Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
78 Cards in this Set
- Front
- Back
Scientists construct arguments which are characterized by reasoning from:
A) Conclusions to Data B) Data To Theories C) Premises to Conclusions D) Reality to Facts |
C) Premises to Conclusions
|
|
The goal of science is to _____,_____,_____ natural phenomena.
|
-Describe
-Classify -Explain |
|
Scale Models are a type of Analogue Model
A) True B) False |
B) False
|
|
A model that accurately represents its target system is said to exhibit:
A) A good map B) An Incomplete Map C) Good Fit D) All of the Above |
C) A Good Fit
|
|
What is a theoretical hypothesis?
|
A statement made about the relationship between a model and some aspect of the real world or target system
|
|
Truth is a property of sentences, statements, or claims, and is distinguished from ______, which are features of the way the world happens to be.
|
Fact
|
|
Data is Obtained Through:
A) Hypothesizing B) Models C) Predictions D) None of the Above |
D) None of the Above
Physical Interaction -Active -Passive |
|
Data is supposed to provide ________ that some hypothesis is true.
|
Evidence
|
|
What are the two possibilities if a model does not fit the real world?
|
1) The Data is Mistaken
2) The Prediction is Mistaken |
|
Models that exhibit good fit are sometimes complete.
A) True B) False |
B) False
MODELS ARE NEVER COMPLETE |
|
Deductive Argument
|
Conclusion follows from the premises WITH CERTAINTY
|
|
Inductive Argument
|
premises supplies varying degrees of evidence, HAS VALUE
|
|
Target System
|
Aspect of the Real World under investigation
|
|
Scale Model Example
|
DNA Staircase
|
|
Analogue Model Example
|
Atom and the Universe
-Compares 2 different types of things |
|
What is Data?
|
Relavent Information used as evidence to determine goodness of fit
|
|
Models that exhibit good fit are:
A) Always Complete B) Sometimes Complete C) Never Complete D) None of the Above |
C) Never Complete
|
|
A Crucial Experiment has a feature that distinguishes it from other types of experiments. This feature is:
A) Goodness of Fit B) Poorness of Fit C) It is Decisive D) It is Not Decisive |
C) It is Decisive
|
|
6 Steps for Analyzing a Scientific Episode AND EXPLAIN:
|
1) Real World
2) Model 3) Prediction 4) Data 5) Negative Evidence? 6) Positive Evidence? |
|
Who developed a heliocentric model of the solar system?
|
Copernicus
|
|
What did Galileo Do?
|
-Elaborated on Copernicus' Heliocentric Model of the Solar System
-Observed the Phases of Venus |
|
Who developed the Geocentric Model of The Solar System?
|
Ptolemy
|
|
What is a Target System?
|
The real world phenomena under investigation
|
|
Crucial Experiment
|
Data uniquely supports only 1 of 2 models
|
|
_______ is the name for a family of models that typically produce inconclusive results.
|
Marginal Science
|
|
There are many reasons why a family of models may produce inconclusive results. Name Two.
|
1) The Prediction is Vague
2) Empirical Equivalence |
|
According to one model, extra-terrestrial visitation is supposed to explain:
A) The Position of the Planets B) Gravitation C) Strange Weather Patterns D) None of the Above |
D) None of the Above
|
|
This model appeals to planetary influence to explain how persons exhibit certain personality characteristics:
A) Astronomy B) Astrology C) Astrophysics D) All of the Above |
B) Astrology
|
|
4 DESCRIPTIVE steps of analyzing a scientific episode:
|
1) Real World
2) Model 3) Prediction 4) Data |
|
2 EVALUATIVE steps of analyzing a scientific episode:
|
1) Negative Evidence?
2) Positive Evidence? |
|
A ______ is a collection of Objects.
|
set
|
|
We can use sets as a way to think about:
A) Models and Inconclusiveness B) Populations and Samples C) Prediction and Control D) Marginal Science |
B) Populations and Samples
|
|
Describe what has to be the case for a statistical model to exhibit good fit.
|
DRAW OUT DIAGRAM
|
|
If two variables are positively correlated, then they:
A) Tend to Go Together B) Tend Not to Go Together C) Are Equally Represented in the Population D) None of the Above |
A) Tend to Go Together
|
|
The Strength of a correlation can vary between ______ and ______
|
-1 and 1
|
|
Which of the following formulas describes combining probabilities when you want to know the probability of one exclusive event or the other, in other words P(A or B), but not P(A and B)
|
P(A) + P(B) - P(A) X P(B)
|
|
What is a Sample?
|
Subset of a population under study
|
|
What are the two things that must obtain for sampling to be random?
|
1) Equal chance of members being selected from the population
2) Independence of Trials |
|
What is a confidence interval and why is it needed?
|
- A range of values that most likely contains a certain unknown population parameter
- Used in order to minimize outliers and account for random sampling error |
|
A 95% confidence level means that:
A) The results are certain B) There is a 1/20 chance that the results are incorrect C) The sample size is too small D) All of the Above |
B) There is a 1/20 chance that the results are incorrect
|
|
P(A) = F(A) is:
A) Always the Case B) Sometimes the Case C) Never the Case D) A Basic Statistical Truth |
C) Never the Case
|
|
For some value of a random variable 'A' there is some probability of A in the population.
A) True B) False |
A) True
|
|
A increase in the confidence level results in the _________ of the margin of error.
|
INCREASE
|
|
The exact value of the margin of error is determined by:
A) Probability B) Proportions in the Population C) Sample Size D) All of the Above |
C) Sample Size
|
|
A Statistical Hypothesis is a claim about a real-world_______.
|
Population
|
|
In a typical case of estimation the value of _________ is unknown, but __________ is known.
A) f(A); P(A) B) P(A); f(A) C) ME; f(A) D) f(A); ME |
B) P(A); f(A)
|
|
3 Types of Statistical Models
|
1) Proportion
2) Correlation 3) Distribution |
|
Proportion
|
1 Variable and 2 Values
|
|
Correlation
|
2 Variables and 2 Values
|
|
Distribution
|
1 Variable and More than 2 Values
|
|
2 Characteristics of Variable
|
1) Exclusive
2) Exhaustive |
|
What is the definition of a correlation?
|
Symmetrical Relationship Between 2 Variables
|
|
6 Steps of Evaluating a Statistical Hypothesis
|
1) Real World
2) Sample Data 3) Statistical Model 4) Random Sampling 5) Evaluate Statistical Hypothesis 6) Summary |
|
A correlation differs from a distribution or proportion in that it has:
A) At least two variables B) At most one variable C) Any number of variables D) The difference has to do with number of values, not number of variables |
A) At least two variables
|
|
P(A or B) equation:
|
P(A) + P(B)
|
|
P( A and B) equation:
|
P(A) x P(B)
|
|
Conditional Probability:
P(E/M) = ??? |
The Probability of E Given M
-M Obtains |
|
What does it mean to sample without replacement?
|
-Population changes during the sampling process
-Removing a member of the population during each selection |
|
Example of replacement in relation to large and small populations:
|
Sample without replacement from a large population is like sampling with replacement from a small population.
- larger population size = less effect if replacement is used |
|
What is Relative Frequency?
|
-Observed Frequency
-Only in Sample |
|
What is Standard Deviation?
|
-Measurement of the deviation from the mean of a given frequency distribution
-Must have a Sample |
|
Why do we need estimation?
|
-Estimating the Probability of a POPULATION based on the Observed Frequency of a SAMPLE
- Gives Rise to Margin of Error |
|
P(R) = ?
|
P(R) = f(R) plus or minus 2 SD
P(R) = f(R) plus or minus ME |
|
Overlap of Variables =
|
No Correlation
|
|
No Overlap of Variables =
|
Correlation
|
|
Correlation vs. Causation
|
Correlation = Symmetrical
Causation = Not Symmetrical -Correlation tells us that there is a relationship, while causation tells us about the relationship (How?) |
|
Causes _____________ their effects
|
PRODUCE
|
|
What does it mean if causation is deterministic?
|
-Deterministic causation produces a binary value
|
|
What is a Positive Causal Factor?
|
C --> E
Not C --> Not E |
|
What were the 2 primary effects of the saccharine studies?
|
-Bladder Cancer
-Not Bladder Cancer |
|
What arguments were made for the legitimacy of the rat selection in the saccharine studies?
|
-All subjects were lab-raised rats
-All rats were raised in the same environments -Anything that causes cancer in humans, does so in rats |
|
Fk(E) =
|
-Observed frequency of the effect in the control group
|
|
SUBk
|
Control
|
|
SUBx
|
Experimental
|
|
What does it mean if there is no statistically significant difference between the experimental and control groups?
|
They are Causally Irrelevant
|
|
Exclusive
|
Member of the population can only exhibit 1 value
|
|
Exhaustive
|
Every member of the population must exhibit SOME value
-cannot be value-less |
|
Standard Deviation and Estimations
|
-67% lie within 1 SD
-95% lie within 2 SD -99% lie within 3 SD |