Introductory Applied Statistics for the Life Sciences
Introductory Applied Statistics for the Life Sciences STAT 371
Popular in Course
Popular in Statistics
Mrs. Triston Collier
verified elite notetaker
This 16 page Class Notes was uploaded by Mrs. Triston Collier on Thursday September 17, 2015. The Class Notes belongs to STAT 371 at University of Wisconsin - Madison taught by Nicholas Keuler in Fall. Since its upload, it has received 25 views. For similar materials see /class/205073/stat-371-university-of-wisconsin-madison in Statistics at University of Wisconsin - Madison.
Reviews for Introductory Applied Statistics for the Life Sciences
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 09/17/15
Review on Chapters 11 and 12 What you need to know C cile An Stat 371 Material for the final exam From Chapter 6 to Chapter 13 inclusive Analysis of Variance 0 Build the Anova table get the pvalue from the F distribution Know what the null hypothesis is Formulate this hypothesis in the context of the study 0 Check the assumptions of the method the design normal probability plot for the small samples and compare the SD s across samples 0 Determine the pooled standard deviation Get a confidence interval for one population mean one treatment using the pooled SD 9 Carry out the NewmanKeuls method to compare all pairs of means when all groups have about equal size Regression 6 Get the coefficients intercept slope and know what they mean in the context ofthe study 0 Check the assumptions of the regression model the design the residual plot and normal probability plot of the residuals Know how to connect a residual plot to the original data plot 0 Build the anova table and do the F test Know what the null hypothesis is for this test Formulate this hypothesis in the context of the study 0 Get the SE of b1 do a ttest to test for 31 Oquot or p 0quot Get a confidence interval for 31 9 Confidence interval for 30 0 Get the correlation coefficient Know what it means when it is close to O 1 or 1 and what its sign means Real data problems You now have a whole array of methods of analysis The design and type of data will help you decide what is the right analysis to do o In particular be careful to use the independent ttest with 2 independent samples and the paired ttest with 2 paired samples 0 with 3 or more samples or categories it will probably be a chisquare test or an ananlysis of variance depending on the type of data Real data problems Make sure you check the validity of the analysis after each analysis Usually you need to look at a normal probability plot if available do a stem and leaf display for yourself otherwise In the case of Anova you also need to compare the SD s across samples to make sure they do not differ too much a 2fold difference is okay In the case of a regression analysis you need to check the residual SD does not change too much from a residual plot Here again a twofold difference is okay For a chisquare test you need to make sure all expected counts were 2 5 If they were not try to combine columns Analyzing the survey data gt strsurvey dataframe 154 obs of 8 variables Sex Factor w 2 levels quotFemalequot Level Ordfactor w 5 levels quotFreshquot Brothers int 0 2 O l O O 0 Sisters int 0 l l l l l 0 MilesHome num 60 75 8 l3 14 53 MilesClass num l 2 l 2 05 l 025 BloodType Factor w 4 levels quotAquotquotABquotquotBquot Height num 62 6O 76 72 63 74 Number int 4 3 7 7 8 7 5 8 7 Analyzing the survey data Questions of interest 0 l hypothesize that students coming from far away will tend to live in dorms so closer to campus than other students 0 l hypothesize that more Freshmen tend to live in dorms than Seniors 0 Can we really pick a number at random What numbers look random and what numbers do not look random 0 lv drug remams unproven thhout p acebo ma Reed canary grass an invader Can we understand what conditions are favorable to its invasion and what conditions help reduce the invasion Experiment Joy Zedler lab Botany 135 outdoor mesocosms 11 m2 Prairie assemblage 25 herbaceous native plant species planted in July 2000 In 2002 Reed canary grass seedlings were added Invasion phase started 0 Flood regime intermittent 2 days every other wk early season 4 wk or constant 14 wks 6 Nutrien level nitrogenphospate 0 low or high o Sediment type added once each year 0 sand ortopsoil 3 x 3 x 3 27 combinations of treatments Reed canary grass an invader Mesocosms arranged in lines One block set of 2 lines Randomized Complete Block design each treatment was applied once in each block Observations 0 Species richness of different species still present in the mesocosm May July and September 2002 0 Reed canary grass biomass above ground dried biomass gO27 m2 October 2002 Reed canary grass data Flooding Intermittent Earlyseason Constant Sediment 0 Sand Topsoil O Topsoil Nutrient O 1 2 O 1 2 O 1 2 O 1 2 2 species mean sd n 5 5 5 5 5 5 Biomass mean sd n 5 5 5 5 5 5 Reed canary grass data Species Richness El No sediment Sand I Tnpsoil Intermittent Early Season Constant Flood Regime Reed canary grass Anova analysis a 15 16 Pdan 16 a Plt J10I7I a E 14 14 14 E n g 12 7 12 b 11 b 3 10 m 10 V1 539 s s s c a h 6 6 6 Nam Law High Nnne Sam Topsoil nun Em Comm 4 k l 40 PltO o l 4n KUJIDOI Phalrm39s Biomass g Nun Sand Tnpsoil Inter Early Constant Reed canary grass Anova analysis m m Sourcc Df May July m Rosidcms Liner B160 4 lt00001 04304 0 0374 00004 01066 00298 Nutr 2 01894 n lt00001 06494 Sod 2 lt010001 I n 00000 00005 Flood 2 lt00001 n lt00001 lt00001 nun x sad 4 06364 04179 0 4511 01721 01851 mm x ood 4 01008 05112 lt00001 06468 sod x 110611 4 00541 00001 00083 11u1 gtlt sod x 11qu x 04510 056 04592 I39 01284 02050 Reed canary grass Conclusions 0 Reed canary grass is a more aggressive invader in flooded areas 0 Species richness decreases more with application of sediments 0 Reed canary grass is more productive with added nutrients
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'