math>\pm 1</math>, the better the linear fit. Note that +1 indicates a perfect fit (the paired values ( <span class="texhtml">''x''<sub>''i''</sub>,''y''<sub>''i''</sub></span> ) lie on a straight line) with a positive slope, while -1 indicates a perfect fit with a negative slope. A correlation coefficient value of zero would indicate that the data are randomly scattered and have no pattern or correlation in relation to the regression line model.

Nicolette Young: /* Background Theory */

2012-04-25T17:21:40Z

Background Theory

← Older revision		Revision as of 17:21, 25 April 2012
Line 7:		Line 7:
	The method of linear least squares is used for all regression analysis performed by Weibull++, except for the cases of the three-parameter Weibull, mixed Weibull, gamma and generalized gamma distributions, where a non-linear regression technique is employed. The terms '''linear regression''' and '''least squares''' are used synonymously in this reference. In Weibull++, the term ''rank regression'' is used instead of least squares, or linear regression, because the regression is performed on the rank values, more specifically, the median rank values (represented on the y-axis). The method of least squares requires that a straight line be fitted to a set of data points, such that the sum of the squares of the distance of the points to the fitted line is minimized. This minimization can be performed in either the vertical or horizontal direction. If the regression is on <span class="texhtml">''X''</span>, then the line is fitted so that the horizontal deviations from the points to the line are minimized. If the regression is on Y, then this means that the distance of the vertical deviations from the points to the line is minimized. This is illustrated in the following figure.		The method of linear least squares is used for all regression analysis performed by Weibull++, except for the cases of the three-parameter Weibull, mixed Weibull, gamma and generalized gamma distributions, where a non-linear regression technique is employed. The terms '''linear regression''' and '''least squares''' are used synonymously in this reference. In Weibull++, the term ''rank regression'' is used instead of least squares, or linear regression, because the regression is performed on the rank values, more specifically, the median rank values (represented on the y-axis). The method of least squares requires that a straight line be fitted to a set of data points, such that the sum of the squares of the distance of the points to the fitted line is minimized. This minimization can be performed in either the vertical or horizontal direction. If the regression is on <span class="texhtml">''X''</span>, then the line is fitted so that the horizontal deviations from the points to the line are minimized. If the regression is on Y, then this means that the distance of the vertical deviations from the points to the line is minimized. This is illustrated in the following figure.

	<br>[[Image:minimizingdistance.png\|center\|~~400px~~]]		<br>[[Image:minimizingdistance.png\|center\|250px]]

	==== Rank Regression on <span class="texhtml">''Y''</span> ====		==== Rank Regression on <span class="texhtml">''Y''</span> ====

Harry Guo: /* Rank Regression on Y */

2012-03-16T22:48:26Z

Rank Regression on Y

← Older revision		Revision as of 22:48, 16 March 2012
Line 11:		Line 11:
	==== Rank Regression on <span class="texhtml">''Y''</span> ====		==== Rank Regression on <span class="texhtml">''Y''</span> ====

	Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced <math>(\hat{ })</math> symbol indicates that this value is an estimate) such that:		Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced (<math>\hat{ }</math>) symbol indicates that this value is an estimate) such that:

	<center> <math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math> </center>		<center> <math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math> </center>

Harry Guo: /* Rank Regression on Y */

2012-03-16T22:47:43Z

Rank Regression on Y

← Older revision		Revision as of 22:47, 16 March 2012
Line 13:		Line 13:
	Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced <math>(\hat{ })</math> symbol indicates that this value is an estimate) such that:		Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced <math>(\hat{ })</math> symbol indicates that this value is an estimate) such that:

	<math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math>		<center> <math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math> </center>

	and where <math>\hat{a}</math> and <math>\hat b</math> are the ''least squares estimates'' of <span class="texhtml">''a''</span> and <span class="texhtml">''b''</span>,and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:		and where <math>\hat{a}</math> and <math>\hat b</math> are the ''least squares estimates'' of <span class="texhtml">''a''</span> and <span class="texhtml">''b''</span>,and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:
Line 19:		Line 19:
	::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}=\bar{y}-\hat{b}\bar{x}</math>		::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}=\bar{y}-\hat{b}\bar{x}</math>

	:and:		and:

	::<math>\hat{b}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}{{y}_{i}}-\tfrac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}}{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,x_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}} \right)}^{2}}}{N}}</math>		::<math>\hat{b}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}{{y}_{i}}-\tfrac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}}{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,x_{i}^{2}-\tfrac{{{\left( \underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}} \right)}^{2}}}{N}}</math>

Harry Guo: /* Rank Regression on Y */

2012-03-16T22:47:18Z

Rank Regression on Y

← Older revision		Revision as of 22:47, 16 March 2012
Line 11:		Line 11:
	==== Rank Regression on <span class="texhtml">''Y''</span> ====		==== Rank Regression on <span class="texhtml">''Y''</span> ====

	Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced <math>(\hat{ })</math> symbol indicates that this value is an estimate) such that: .. and where <math>\hat{a}</math> and <math>\hat b</math> are the ''least squares estimates'' of <span class="texhtml">''a''</span> and <span class="texhtml">''b''</span>,and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:		Assume that a set of data pairs <span class="texhtml">(''x''<sub>1</sub>,''y''<sub>1</sub>)</span>, <span class="texhtml">(''x''<sub>2</sub>,''y''<sub>2</sub>)</span>,..., <span class="texhtml">(''x''<sub>''N''</sub>,''y''<sub>''N''</sub>)</span> were obtained and plotted, and that the <span class="texhtml">''x''</span> -values are known exactly. Then, according to the ''least squares principle,'' which minimizes the vertical distance between the data points and the straight line fitted to the data, the best fitting straight line to these data is the straight line <math>y=\hat{a}+\hat{b}x</math> (where the recently introduced <math>(\hat{ })</math> symbol indicates that this value is an estimate) such that:

			<math>\sum\limits_{i=1}^{N}{{{\left( \hat{a}+\hat{b}{{x}_{i}}-{{y}_{i}} \right)}^{2}}=\min \sum\limits_{i=1}^{N}{{{\left( a+b{{x}_{i}}-{{y}_{i}} \right)}^{2}}}}</math>

			and where <math>\hat{a}</math> and <math>\hat b</math> are the ''least squares estimates'' of <span class="texhtml">''a''</span> and <span class="texhtml">''b''</span>,and <span class="texhtml">''N''</span> is the number of data points. These equations are minimized by estimates of <math>\widehat a</math> and <math>\widehat{b}</math> such that:

	::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}=\bar{y}-\hat{b}\bar{x}</math>		::<math>\hat{a}=\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{y}_{i}}}{N}-\hat{b}\frac{\underset{i=1}{\overset{N}{\mathop{\sum }}}\,{{x}_{i}}}{N}=\bar{y}-\hat{b}\bar{x}</math>

Kate Racaza: /* The Correlation Coefficient */

2012-03-16T18:09:15Z

The Correlation Coefficient

← Older revision		Revision as of 18:09, 16 March 2012
Line 41:		Line 41:
	::<math>\rho =\frac{{{\sigma }_{xy}}}{{{\sigma }_{x}}{{\sigma }_{y}}}</math>		::<math>\rho =\frac{{{\sigma }_{xy}}}{{{\sigma }_{x}}{{\sigma }_{y}}}</math>

	where <span class="texhtml">σ<sub>''x''''y'''</sub> = </span>covariance of and <span class="texhtml">''y''</span> , <span class="texhtml">σ<sub>''x''</sub> = </span>standard deviation of <span class="texhtml">''x''</span> , and <span class="texhtml">σ<sub>''y''</sub> = </span>standard deviation of <span class="texhtml">''y''</span>.		where <span class="texhtml">σ<sub>''x''''y'''</sub> = </span>covariance of <span class="texhtml">''x''</span> and <span class="texhtml">''y''</span> , <span class="texhtml">σ<sub>''x''</sub> = </span>standard deviation of <span class="texhtml">''x''</span>, and <span class="texhtml">σ<sub>''y''</sub> = </span>standard deviation of <span class="texhtml">''y''</span>.

	The estimator of <span class="texhtml">ρ</span> is the sample correlation coefficient, <math>\hat{\rho }</math>, given by,		The estimator of <span class="texhtml">ρ</span> is the sample correlation coefficient, <math>\hat{\rho }</math>, given by,

Nicolette Young: /* The Correlation Coefficient */

2012-03-13T16:00:37Z

The Correlation Coefficient

← Older revision		Revision as of 16:00, 13 March 2012
Line 49:		Line 49:
	The range of <math>\hat \rho </math> is <math>-1\le \hat{\rho }\le 1.</math>		The range of <math>\hat \rho </math> is <math>-1\le \hat{\rho }\le 1.</math>

	[[Image:correlationcoeffficient.png~~\|thumb~~\|center\|500px]]		[[Image:correlationcoeffficient.png\|center\|500px]]

	The closer the value is to <math>\pm 1</math>, the better the linear fit. Note that +1 indicates a perfect fit (the paired values ( <span class="texhtml">''x''<sub>''i''</sub>,''y''<sub>''i''</sub></span> ) lie on a straight line) with a positive slope, while -1 indicates a perfect fit with a negative slope. A correlation coefficient value of zero would indicate that the data are randomly scattered and have no pattern or correlation in relation to the regression line model.		The closer the value is to <math>\pm 1</math>, the better the linear fit. Note that +1 indicates a perfect fit (the paired values ( <span class="texhtml">''x''<sub>''i''</sub>,''y''<sub>''i''</sub></span> ) lie on a straight line) with a positive slope, while -1 indicates a perfect fit with a negative slope. A correlation coefficient value of zero would indicate that the data are randomly scattered and have no pattern or correlation in relation to the regression line model.

Nicolette Young: /* Background Theory */

2012-03-13T16:00:26Z

Background Theory

← Older revision		Revision as of 16:00, 13 March 2012
Line 7:		Line 7:
	The method of linear least squares is used for all regression analysis performed by Weibull++, except for the cases of the three-parameter Weibull, mixed Weibull, gamma and generalized gamma distributions, where a non-linear regression technique is employed. The terms '''linear regression''' and '''least squares''' are used synonymously in this reference. In Weibull++, the term ''rank regression'' is used instead of least squares, or linear regression, because the regression is performed on the rank values, more specifically, the median rank values (represented on the y-axis). The method of least squares requires that a straight line be fitted to a set of data points, such that the sum of the squares of the distance of the points to the fitted line is minimized. This minimization can be performed in either the vertical or horizontal direction. If the regression is on <span class="texhtml">''X''</span>, then the line is fitted so that the horizontal deviations from the points to the line are minimized. If the regression is on Y, then this means that the distance of the vertical deviations from the points to the line is minimized. This is illustrated in the following figure.		The method of linear least squares is used for all regression analysis performed by Weibull++, except for the cases of the three-parameter Weibull, mixed Weibull, gamma and generalized gamma distributions, where a non-linear regression technique is employed. The terms '''linear regression''' and '''least squares''' are used synonymously in this reference. In Weibull++, the term ''rank regression'' is used instead of least squares, or linear regression, because the regression is performed on the rank values, more specifically, the median rank values (represented on the y-axis). The method of least squares requires that a straight line be fitted to a set of data points, such that the sum of the squares of the distance of the points to the fitted line is minimized. This minimization can be performed in either the vertical or horizontal direction. If the regression is on <span class="texhtml">''X''</span>, then the line is fitted so that the horizontal deviations from the points to the line are minimized. If the regression is on Y, then this means that the distance of the vertical deviations from the points to the line is minimized. This is illustrated in the following figure.

	<br>[[Image:minimizingdistance.png~~\|thumb~~\|center\|400px]]		<br>[[Image:minimizingdistance.png\|center\|400px]]

	==== Rank Regression on <span class="texhtml">''Y''</span> ====		==== Rank Regression on <span class="texhtml">''Y''</span> ====