情報管理学科で学ぶ



Similar documents
Use R

R John Fox R R R Console library(rcmdr) Rcmdr R GUI Windows R R SDI *1 R Console R 1 2 Windows XP Windows * 2 R R Console R ˆ R

(lm) lm AIC 2 / 1

DAA09

Rによる計量分析:データ解析と可視化 - 第3回 Rの基礎とデータ操作・管理

R Console >R ˆ 2 ˆ 2 ˆ Graphics Device 1 Rcmdr R Console R R Rcmdr Rcmdr Fox, 2007 Fox and Carvalho, 2012 R R 2

k2 ( :35 ) ( k2) (GLM) web web 1 :

J1順位と得点者数の関係分析

<4D F736F F F696E74202D C835B B E B8CDD8AB B83685D>


SC-85X2取説




untitled

活用ガイド (ソフトウェア編)

講義のーと : データ解析のための統計モデリング. 第3回

インターネットを活用した経済分析 - フリーソフト Rを使おう


一般化線形 (混合) モデル (2) - ロジスティック回帰と GLMM

II

これわかWord2010_第1部_ indd

パワポカバー入稿用.indd

これでわかるAccess2010

活用ガイド (ソフトウェア編)

o 2o 3o 3 1. I o 3. 1o 2o 31. I 3o PDF Adobe Reader 4o 2 1o I 2o 3o 4o 5o 6o 7o 2197/ o 1o 1 1o

1 15 R Part : website:

untitled

平成18年版 男女共同参画白書

III


ii


2

untitled

i

Stata11 whitepapers mwp-037 regress - regress regress. regress mpg weight foreign Source SS df MS Number of obs = 74 F(


DVIOUT-MTT元原

i


Wide Scanner TWAIN Source ユーザーズガイド

> usdata01 と打ち込んでエンター キーを押すと V1 V2 V : : : : のように表示され 読み込まれていることがわかる ここで V1, V2, V3 は R が列のデータに自 動的につけた変数名である ( variable

エクセルカバー入稿用.indd

01_.g.r..

最小2乗法

報告書.PDF

kubostat2017c p (c) Poisson regression, a generalized linear model (GLM) : :


kubostat2018d p.2 :? bod size x and fertilization f change seed number? : a statistical model for this example? i response variable seed number : { i

201711grade2.pdf

活用ガイド (ハードウェア編)

untitled


入門ガイド

2004/01/ /01/23 2 I /04/ /04/ ,-1-8-1,-2-2-1,-3-4-1,-3-5-1,-4-2-1, ,-5-6-1, _.doc 1

¥¤¥ó¥¿¡¼¥Í¥Ã¥È·×¬¤È¥Ç¡¼¥¿²òÀÏ Âè2²ó

困ったときのQ&A

²¾ÁÛ¾õ¶·É¾²ÁË¡¤Î¤¿¤á¤Î¥Ñ¥Ã¥±¡¼¥¸DCchoice ¡Ê»ÃÄêÈÇ¡Ë

R int num factor character 1 2 (dichotomous variable) (trichotomous variable) 3 (nominal scale) M F 1 2 coding as.numeric() as.integer() 2

28

q( ) 2: R 2 R R R R C:nProgram FilesnRnrw1030) [File] [Change Dir] c:ndatadir OK 2

ii

untitled

kubostat2015e p.2 how to specify Poisson regression model, a GLM GLM how to specify model, a GLM GLM logistic probability distribution Poisson distrib

講義のーと : データ解析のための統計モデリング. 第5回

k3 ( :07 ) 2 (A) k = 1 (B) k = 7 y x x 1 (k2)?? x y (A) GLM (k

kubostat2017e p.1 I 2017 (e) GLM logistic regression : : :02 1 N y count data or

5 5.1 A B mm 0.1mm Nominal Scale 74

i

BMIdata.txt DT DT <- read.table("bmidata.txt") DT head(dt) names(dt) str(dt)

5.2 White

1 2 Windows 7 *3 Windows * 4 R R Console R R Console ˆ R GUI R R R *5 R 2 R R R 6.1 ˆ 2 ˆ 2 ˆ Graphics Device 1 Rcmdr R Console R Rconsole R --sdi R M

橡6.プログラム.doc

2

活用ガイド (ソフトウェア編)

パソコン機能ガイド

パソコン機能ガイド

「産業上利用することができる発明」の審査の運用指針(案)

はしがき・目次・事例目次・凡例.indd

Javaと.NET


2004年度日本経団連規制改革要望


yamadaiR(cEFA).pdf

<4D F736F F F696E74202D BD95CF97CA89F090CD F6489F18B4195AA90CD816A>

Microsoft Word - 研究デザインと統計学.doc

provider_020524_2.PDF

I II III 28 29

生活設計レジメ

44 4 I (1) ( ) (10 15 ) ( 17 ) ( 3 1 ) (2)


1 I EViews View Proc Freeze


178 5 I 1 ( ) ( ) ( ) ( ) (1) ( 2 )

長崎県地域防災計画

29 Short-time prediction of time series data for binary option trade

udc-2.dvi


2 The Bulletin of Meiji University of Integrative Medicine 3, Yamashita 10 11

Transcription:

1/17 ` <kumazawa@biwako.shiga-u.ac.jp> http://www.biwako.shiga-u.ac.jp/sensei/kumazawa/ 6............................................ 5 1............................... 1 1.1 I II III 1 1.2 2 1.3 2 2...................................... 2 3........................................ 3 3.1 4 3.2 4 4............................................ 4 5............................................ 4 7............................................ 7 8................................................ 9 9.....................................10 9.1 10... 10... 12 9.2 12 9.3 13 9.4 13 9.5 13 9.6 13 9.7 13 10............................................. 13 11....................................... 16 1 OR R OR I II III 1.1 I II III I II I 1/17

2/17 II III 1.2 R III 1.3 R 2 descriptive statistics inferential statistics ( ) X 1,X 2,,X n : n estimation testing prediction significance interval A B 2/17

3/17 ( )/ 10 + 50 = n i=1 x i n = x, = n i=1 (x i x) 2 n n x i 5 Statistical Quality Control 7? 1959 1997 Mauna Loa is the largest volcano on Earth with an estimated volume of 9,600 cubic miles (40,000 cubic kilometers). It makes half of the area of the Island of Hawaii. Mauna Loa began to form nearly a million years ago. There is a caldera, Mokuaweoweo, at the summit and rift zones extend to the northeast and southwest. Mauna Loa is in the shieldbuilding stage and is one of the most active volcanoes on Earth, erupting 15 times since 1900. The last eruption was in 1984 and sent lavas within 4 miles (6.5 km) of Hilo. (http://volcano.oregonstate.edu/ ) FreeWare R plot(co2) R MacOS Windows Unix Linux OS Australia New Zealand http://cran.r-project.org/ 3 data sample 3/17

4/17 3.1 qualitative data nominal scale ordinal scale CD 3.2 quantitative data continuous data discrete data 1 interval scale ratio scale 4 1. simple random sampling 2. systematic sampling 3. stratified sampling 4. two stage sampling 1 2 5. 2 stratified tow stage sampling 2 5 1. parameter 4/17

5/17 2. 3. T.Bayes 1710-1761 6 1 2 x y r = s xy sxx s yy (x 1,y 1 ),(x 2,y 2 ),,(x n,y n ) 2 n s xy = n i=1 (x i x)(y i y) n 1 s yy = n i=1 (y i y) 2 n 1, s xx = n i=1 (x i x) 2, n 1 n, x = 1 i, y = n i=1x 1 n s xy,s xx,s yy,x,y x y r xy Pearson x y -1 +1 +1-1 0 20 50m R n y i i=1 50m running income age 7.7 342 23 8.2 923 43 8.5 985 50 7.8 581 35 8.0 627 33 7.8 388 25 7.7 290 20 8.2 860 44 8.5 787 48 8.1 654 37 8.4 788 39 7.7 334 22 7.9 412 29 8.3 915 46 8.2 648 43 7.9 761 33 7.8 589 30 8.4 946 47 7.8 477 28 7.7 412 25 5/17

6/17 50m 0.86 50m 0.93 0.94 3 R cor(d) d 50m 3 r xy r zx r zy (1 rzx)(1 2 rzy) 2 3-0.05382888 50m Mammal species 0 5 10 15 20 25 f f d d f d e c d d c c c e e d d d e e b b c e a a b b e c c e a a a a a b a b b b c f f f f f 0 5 10 15 20 25 30 Productivity 6 a f 0.7056966 6/17

7/17 0 5 10 15 20 25 30 d e f 25 20 15 10 Mammal species 25 20 a b c 5 0 15 10 5 0 0 5 10 15 20 25 30 0 5 10 15 20 25 30 Productivity 9 7 t X Y t X Y 1 100 10 2 200 20 3 100 10 4 200 20 5 100 10 6 200 20 7 100 10 8 200 20 9 100 10 10 200 20 Numbers 0 50 150 250 2 4 6 8 10 Index X 100 200 10 20 Y 7/17

8/17 t X Y 1 100 10 2 200 20 3 100 10 4 200 20 5 100 10 6 200 20 7 100 10 8 200 20 9 100 10 10 200 20 Numbers 1 2 3 4 5 6 2 4 6 8 10 Index X Y, 120 X Y X Y 0.241 0.387 0.615 0.723 1 1 1.88 1.52 11.9 5.20 29.5 9.55 84.0 19.2 165 30.1 248 39.5 0 50 150 250 Y 0 10 20 30 40 X X Y (x i,y i ) n i=1 { yi (β 0 + β 1 x i ) } 2 X Y 8/17

9/17 X Y -1.422958-0.94933-0.486133-0.32434 0.0000000 0.000000 0.6312718 0.418710 2.4765384 1.648658 3.3843903 2.256541 4.4308168 2.954910 5.1059455 3.404525 5.5134287 3.676300 1 1 2 3 4 5 logy 1 0 1 2 3 logx mercury 0.241 0.387 venus 0.615 0.723 earth 1 1 mars 1.88 1.52 jupiter 11.9 5.20 saturn 29.5 9.55 Uranus 84.0 19.2 Neptune 165 30.1 Pluto 248 39.5 1 = 1.50 1011m 2 3 1619 1 : 2 : 3 : 2 3 8 4 9/17

10/17 EXPLORATORY DATA ANALYSIS Histogram of x Density of x Boxplot of x Q Q Plot of x Sturges 7 Gaussian Shapiro-Wilk SQC Statistical Quality Control 7 9 7 QC7 (i) Graph, Control Chart (ii) Pareto Diagram (iii) Histogram (iv) Cause and Effect Diagram (v) Scatter Diagram (vi) Stratification (vii) CheckSheet 7 5 R qcc 9.1 9.1.1 (i) 10/17

11/17 (ii) (iii) 100% (iv) median 25% 1 first quartile 25% 3 third quartile 1 3 1 3 1.5 1 3 boxplot (v) qqnorm qqline 1 3 11/17

12/17 9.1.2 Shewhart control chart CL Center Line UCL Upper Control Limit LCL Lower Control Limit (i) x x (ii) R R (iii) x x (iv) p p (v) pn pn (vi) c (vii) u 3 9.2 Pareto Pareto chart 12/17

13/17 9.3 9.4 Fishbone Diagram Cause and Effect diagram Communication SKills ambiguity lack of knowledge Knowledge Literacy Incorrect Deliver Procedures Manual automated Transport carriers Information 9.5 2 9.6 9.7 10 R airquality 1973 5 9 153 Ozone Solar.R Wind Temp Month Day R help airqualtiy 13/17

14/17 6 0 100 250 60 80 0 10 20 30 Ozone 0 50 150 0 150 300 Solar.R Wind 5 15 60 80 Temp Month 5 6 7 8 9 0 10 25 Day 0 50 100 5 10 15 20 5 6 7 8 9 30 15 2 2 airq airq 0 50 150 250 60 70 80 90 Ozone 0.35 0.60 0.70 0 50 100 0 100 200 300 Solar.R 0.057 0.28 Wind 0.46 5 10 15 20 60 70 80 90 Temp 0 50 100 150 5 10 15 20 14/17

15/17 Temp < 82.5 Wind < 7.15 Wind < 10.6 Temp < 88.5 Solar.R < 205 Solar.R < 79.5 48.71 61.00 Temp < 77.5 74.54 83.43 102.40 12.22 20.97 34.56 Temp<82.5 28.1 Wind>=7.15 Call: lm(formula = Ozone Temp * Wind * Solar.R + I(Solar.Rˆ2) + I(Tempˆ2) + I(Windˆ2)) Residuals: Min 1Q Median 3Q Max -38.879-11.231-2.706 8.824 70.546 Coefficients: Estimate Std. Error t value Pr(> t ) (Intercept) 5.670e+02 2.077e+02 2.730 0.00748 ** Temp -1.073e+01 4.308e+00-2.491 0.01439 * Wind -3.232e+01 1.176e+01-2.749 0.00709 ** Solar.R -3.140e-01 5.593e-01-0.561 0.57581 I(Solar.Rˆ2) -3.610e-04 2.576e-04-1.401 0.16421 I(Tempˆ2) 5.815e-02 2.399e-02 2.424 0.01715 * I(Windˆ2) 6.095e-01 1.473e-01 4.138 7.32e-05 *** Temp:Wind 2.373e-01 1.370e-01 1.733 0.08624. Temp:Solar.R 8.433e-03 7.523e-03 1.121 0.26499 Wind:Solar.R 2.063e-02 4.899e-02 0.421 0.67450 Temp:Wind:Solar.R -4.340e-04 6.605e-04-0.657 0.51264 --- Signif. codes: 0 *** 0.001 ** 0.01 * 0.05. 0.1 1 Residual standard error: 17.84 on 100 degrees of freedom 15/17

16/17 (42 observations deleted due to missingness) Multiple R-squared: 0.7387, Adjusted R-squared: 0.7126 F-statistic: 28.27 on 10 and 100 DF, p-value: < 2.2e-16 3 Call: lm(formula = log(ozone) Temp + Wind + Solar.R + I(Windˆ2), subset = (1:length(Ozone)!= 17)) Residuals: Min 1Q Median 3Q Max -2.01817-0.27787-0.01111 0.31407 1.29569 Coefficients: Estimate Std. Error t value Pr(> t ) (Intercept) 0.6741274 0.6466060 1.043 0.299545 Temp 0.0474201 0.0060421 7.848 3.76e-12 *** Wind -0.2232387 0.0598210-3.732 0.000309 *** Solar.R 0.0024195 0.0005477 4.418 2.43e-05 *** I(Windˆ2) 0.0073580 0.0026307 2.797 0.006137 ** --- Signif. codes: 0 *** 0.001 ** 0.01 * 0.05. 0.1 1 Residual standard error: 0.4928 on 105 degrees of freedom (42 observations deleted due to missingness) Multiple R-squared: 0.6907, Adjusted R-squared: 0.679 F-statistic: 58.63 on 4 and 105 DF, p-value: < 2.2e-16 11 (i) Web Wikipedia : http://ja.wikipedia.org/wiki/ (ii) google goo yahoo http://www.google.co.jp/ http://www.goo.ne.jp/ http://www.yahoo.co.jp/ AND 1 AND 2 AND AND OR 2 ( OR ) AND 16/17

17/17 NOT black and white black and white site:www.shiga-u.ac.jp http://www.shiga-u.ac.jp filetype:ppt filetype PowerPoint Web IT http://e-words.jp/ ppt Word Excel PowerPoint Acrobat Reader doc xls ppt pdf (iii) Windows Ctrl +C Ctrl +V Ctrl +A Ctrl +Z Ctrl +S Ctrl +Shift+S Ctrl +F Ctrl + Ctrl C V A Z S F Windows WebBrowser InternetExplorer FoxFire Ctrl+L URL 17/17