likelihood ratio test

尤度比検定

WordNet

1. undergo a test; "She doesnt test well"
2. any standardized procedure for measuring sensitivity or memory or intelligence or aptitude or personality etc; "the test was standardized on a large sample of students" (同)mental test, mental testing, psychometric test
3. the act of undergoing testing; "he survived the great test of battle"; "candidates must compete in a trial of skill" (同)trial
4. the act of testing something; "in the experimental trials the amount of carbon was measured separately"; "he called each flip of the coin a new trial" (同)trial, run
5. a hard outer covering as of some amoebas and sea urchins
6. put to the test, as for its quality, or give experimental use to; "This approach has been tried with good results"; "Test this recipe" (同)prove, try, try out, examine, essay
7. achieve a certain score or rating on a test; "She tested high on the LSAT and was admitted to all the good law schools"
8. determine the presence or properties of (a substance)
9. show a certain characteristic when tested; "He tested positive for HIV"
10. give (hair) the appearance of being fuller by using a rat
11. a pad (usually made of hair) worn as part of a womans coiffure
12. any of various long-tailed rodents similar to but larger than a mouse
13. catch rats, especially with dogs
14. desert ones party or group of friends, for example, for ones personal advantage
15. employ scabs or strike breakers in
16. an examination of the characteristics of something; "there are laboratories for commercial testing"; "it involved testing thousands of children for smallpox"
17. the act of subjecting to experimental test in order to determine how well something works; "they agreed to end the testing of atomic weapons"
18. the probability of a specified outcome (同)likeliness
19. the relative magnitudes of two quantities (usually expressed as a quotient)

PrepTutorEJDIC

1. (人の能力などの)『試験』,考査,テスト / (物事の)『試験』,検済,試錬,実験《+of+名》 / 化学分析;試薬 / =test match / …‘を'『試験する』,検査する / …‘を'化学分析する / (…の)試験を受ける,試験をする《+for+名》
2. 『ネズミ』 / ひきょう者,裏切り者 / ネズミをつかまえる / 《話》(人を)裏切る,密告する《+『on』+『名』〈人〉》
3. (…が)ありそうなこと,(…の)見込み,可能性(probability)《+『of』+『名』》
4. 『比』,比率,『割合』;『比例』

Wikipedia preview

出典(authority):フリー百科事典『ウィキペディア（Wikipedia）』「2015/08/03 04:15:03」(JST)

wiki en

[Wiki en表示]

Not to be confused with the use of likelihood ratios in diagnostic testing.

In statistics, a likelihood ratio test is a statistical test used to compare the goodness of fit of two models, one of which (the null model) is a special case of the other (the alternative model). The test is based on the likelihood ratio, which expresses how many times more likely the data are under one model than the other. This likelihood ratio, or equivalently its logarithm, can then be used to compute a p-value, or compared to a critical value to decide whether to reject the null model in favour of the alternative model. When the logarithm of the likelihood ratio is used, the statistic is known as a log-likelihood ratio statistic, and the probability distribution of this test statistic, assuming that the null model is true, can be approximated using Wilks's theorem.

In the case of distinguishing between two models, each of which has no unknown parameters, use of the likelihood ratio test can be justified by the Neyman–Pearson lemma, which demonstrates that such a test has the highest power among all competitors.

Use

Each of the two competing models, the null model and the alternative model, is separately fitted to the data and the log-likelihood recorded. The test statistic (often denoted by D) is twice the difference in these log-likelihoods:

$\begin{align} D & = -2\ln\left( \frac{\text{likelihood for null model}}{\text{likelihood for alternative model}} \right) \\ &= -2\ln(\text{likelihood for null model}) + 2\ln(\text{likelihood for alternative model}) \\ \end{align}$

The model with more parameters will always fit at least as well (have an equal or greater log-likelihood). Whether it fits significantly better and should thus be preferred is determined by deriving the probability or p-value of the difference D. Where the null hypothesis represents a special case of the alternative hypothesis, the probability distribution of the test statistic is approximately a chi-squared distribution with degrees of freedom equal to df2 − df1 . Symbols df1 and df2 represent the number of free parameters of models 1 and 2, the null model and the alternative model, respectively.

Here is an example of use. If the null model has 1 parameter and a log-likelihood of −8024 and the alternative model has 3 parameters and a log-likelihood of −8012, then the probability of this difference is that of chi-squared value of +2·(8024 − 8012) = 24 with 3 − 1 = 2 degrees of freedom. Certain assumptions must be met for the statistic to follow a chi-squared distribution, and often empirical p-values are computed.

The likelihood-ratio test requires nested models, i.e. models in which the more complex one can be transformed into the simpler model by imposing a set of constraints on the parameters. If the models are not nested, then a generalization of the likelihood-ratio test can usually be used instead: the relative likelihood.

Simple-vs-simple hypotheses

Main article: Neyman–Pearson lemma

A statistical model is often a parametrized family of probability density functions or probability mass functions . A simple-vs-simple hypothesis test has completely specified models under both the null and alternative hypotheses, which for convenience are written in terms of fixed values of a notional parameter :

$\begin{align} H_0 &:& \theta=\theta_0 ,\\ H_1 &:& \theta=\theta_1 . \end{align}$

Note that under either hypothesis, the distribution of the data is fully specified; there are no unknown parameters to estimate. The likelihood ratio test is based on the likelihood ratio, which is often denoted by (the capital Greek letter lambda). The likelihood ratio is defined as follows:

$\Lambda(x) = \frac{ L(\theta_0|x) }{ L(\theta_1|x) } = \frac{ f(\cup_i \, x_i|\theta_0) }{ f(\cup_i \, x_i|\theta_1) }$

or

where is the likelihood function, and is the supremum function. Note that some references may use the reciprocal as the definition. In the form stated here, the likelihood ratio is small if the alternative model is better than the null model and the likelihood ratio test provides the decision rule as follows:

If , do not reject ;

If , reject ;

Reject with probability if

The values are usually chosen to obtain a specified significance level , through the relation . The Neyman-Pearson lemma states that this likelihood ratio test is the most powerful among all level tests for this problem.

Definition (likelihood ratio test for composite hypotheses)

A null hypothesis is often stated by saying the parameter is in a specified subset of the parameter space .

$\begin{align} H_0 &:& \theta \in \Theta_0\\ H_1 &:& \theta \in \Theta_0^{\complement} \end{align}$

The likelihood function is (with being the pdf or pmf), which is a function of the parameter with held fixed at the value that was actually observed, i.e., the data. The likelihood ratio test statistic is

Here, the notation refers to the supremum function.

A likelihood ratio test is any test with critical region (or rejection region) of the form where is any number satisfying . Many common test statistics such as the Z-test, the F-test, Pearson's chi-squared test and the G-test are tests for nested models and can be phrased as log-likelihood ratios or approximations thereof.

Interpretation

Being a function of the data , the likelihood ratio is therefore a statistic. The likelihood ratio test rejects the null hypothesis if the value of this statistic is too small. How small is too small depends on the significance level of the test, i.e., on what probability of Type I error is considered tolerable ("Type I" errors consist of the rejection of a null hypothesis that is true).

The numerator corresponds to the maximum likelihood of an observed outcome under the null hypothesis. The denominator corresponds to the maximum likelihood of an observed outcome varying parameters over the whole parameter space. The numerator of this ratio is less than the denominator. The likelihood ratio hence is between 0 and 1. Low values of the likelihood ratio mean that the observed result was less likely to occur under the null hypothesis as compared to the alternative. High values of the statistic mean that the observed outcome was nearly as likely to occur under the null hypothesis as the alternative, and the null hypothesis cannot be rejected.

Distribution: Wilks's theorem

If the distribution of the likelihood ratio corresponding to a particular null and alternative hypothesis can be explicitly determined then it can directly be used to form decision regions (to accept/reject the null hypothesis). In most cases, however, the exact distribution of the likelihood ratio corresponding to specific hypotheses is very difficult to determine. A convenient result, attributed to Samuel S. Wilks, says that as the sample size approaches , the test statistic for a nested model will be asymptotically -distributed with degrees of freedom equal to the difference in dimensionality of and . This means that for a great variety of hypotheses, a practitioner can compute the likelihood ratio for the data and compare to the value corresponding to a desired statistical significance as an approximate statistical test.

Examples

Coin tossing

An example, in the case of Pearson's test, we might try to compare two coins to determine whether they have the same probability of coming up heads. Our observation can be put into a contingency table with rows corresponding to the coin and columns corresponding to heads or tails. The elements of the contingency table will be the number of times the coin for that row came up heads or tails. The contents of this table are our observation .

	Heads	Tails
Coin 1
Coin 2

Here consists of the possible combinations of values of the parameters , , , and , which are the probability that coins 1 and 2 come up heads or tails. In what follows, and . The hypothesis space is constrained by the usual constraints on a probability distribution, , and . The space of the null hypothesis is the subspace where . Writing for the best values for under the hypothesis , the maximum likelihood estimate is given by

Similarly, the maximum likelihood estimates of under the null hypothesis are given by

which does not depend on the coin .

The hypothesis and null hypothesis can be rewritten slightly so that they satisfy the constraints for the logarithm of the likelihood ratio to have the desired nice distribution. Since the constraint causes the two-dimensional to be reduced to the one-dimensional , the asymptotic distribution for the test will be , the distribution with one degree of freedom.

For the general contingency table, we can write the log-likelihood ratio statistic as

References

External links

• Practical application of likelihood ratio test described
• R Package: Wald's Sequential Probability Ratio Test
• Richard Lowry's Predictive Values and Likelihood Ratios Online Clinical Calculator

UpToDate Contents

全文を閲覧するには購読必要です。 To read the full text you will need to subscribe.

• 1. 診断的検査の評価 evaluating diagnostic tests
• 2. 生物統計学および疫学に関する一般用語集 glossary of common biostatistical and epidemiological terms
• 3. 分娩時胎児心拍数の評価 intrapartum fetal heart rate assessment
• 4. 褐色細胞腫の臨床症状および診断 clinical presentation and diagnosis of pheochromocytoma
• 5. クッシング症候群の診断 establishing the diagnosis of cushings syndrome

English Journal

• Prescription of antidepressants is increased in Danish patients with polycystic ovary syndrome and is associated with hyperandrogenism. A population-based cohort study.

• Altinok ML1, Glintborg D, Depont Christensen R, Hallas J, Andersen M.Author information 1Department of Endocrinology and Metabolism, Odense University Hospital, Odense C, Denmark.AbstractOBJECTIVE: Quality of life is impaired in polycystic ovary syndrome (PCOS). In this study, we compared the time to first prescription of antidepressants (ADM) in PCOS vs two control groups.
• Clinical endocrinology.Clin Endocrinol (Oxf).2014 Jun;80(6):884-9. doi: 10.1111/cen.12365. Epub 2013 Dec 5.
• OBJECTIVE: Quality of life is impaired in polycystic ovary syndrome (PCOS). In this study, we compared the time to first prescription of antidepressants (ADM) in PCOS vs two control groups.DESIGN: Register-based cohort study.PATIENTS: One thousand and one hundred and twenty-four premenopausal women
• PMID 24224860

• MicroRNAs in Body Fluids as Biomarkers for Non-small Cell Lung Cancer: A Systematic Review.

• Huang Y1, Hu Q, Deng Z, Hang Y, Wang J, Wang K.Author information 1Department of Laboratory Medicine, Affiliated Hospital of Luzhou Medical College, Luzhou, Sichuan Province, P. R. China. hys@live.cn.AbstractNon-small cell lung cancer (NSCLC) is one of the most common life-threatening malignant tumors. A test for early diagnosis of NSCLC needs to be not too invasive and not too heavy a burden for weakened patients. A series of studies reported various microRNAs (miRNAs) could be novel serum biomarkers for NSCLC. However, the diagnostic ability of different miRNA biomarkers varies among the reports. The goal of this study was to perform a systematic review to examine the effect of miRNAs on NSCLC-related outcomes. We systematically searched The Cochrane Central Register of Controlled Trials, MEDLINE, Pub Med, EMBASE, the Chinese Biomedical Literature Database, the China Academic Journals Full-text Database, and the Chinese Scientific Journals Database for potential studies. Studies were included if they were related to miRNAs, NSCLC, and reported diagnostic outcomes. Diagnostic values analysis was used to summarize the overall test performance of miRNAs. 13 studies were included in this systematic review. The ranges of sensitivity (SEN) and specificity (SPE) of diagnosis model with miRNAs as identifying NSCLC were 0.69˜1.00 and 0.66˜1.00, respectively. The overall area under the curve (AUC) value of summary receiver operating characteristic (SROC) curve was 0.9151. The ranges of positive likelihood ratio (PLR) and negative likelihood ratio (NLR) were 2.33˜24.75 and 0.010.40, respectively. The range of diagnostic odds ratio (DOR) was 6.52˜983.38. The current evidence indicates that miRNAs in body fluids show high accuracy in identifying NSCLC, and could be a useful screening tool for diagnosing NSCLC patients.
• Technology in cancer research & treatment.Technol Cancer Res Treat.2014 Jun;13(3):277-87. doi: 10.7785/tcrt.2012.500377. Epub 2013 Sep 20.
• Non-small cell lung cancer (NSCLC) is one of the most common life-threatening malignant tumors. A test for early diagnosis of NSCLC needs to be not too invasive and not too heavy a burden for weakened patients. A series of studies reported various microRNAs (miRNAs) could be novel serum biomarkers f
• PMID 24066954

• Preperimetric normal tension glaucoma study: long-term clinical course and effect of therapeutic lowering of intraocular pressure.

• Jeong JH1, Park KH, Jeoung JW, Kim DM.Author information 1Department of Ophthalmology, Seoul National University Hospital, Seoul, Korea.AbstractPURPOSE: The purpose of this study was to investigate the long-term clinical course of normotensive preperimetric glaucoma (PPG).
• Acta ophthalmologica.Acta Ophthalmol.2014 May;92(3):e185-93. doi: 10.1111/aos.12277. Epub 2014 Jan 23.
• PURPOSE: The purpose of this study was to investigate the long-term clinical course of normotensive preperimetric glaucoma (PPG).METHODS: The medical records of 71 eyes of 71 patients with normotensive PPG who underwent intraocular pressure (IOP)-lowering therapy were reviewed retrospectively. The p
• PMID 24456145

Japanese Journal

• Comparison of model selection methods for the estimation of principal points for a multivariate binary distribution

• Yamashita Haruka,Matsuura Shun,Suzuki Hideo
• Total Quality Science 1(1), 22-31, 2015
• … This paper compares three model selection methods based on AIC, Bayesian information criterion (BIC), and the likelihood ratio test (LRT) for estimating principal points for a multivariate binary distribution. …
• NAID 130005070675

• 時変母数による非定常水文頻度解析手法のモデル選択に関する考察

• 林 敬大,立川 康人,椎葉 充晴
• 土木学会論文集B1（水工学） 71(1), 28-42, 2015
• 　時間を説明変数とする多項式回帰モデルによって母数をモデル化することで，非定常の水文頻度解析モデルを構築することができる．このとき，確率分布モデルの選択手法として尤度比検定が利用されることが多いが，包含関係にないモデル間の選択には有効ではない．そこで本研究では，定常の場合と同様に非定常水文頻度解析モデルのモデル選択規準としてもTICやAICが有効であることを解析的に示す．次に，時変母数を導入した水 …
• NAID 130005065587

• 隠匿情報検査研究で用いられる統計量の判定成績による比較

• 松田 いづみ,小川 時洋,常岡 充子
• 日本法科学技術学会誌 20(1), 59-67, 2015
• …   The concealed information test (CIT) estimates whether an examinee knows crime-relevant information on the basis of differences in physiological responses between the crime-relevant and irrelevant information. … To examine the differences in physiological responses, this study used the following four statistical values: Lykken's scores, likelihood ratios, effect sizes, and p values of randomization tests. …
• NAID 130004942662

Related Links

• Likelihood-ratio testとは - goo Wikipedia (ウィキペディア)

This article includes a list of references, but its sources remain unclear because it has insufficient inline citations. Please help to improve this article by ... In statistics, a likelihood ratio test is a statistical test used to compare the goodness of fit ...

• 8.2.3.3. Likelihood ratio tests - Information Technology ...

Likelihood Ratio Tests are a powerful, very general method of testing model assumptions. However, they require special software, not always readily available. Likelihood functions for reliability data are described in Section 4. Two ways ...

Related Pictures

---

★リンクテーブル★

関連記事	「likelihood」「testing」「rat」「ratio」「test」

「likelihood」

　　[★]

• n.

• 見込み、可能性、(統計)尤度

関

capability、chance、estimate、expectation、feasibility、odds、perspective、possibility、potential、potentiality、probability、promise、prospect

　 　

「testing」

　　[★]

• n.

• 試験

関

assessment、data quality、exam、examination、examine、experimental design、matched group、measurement、research design、scoring method、test、trial

　 　

「rat」

　　[★]

• n.

• (げっ歯類)ラット、(マウスも含めての総称)ネズミ、ラットの

関

laboratory rat、mouse、Norway rat、Rattus、Rattus norvegicus

　 　 　 　 　 　 　

「ratio」

　　[★]

• 比、割合、レシオ

関

fraction、percentage、proportion、rate、specific

　 　

「test」

　　[★] テスト