2 different datasets (mystery data 4 and 7)

Author: markdunning

mystery-data.zip

@@ -1,11 +1,9 @@
-Group1,Group2
-0.7,1.9
--1.6,0.8
--0.2,1.1
--1.2,0.1
--0.1,-0.1
-3.4,4.4
-3.7,5.5
-0.8,1.6
-0,4.6
-2,3.4
+Before,After
+85,75
+70,50
+40,50
+65,40
+80,20
+75,65
+55,40
+20,25

mystery-data/data4.csv

@@ -1,101 +1,101 @@
 Before,After
-3.86742471266244,5.34799509821092
-5.44302072581142,5.77083934238885
-4.12977055055094,6.61885785412577
-4.06814827579831,4.46992888351995
-4.92875436478702,5.38977954456214
-4.79670083448242,6.07263960878491
-5.87229736132638,6.91549077926941
-5.4937227998083,5.79285908049972
-5.10932787141978,6.28349699623494
-6.2971607968844,4.99422074069174
-5.14654249435327,4.59631393462502
-5.2344234049385,5.10671744008003
-5.19430439604953,5.65318319218658
-5.78029423051111,6.18117747718444
-6.52144852377806,6.79406477313316
-4.06007991427792,4.11525679841329
-5.09435796626848,5.00411321384976
-6.92341292193378,5.77679163982642
-4.10570033483655,5.01285247307354
-7.66574504365385,6.17564541448577
-5.35701627037348,7.36365973213449
-3.48538110719407,4.87369219415644
-5.3787872045258,5.59867364600418
-5.09958921081938,5.03073971958723
-4.55004770644439,6.35396020800683
-3.43488066584604,4.70750516265895
-4.51884153513657,6.1711917079173
-4.91754378065697,6.67682012499472
-5.10195198023253,4.86430777409148
-4.16829187781692,6.14408219272787
-4.4529196513749,4.43694175963381
-3.11437162198838,5.29139274287177
-6.21893020204033,5.56745111020949
-3.46296439841883,4.33535230630586
-6.55716667636759,6.95588096556676
-4.79442297398042,5.70617618776457
-5.85153302305026,6.19075238380252
-4.56985564179787,5.66916570308593
-4.21700106105276,5.96285492445076
-5.38359385422245,6.22032399536323
-5.78740678301614,6.06719878119245
-4.30865355311008,6.06472277471777
-3.81319891113306,8.59413831534837
-5.95598039700588,6.36637729855923
-4.89346224745456,5.26049327188695
-6.76170722577193,4.65183831191129
-5.54678681746598,5.92034123651943
-4.48710981464151,5.43969262944199
-5.41084510183402,6.1904491137286
-3.80267135908683,5.4631941723757
-3.8574974691253,6.4093810054597
-3.05551581623659,4.74285185008093
-4.39851056811042,5.93135485709729
-4.7888479019937,5.47661251534808
-5.22346488385762,3.05224458517395
-6.0225233909491,6.32507192601445
-5.4567625348103,5.10207037280747
-4.42525655354525,4.44444420815608
-4.14851900975177,5.71301675169265
-5.26497576684805,7.34727589177775
-6.98256881952284,5.79518116950373
-6.79142552786418,4.92165995540776
-4.30424890153367,5.92651067221646
-4.45207440549117,5.05342013952313
-5.86924751750422,3.2950465165048
-3.5481065702105,6.02448813246303
-5.37075784995012,6.11356347844423
-2.26094292510698,5.58834584575776
-5.76544986346151,5.31443832646173
-5.11780945051587,4.33778361770661
-7.42946098449296,6.34418368074845
-4.21214662418593,5.1944262218357
-3.1431956178091,6.33575757671344
-3.87282601175461,6.24664989707643
-5.89362947195591,5.45299940234452
-4.04440873807453,6.27538778075636
-4.66128150601909,5.06421511502248
-4.70962606102851,4.20971978902807
-4.25752616881211,4.24629538885353
-4.65207526252791,5.40492570263223
-3.97847823665323,5.67616434244428
-3.03081913902277,5.32593071888426
-5.13640514974908,6.21509248160154
-4.72449339207167,4.92995593876198
-5.11303391470569,5.13284664102819
-5.1430326711442,5.51807404228089
-5.16208317014053,7.30377567580694
-4.30207014116144,5.06375059947036
-5.79888639624305,6.88173873946018
-3.95525166767843,5.8958631596413
-5.33088719373288,5.79203516042205
-5.80211370048751,5.1392873909505
-5.36210745277515,4.76092981766756
-3.44266410754941,5.89496336371729
-5.00323812023262,5.37159272331979
-5.17028063699446,6.64767976857032
-5.50963670033692,4.84994583059593
-5.94246568674972,6.31973694223943
-3.92355954362466,5.94901785956371
-4.31167351228822,6.08795654522241
+4.26966258937941,5.92516286094901
+3.77252900710419,4.82457978356335
+7.01129265960208,5.37990015789653
+3.7376150930703,4.63176070072204
+4.81770615280243,7.12129611704166
+5.64414253552135,5.19626081148799
+5.29826400684533,4.40787133850167
+5.84323685564281,5.21579679321744
+3.63022059291777,5.65744738049738
+5.9404834825618,5.97956748351097
+3.38656860392474,4.45010938204416
+7.11120629749673,5.67264575642377
+4.81831394076906,7.10145860949749
+4.59661718556736,4.9678374166008
+5.01283216138533,5.14848909792138
+3.65580330996474,4.46849617080025
+7.19958322395298,5.36175787547516
+6.50684605426548,5.65549116213647
+5.94232633634117,3.23545092194219
+6.75495120001045,5.01313277570429
+5.47162470791784,3.96191667228983
+3.3396955642073,5.56434216199771
+4.8165674033112,4.26624750213829
+3.7886654269429,5.78053888784902
+4.12750505199339,4.82485375350003
+5.18437133297427,5.36482443781866
+4.42228019822818,4.20305032136328
+3.5043635621442,4.69970344111892
+3.96809562688034,5.84293532470908
+5.9725889266402,5.70621121521026
+4.71146501654787,5.5492178213097
+5.53634626872862,5.90425944872174
+3.58783607786553,4.1941481494595
+3.45998874162922,4.27055087534582
+5.49640306749457,5.77549649677766
+5.61127973318879,6.39189658587217
+5.01204797175893,4.76611957321555
+5.36369007893939,4.63953178715955
+5.29333598951372,4.98304232842366
+6.26050142708007,6.56326577561772
+7.00401178902151,4.48963740061468
+4.3854449316488,4.18717024333839
+5.8917918601956,6.13381612419914
+4.09898432189678,7.44969842382997
+3.9739759706041,4.85082251693038
+3.77832177435661,4.96425900693006
+5.61480863425842,5.78516300221936
+5.21354979392656,6.4528919024955
+5.87195797987612,4.20164068718401
+4.33109539059665,6.16978651541144
+5.92216582103262,4.33764151638569
+5.34898543819138,7.30279006077873
+4.52663136157609,5.07220013727927
+5.23022047771636,5.42499709843795
+4.88786041424353,4.59102815876287
+4.96543249949444,4.79614921418964
+6.12723932776391,5.89710752710511
+5.44234517309018,6.86568672477544
+5.96801697255707,6.34447196263256
+6.04000497436364,6.3221428964113
+4.596422728516,5.27363457431021
+3.66234000670527,5.73951481331435
+3.89758835343045,6.01908480874724
+2.8857803307234,4.83299511575399
+4.39140749308814,4.85869097565217
+5.31579322033981,3.53612798344628
+6.10482124433367,5.22908505488085
+3.92999140583584,4.81131621688507
+6.93380672404583,5.56257421916021
+4.08560800099396,4.04073932465996
+5.37851322285364,6.12005644184124
+5.67835668690078,4.80426814019064
+5.56840043240553,6.33966003107779
+4.30738250309661,4.55586047865873
+5.66765809521458,6.10579363795745
+3.46418753586412,4.91481573064849
+3.69897424119634,5.87215147448101
+5.33040411728839,5.98904917588096
+5.82214377861419,6.40203834925397
+5.02966947595126,7.98642258766233
+5.11202352171473,4.52942185505885
+6.47948655816117,5.51046876065764
+4.22815217571145,4.11282385909362
+4.77078099030668,6.40170722448669
+4.79927458956966,4.62083353790189
+6.38142323877427,5.77049008959382
+6.20644642425947,6.71623724051249
+5.34607669671352,5.27919652859588
+5.44776714372478,6.17332828548977
+4.64308794758906,5.80842604455848
+5.47520943585245,6.26692676068933
+5.9985390833877,6.331903154441
+4.7773436271923,5.26542834739014
+4.785186951215,6.37104084492817
+4.14957848224147,4.77031284010497
+5.33546276661176,4.55804929534339
+5.83335353225774,5.31491763143331
+7.14815156164517,5.6288914113136
+5.69380538251409,5.15375902816261
+5.73125907903491,4.85245301575252

mystery-data/data6.csv

@@ -1,41 +1,14 @@
-type,weightgain
-High,73
-High,102
-High,118
-High,104
-High,81
-High,107
-High,100
-High,87
-High,117
-High,111
-High,98
-High,74
-High,56
-High,111
-High,95
-High,88
-High,82
-High,77
-High,86
-High,92
-Low,90
-Low,76
-Low,90
-Low,64
-Low,86
-Low,51
-Low,72
-Low,90
-Low,95
-Low,78
-Low,107
-Low,95
-Low,97
-Low,80
-Low,98
-Low,74
-Low,74
-Low,67
-Low,89
-Low,58
+August,November
+8.1,11.2
+10,16.3
+16.5,15.3
+13.6,15.6
+9.5,10.5
+8.3,15.5
+18.3,12.7
+13.3,11.1
+7.9,19.9
+8.1,20.4
+8.9,14.2
+12.6,12.7
+13.4,36.8

mystery-data/data7.csv

@@ -15,17 +15,17 @@ opts_chunk$set(tidy=FALSE,dev="png",fig.show="as.is",
 ```
 
 # Introduction
-In this practical, we will use several 'read-life' datasets to demonstrate some of the concepts you have seen in the lectures. We will guide you through how to analyse these datasets in Shiny and the kinds of questions you should be asking yourself when faced with similar data.
+In this practical, we will use several 'real-life' datasets to demonstrate some of the concepts you have seen in the lectures. We will guide you through how to analyse these datasets in Shiny and the kinds of questions you should be asking yourself when faced with similar data.
 
 To answer the questions in this practical we will be using apps that we have developed using the [***Shiny***](http://shiny.rstudio.com/gallery/) add-on for the *R* statistical package. **R** is a freely-available open-source software that is popular within academic and commercial communities. The functionality within the software compares favourably with other statistical packages (SAS, SPSS and Stata). The downside is that **R** has a steep learning-curve and requires a basic familiarity with command-line software. To ease the transition we have chosen to present this course using a series of online tools that will allow you to perform statistical analysis without having to worry about learning R. At the same time, the R code required for the analysis will be recorded in the background. You will therefore be able to repeat the analysis at a later date, or pass-on to others. As you gain familiarity with R through other courses, you will see how the code generated by Shiny can be adapted to your own needs.
 
-The datasets you will need for this practical should be [***downloaded and unzipped now***](https://rawgit.com/bioinformatics-core-shared-training/IntroductionToStats/master/CourseData.zip)
+The datasets you will need for this practical should be ***downloaded and unzipped now***:- https://rawgit.com/bioinformatics-core-shared-training/IntroductionToStats/master/CourseData.zip
 
 
 # T-tests practical: Parametric Tests
 
 ## The effect of disease on height
-A scientist knows that the mean height of females in England is 165cm and wants to know whether her patients with disease X have heights that differ significantly from the population mean - we will use a one-sample t-test to test this. The data are contained in the file **`diseaseX.csv`** and can be analysed online at:-
+A scientist knows that the mean height of females in England is ***165cm*** and wants to know whether her patients with disease X have heights that differ significantly from the population mean - we will use a one-sample t-test to test this. The data are contained in the file **`diseaseX.csv`** and can be analysed online at:-
 
 [http://bioinformatics.cruk.cam.ac.uk/stats/OneSampleTest/](http://bioinformatics.cruk.cam.ac.uk/stats/OneSampleTest/)
 
@@ -41,7 +41,7 @@ cat("Alternative hypothesis: The mean height of female patients with disease X !
 
 To import the file `diseaseX.csv` into ***Shiny*** you will need to select the `Choose File` option from the `Data Input` tab and navigate to where the course data are located on your laptop. The right-hand panel of the `Data Input` tab should update to show the Heights of various individuals in the study.
 
-Also, on the `Data Input` tab you will need to change the value of ***True mean***.
+Also, on the `Data Input` tab you will need to change the value of ***Hypothesized mean***.
 
 ```{r}
 myfile <- "Practical/diseaseX.csv"
@@ -56,7 +56,7 @@ data <- read.csv(myfile, header=header, sep=sep, quote=quote,skip=skip)
 
 b) A histogram and boxplot of the `Height` variable will be automatically generated for you. To view it, click on the ***Data Distribution***. You can toggle whether to overlay a density plot on top of the boxplot, or choose different bin sizes for the histogram.
 
-Do the data look normally distributed? Based on the plots, is the one-sample t –test appropriate?
+Do the data look normally distributed? Based on the plots, is the parametric one-sample t –test appropriate?
 
 ```{r}
 datacol <-  2 
@@ -117,8 +117,9 @@ biological process for the two cell types.")
 
 Import the data using ***Choose File*** as before. Make sure that the ***1st column is a factor?*** checkbox is ticked.
 
-b) Histograms and boxplots to compare the two groups will be created for you automatically. Do the data look normally distributed for each cell-type? Is the independent t-test appropriate?
+b) Histograms and boxplots to compare the two groups will be created for you automatically. You can also see a basic numerical summary of the data distribution.
 
+Do the data look normally distributed for each cell-type? Is the independent t-test appropriate? What statistics are appropriate to report the location (mean or median) and spread (sd or IQR) of the data?
 
 ```{r}
 myfile <- "Practical/bp_times.csv"
@@ -566,19 +567,19 @@ t.test(value~variable,data=data,alternative=alternative,paired=paired,var.equal=
 ```
 
 
-## Dataset4: Sleep Data `data4.csv`
+## Dataset4: Effect of Autism drug  `data4.csv`
 
-Data which show the effect of two soporific drugs (increase in hours of sleep compared to control) on 10 patients.
+A new chemotherapy treatment is proposed for patients with breast cancer.   Investigators are concerned with patient's ability to tolerate the treatment and assess their quality of life both before and after receiving the new chemotherapy treatment.   Quality of life (QOL) is measured on an ordinal scale and for analysis purposes, numbers are assigned to each response category as follows: 1=Poor, 2= Fair, 3=Good, 4= Very Good, 5 = Excellent.  
 
-*Does the drug have an effect on the amount of sleep?*
+*Is there statistically significant improvement in repetitive behavior after 1 week of treatment?*
 
 ```{r echo=FALSE,eval=FALSE}
-data(sleep)
-sleep <- spread(sleep, group,extra)[,-1]
-colnames(sleep) <- c("Group1","Group2")
-write.csv(sleep, file="mystery-data/data4.csv",quote=FALSE,row.names=FALSE)
+###http://sphweb.bumc.bu.edu/otlt/MPH-Modules/BS/BS704_Nonparametric/BS704_Nonparametric5.html
+data <- data.frame(Before=c(85,70,40,65,80,75,55,20),After = c(75,50,50,40,20,65,40,25))
+
+write.csv(data, file="mystery-data/data4.csv",quote=FALSE,row.names=FALSE)
+
 
-t.test(sleep[,1],sleep[,2],paired=TRUE)
 ```
 
 ```{r}
@@ -656,7 +657,7 @@ t.test(value~variable,data=data,alternative=alternative,paired=paired,var.equal=
 
 Drunk driving is one of the main causes of car accidents. Interviews with drunk drivers who were involved in accidents and survived revealed that one of the main problems is that drivers do not realize that they are impaired, thinking “I only had 1-2 drinks … I am OK to drive.”
 
-A sample of 100 drivers was chosen, and their reaction times in an obstacle course were measured before and after drinking two beers. The purpose of this study was to check whether drivers are impaired after drinking two beers
+A sample of 100 drivers was chosen, and their reaction times in an obstacle course were measured *before* and *after* drinking two beers. The purpose of this study was to check whether drivers are impaired after drinking two beers
 
 *Does drinking beer alter the reaction time of the driver?*
 
@@ -698,16 +699,20 @@ t.test(value~variable,data=data,alternative=alternative,paired=paired,var.equal=
 
 ```
 
-## Dataset7: Weight gain in Rats `data7.csv`
+## Dataset7: Pollution in Trees `data7.csv`
 
-The data arise from an experiment to study the gain in weight of rats fed on four different diets, distinguished by amount of protein (low and high) and by source of protein (beef and cereal).
+Laureysens et al. (2004) measured metal content in the wood of 13 poplar clones growing in a polluted area, once in August and once in November. Concentrations of aluminum (in micrograms of Al per gram of wood) are shown below.
 
-*Does the high protein diet increase the weight of the rats?*
+*Is there any evidence for an increase in pollution between November and August?*
 
 ```{r eval=FALSE,echo=FALSE}
-data <- read.csv("http://vincentarelbundock.github.io/Rdatasets/csv/HSAUR/weightgain.csv")[,c(3,4)] %>% arrange(type)
+## http://www.biostathandbook.com/wilcoxonsignedrank.html
+##"The differences are somewhat skewed; the Wolterson clone, in particular, has a much larger difference than any other clone. To be safe, the authors analyzed the data using a Wilcoxon signed-rank test"
+
+data <- data.frame(August = c(8.1,10,16.5,13.6,9.5,8.3,18.3,13.3,7.9,8.1,8.9,12.6,13.4), November = c(11.2,16.3,15.3,15.6,10.5,15.5,12.7,11.1,19.9,20.4,14.2,12.7,36.8))
+
 write.csv(data, file="mystery-data/data7.csv",quote=FALSE,row.names=FALSE)
-boxplot(weightgain ~ type,data)
+boxplot(data)
 ```
 
 ```{r}