01| Lab
1| File organization
2| Cottonwood
cottonwood <- read.csv("Data/cottonwood.csv")
3| Tree_height
Tree_height <- 15
Tree_circ <- pi*Tree_height
Tree_circ## [1] 47.12389
01| Lecture
1| What are the steps to Strong Inference?
Creating lots of hypotheses to explain the phenomenon observed \(\rightarrow\) Coming up with experiments to disprove those hypotheses \(\rightarrow\) Conducting said experiments \(\rightarrow\) Starting over and refining
Platt writes that Strong Inference should be the name of Inductive Inference which is also the Bayesian approach
2| Where would statistics come into this design?
I think that the entire process is a bit statistical? But to be exact, data analysis would occur after the experiment has occurred, the data have been collected, and a statistical test has been run to either refine or reject the proposed hypotheses.
3| Can Platt’s method work as well as he thinks in all fields of biology? Field ecology, behavior?
Definitely! Platt even argues that, “Many - perhaps most - of the great issues of science are qualitative, not quantitative, even in physics and chemistry.” (p. 352) and Gotelli and Ellison mention that, “many important theoretical insights have come from theoretical modeling, abstract reasoning, and plain old intuition. Important hypotheses in all sciences have often emerged well in advance of the critical data that are needed to test them.”. Platt is championing that this method works for all sciences.
4| In your branch of biology, is Platt’s method the one used?
I am used to creating a scientific question and from that testing a null and alternative hypothesis. It is my understanding that professors will do the iterative process mentioned above through many years of conducting research by assigning one part of the big question to one graduate student, and another part to another graduate student. So under that method, yes. It is used in my branch of biology.
5| What is the difference between method-oriented research and problem-oriented research?
“The method oriented man is shackled and the problem oriented man is at least reaching freely to what is important.” (p. 351) meaning that a method oriented man can be so caught in the methods he knows that he will not venture out into new methods.
6| Based on his paper, what would Platt say about teaching intelligent design in a science course?
Platt does not agree with intelligent design because it is not testable.
7| What are the dangers of unenlightened (i.e. not knowing your system) use of the methods advocated by Platt?
He talks about Pasteur on page 351, saying that there were experts in Europe that knew SO MUCH MORE than Pasteur did on EVERY topic Pasteur advanced, and because he was so good at strong inference, he answered those questions before the experts ever could. So, Platt thinks if you can inductively induce, you don’t need to know much about your field in order to advance it. Which I LOVE.
8| Why is there no such thing as proof in science?
Because science only advances by disproofs according to Karl Popper.
9| What does this statement mean: “It predicts everything, and therefore does not predict anything.”?
If someone takes a theory and places every experimental result to fit within it, then that theory is predicting everything and therefore nothing. I think that what Platt is showing, is that if we just accept everything we hear or expect as fact, then we will stop using our data to update our theories and instead use our theories to update our data. As the example of the C-Cl bond on page 350 of Platt, 1964.
10| Practice the scientific method
Practice 1: Mosquitoes
a| observation: wow, over the last 15 lakes that I visited, I noticed that there was a major increase in mosquitoes as I got nearer to the water. Mosquitoes seem to enjoy water.
b| question: why are there more mosquitoes near the water?
c| alternative hypotheses: 1. Mosquitoes drink the water 2. Mosquitoes swim in the water 3. Mosquitoes forage from the water d| predictions: 1. no 2. yes, at a certain point in their life cycle 3. no
Practice 2: DDIRT
a| observation: The soil beneath this sagebrush is darker and more rich than the soil not surrounded by vegetation.
b| question: Does increased litter from leaves and root material increase soil fertility?
c| alternative hypotheses: 1. The soil is darker because of iron content 2. The soil is darker because it is moist 3. The soil is darker because it is poorly drained
Notes
Platt, 1964
STRONG INFERENCE, AKA INDUCTIVE INFERENCE, AKA BAYESIAN INFERENCE
Inductive inference is not as simple as certain deduction because it requires “reaching into the unknown”.
Inductive reasoning \(\rightarrow\) Strong inference \(\rightarrow\) Logical tree
Crick & Brenner: blackboards covered in logical trees
Hot new result \(\rightarrow\) 2-3 alternative explanations \(\rightarrow\) series of suggested experiments to reduce the number of explanations
The Problem-Oriented Man
Conditional Inductive Tree
Alternative Hypotheses (“possible causes”) \(\rightarrow\) Crucial Experiments (“Instances of the Fingerpost”) \(\rightarrow\) Establishing Axioms: exclusion of alternatives and adoption of what is left. - Francis Bacon, the king of inductive science
“Science advances only by disproofs” - Karl Popper
“To avoid the grave danger [of too much affection for your single hypothesis/intellectual child], the method of multiple working hypotheses is urged. It differs from the simple working hypothesis in that it distributes the effort and divides the affections. Each hypothesis suggests its own criteria, its own means of proof, its own method of developing the truth, and if a group of hypotheses encompass the subject on all sides, the total outcome of means and of methods is full and rich” - T. C. Chamberlin
“To the extent that this kind of story is accurate, a theory of this sort is not a theory at all, because it does not exclude anything. It predicts everything, and therefore does not predict anything. It becomes simply a verbal formula which the graduate student repeats and believes because the professor has said it so often. This is not science, but faith; not theory but theology. Whether it is hand waving of number waving or equation waving, a theory is not a theory unless it can be disproved. That is, unless it can be falsified by some possible experimental outcome.” - J. R. Platt
“We realize that it was out of this kind of atmosphere that Pasteur came to the field of biology. Can anyone doubt that he brought with hi111 a completely different method of reasoning? Every 2 or 3 years he moved to one biological problem after another, from optical activity to the fermentation of beet sugar, to the”diseases” of wine and beer, to the disease of silkworms, to the problem of “spontaneous generation,” to the anthrax disease of sheep, to rabies. In each of these fields there were experts in Europe who knew a hundred times as much as Pasteur, yet each time he solved problems in a few months that they had not been able to solve. Obviously it was not encyclopedic knowledge that produced his success, and obviously it was not simply luck, when it waq repeated over and over again; it can only have been the systematic power of a special method of exploration. Are bacteria falling in’? Make the necks of the flasks S-shaped. Are bacteria sucked in by the partial vacuum? Put in a cotton plug. Week after week his crucial experiments build up the logical tree of exclusions. The drama of strong inference in molecular biology today is only a repetition of Pasteur’s story.” - J. R. Platt
“To paraphrase an old saying, Beware of the man of one methcd or one instrument, either experimental or theoretical. He tends to become ~nethod-oriented rather than problem-oriented. The method-oriented man is shackled; the problem-oriented man is at least reaching freely toward what is most important. Strong inference redirects a man to problem-orientation, but it requires him to be willing repeatedly to put aside his last methods and teach himself new ones.” - J. R. Platt
“But sir, what experiment could disprove your theory?” - J. R. Platt
Gotelli & Ellison Notes
p. 79-90
Deduction
Proceeds from the general case to the specific case. It is certain inference. Suggests multiple hypotheses and then denies the ones that aren’t confirmed by the data later collected.
Induction
Proceeds from the specific case to the general case. It is probable inference. Takes an observation and develops a single hypothesis to explain it. Uses data to suggest the hypothesis.
Advantage
Emphasizes the close link between data and theory
Explicitly builds and modifies hypotheses based on new data
Disadvantage
Considers only a single starting hypothesis
It could take a long time to arrive at the correct hypothesis
Induction can be personal, people don’t appreciate dropping it if they have spent lots of time on it.
Null Hypotheses
Simple null: no association between two variables; line. Hypothetico-DEDUCTIVE approach. Black dotted line in figure. Aristotle
Bayesian null: Informed null. Brings prior knowledge to inform the null. For example, in the leaf and sun example, light intensity’s relationship with photosynthetic response is non-linear with assymptote at high light intensity. The Michaelis-Menten equation is the null here. INDUCTIVE. Blue line in figure. Bacon
Whether you use deductive or inductive approach is dependent on the question you are trying to answer.
8.24.26
Scientific Process
Observation \(\rightarrow\) Question \(\rightarrow\) Hypotheses \(\rightarrow\) Experimental Design \(\rightarrow\) Analysis \(\rightarrow\) Back to observation (depending on if your hypotheses were supported or not)
Arbitrary Probabilities
P values are refering to the likelihood of obtaining that same data again. Replication.
Review
Induce
Deduce
Infer
Lecture HW
Read Platt 1964
Lab Notes
min_height <- 4
max.height <- 15
age <- 20
mass <- 100
MaxLength <- 50
min_length <- 2
widths <- 15
celsius2kelvin <- 10
Species <- "cat"
cat <- "cat"
TempF <- 50
TempC <- (TempF - 32) * 5/9
cottonwood <- read.csv("Data/cottonwood.csv")Vectors
colors <- c("green", "purple", "blue", "orange")
feelings <- c("good", "weird", "calm", "nervous")
df1 <- c(colors, feelings)
df <- data.frame(c(colors, feelings))