CO2 Uptake Experiment
This example is taken from an experiment listed in the R help files under ?CO2.
“An experiment on the cold tolerance of the grass species Echinochloa crus-galli was conducted. The CO2 uptake of six plants from Quebec and six plants from Mississippi was measured at several levels of ambient CO2 concentration. Half the plants of each type were chilled overnight before the experiment was conducted.” Plants were considered tolerant to the cold if they were still able to achieve high CO2 uptake values after being chilled.
Ignoring the Plant ID for a moment, there are three factors that possibly effect the uptake of a plant. These include Type, Treatment, and conc. The factor Type has two levels, Quebec and Mississippi. The factor Treatment has two levels chilled and nonchilled and the factor conc has seven levels 95, 175, 250, 350, 500, 675, and 1000.
Conc is related to the ambient concentration of CO2.
Our main interest in CO2 uptake and how the other factors impact it. We will first do a univariate analysis of uptake.
Create a table with the overall summary statistics for uptake:
# This is NEW! if you tell R to knit the favstats output using the "kable" function, it will look a lot nicer when the document is rendered.
knitr::kable(favstats(CO2$uptake))| min | Q1 | median | Q3 | max | mean | sd | n | missing | |
|---|---|---|---|---|---|---|---|---|---|
| 7.7 | 17.9 | 28.3 | 37.125 | 45.5 | 27.2131 | 10.81441 | 84 | 0 |
Create a histogram of the uptake data:
histogram(CO2$uptake, col= c("yellow","lightblue","green","pink", "navy","darkgreen","maroon"))
We will now look at how other factors might impact CO2 uptake.
Create a table of summary statistics of uptake for each type of plants used in the experiment.
favstats(CO2$uptake ~ CO2$Type) CO2$Type min Q1 median Q3 max mean sd n missing
1 Quebec 9.3 30.325 37.15 40.15 45.5 33.54286 9.673830 42 0
2 Mississippi 7.7 13.875 19.30 28.05 35.5 20.88333 7.815773 42 0Create a side-by-side boxplot of uptake for each type of plants used in the experiment.
boxplot(CO2$uptake ~ CO2$Type, col= c("lightblue", "maroon"))
Create a table of summary statistics of uptake for each treatment used in the experiment.
favstats(CO2$uptake ~ CO2$Treatment) CO2$Treatment min Q1 median Q3 max mean sd n missing
1 nonchilled 10.6 26.475 31.3 38.7 45.5 30.64286 9.704994 42 0
2 chilled 7.7 14.525 19.7 34.9 42.4 23.78333 10.884312 42 0Create a side-by-side boxplot of uptake for each treatment used in the experiment.
boxplot(CO2$uptake ~ CO2$Treatment, col= c(2,5))
Create a table of summary statistics of uptake for each level of CO2 found in the experiment.
favstats(CO2$uptake ~ CO2$conc) CO2$conc min Q1 median Q3 max mean sd n missing
1 95 7.7 10.575 11.65 14.425 16.2 12.25833 2.735111 12 0
2 175 11.4 18.900 21.50 27.300 32.4 22.28333 6.271992 12 0
3 250 12.3 23.875 30.45 35.525 40.3 28.87500 8.988895 12 0
4 350 13.0 25.650 32.90 37.600 42.1 30.66667 9.596527 12 0
5 500 12.5 26.250 32.45 38.675 42.9 30.87500 9.671056 12 0
6 675 13.7 26.625 33.90 39.300 43.9 31.95000 9.534960 12 0
7 1000 14.4 26.325 37.10 41.650 45.5 33.58333 10.411867 12 0Create a side-by-side boxplot of uptake for each level of CO2 found used in the experiment.
boxplot(CO2$uptake ~ CO2$conc,col= c("lightyellow", "lightblue", "lightpink", "lightgreen", "purple", "orange", "yellow"))
The background suggests this study was an experiment. In your own words, describe the difference between an experiment and an observational study.
An experiment has a treatment and a control group to show if the treatment works or not with the researchers controlling the experiment. An observational study doesn’t have groups, they just watch as the variable they are studying occurs without intervention.
What would this study have looked like if it had been an observational study?
If this study was an observational study, there would have been less of a spread as they did not manipulate the treatments and enviornments as much.
Describe in your own words what the population of this study could be. How broad can we make our conclusions?
The population of this study is the plants in Mississippi and Quebec but it can be assumed that the data will apply more broudly to the same regions/climates of each area.
If you were to recommend a planting scenario to maximize CO2 uptake, what would you recommend based on the summaries provided?
I would recommend planting in Quebec in a non chilled and high CO2 concentration for a higher uptake.