|
|
| Line 1: |
Line 1: |
| {{Regression bar}}
| | Alyson is what my spouse loves to call me but I don't like when [http://ustanford.com/index.php?do=/profile-38218/info/ best psychics] people use my complete name. Invoicing is what I do for a residing but I've usually needed my personal company. For years he's been residing in [http://mybrandcp.com/xe/board_XmDx25/107997 online reader] Mississippi and he doesn't strategy on altering it. She is truly fond of caving but she doesn't have the time lately.<br><br>Also visit my webpage [http://Myoceancounty.net/groups/apply-these-guidelines-when-gardening-and-grow/ psychic readers] |
| {{merge to|Ordinal regression|discuss=Talk:Ordinal regression#Merge discussion|date=May 2012}}
| |
| | |
| In [[statistics]], the '''ordered logit''' model (also '''ordered logistic regression''' or '''proportional odds model'''), is a [[Regression analysis|regression]] model for [[Levels_of_measurement#Ordinal type|ordinal]] [[dependent variable]]s. It can be thought of as an extension of the [[logistic regression]] model that applies to [[dichotomous]] dependent variables, allowing for more than two (ordered) response categories.
| |
| | |
| The model only applies to data that meet the ''proportional odds assumption'', that the relationship{{clarify|date=January 2013}} between any two pairs of outcome groups is statistically the same. This means that the coefficients that describe the relationship between, say, the lowest versus all higher categories of the response variable are the same as those that describe the relationship between the next lowest category and all higher categories, etc. Because the relationship between all pairs of groups is the same, there is only one set of coefficients.<ref>http://www.ats.ucla.edu/stat/r/dae/ologit.htm</ref>
| |
| | |
| The model cannot be consistently estimated using [[ordinary least squares]]; it is usually estimated using [[maximum likelihood]].
| |
| | |
| Examples of multiple ordered response categories include bond ratings, opinion surveys with responses ranging from "strongly agree" to "strongly disagree," levels of state spending on government programs (high, medium, or low), the level of insurance coverage chosen (none, partial, or full), and employment status (not employed, employed part-time, or fully employed).<ref>Greene, William H., ''Econometric Analysis'' (fifth edition), Prentice Hall, 2003, 736-740.</ref>
| |
| | |
| Suppose the underlying process to be characterized is
| |
| | |
| :<math>y^* =x' \beta + \epsilon</math>,
| |
| | |
| where ''y*'' is the exact but unobserved dependent variable (perhaps the exact level of agreement with the statement proposed by the pollster); '''x''' is the vector of independent variables, and '''<math>\beta</math>''' is the vector of regression coefficients which we wish to estimate. Further suppose that while we cannot observe ''y*'', we instead can only observe the categories of response
| |
| | |
| :<math> y= \begin{cases}
| |
| 0~~ \text{if}~~y^* \le \mu_1, \\
| |
| 1~~ \text{if}~~\mu_1<y^* \le \mu_2, \\
| |
| 2~~ \text{if}~~\mu_2 <y^* \le \mu_3 \\
| |
| \vdots \\
| |
| N~~ \text{if}~~ \mu_{N} < y^*.
| |
| \end{cases}</math>
| |
| | |
| Then the ordered logit technique will use the observations on ''y'', which are a form of [[Censoring (statistics)|censored data]] on ''y*'', to fit the parameter vector <math>\beta</math>.
| |
| | |
| ==See also==
| |
| | |
| *[[Multinomial logit]]
| |
| *[[Multinomial probit]]
| |
| *[[Ordered probit]]
| |
| | |
| ==References==
| |
| | |
| {{Reflist}}
| |
| | |
| ==Further reading==
| |
| *{{cite web| title=Sample size for an ordinal outcome | date=2004-09-22| url=http://www.childrens-mercy.org/stats/weblog2004/OrdinalLogistic.asp| author=Steve Simon| work=STATS - STeve's Attempt to Teach Statistics | accessdate=2008-03-04}}
| |
| | |
| *{{cite book
| |
| | last= Woodward | first=Mark
| |
| | year = 2005
| |
| | title = Epidemiology: Study Design and Data Analysis
| |
| | publisher = Chapman & Hall/CRC
| |
| | isbn = 978-1-58488-415-6 | edition=2nd edition
| |
| }}
| |
| *{{cite book | last = Hardin| first = James | coauthors = [[Joseph Hilbe|Hilbe, Joseph]] | title = Generalized Linear Models and Extensions | publisher = College Station: Stata Press | year = 2007|edition=2nd edition | isbn=978-1-59718-014-6}}
| |
| | |
| [[Category:Regression analysis]]
| |
| [[Category:Categorical data]]
| |
Alyson is what my spouse loves to call me but I don't like when best psychics people use my complete name. Invoicing is what I do for a residing but I've usually needed my personal company. For years he's been residing in online reader Mississippi and he doesn't strategy on altering it. She is truly fond of caving but she doesn't have the time lately.
Also visit my webpage psychic readers