Exam Review Flashcards

1
Q

What are the 4 different types of hypothesis tests?

A
  • Observational
  • Meta- Analysis
  • Model
  • Controlled
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are Means and Standard deviation?

A
  • Standard deviation is a measure of how dispersed the data is in relation to the mean
  • The mean is the average (sum total of all values, divided by the number of values in total)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Where does variance come from?

A
  • Variance is a measure of variability

- Calculated by taking the average of the squared deviation from the mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What does variance mean?

A
  • It tells you the degree of spread in your data set (the more spread the data is, the larger the variance is in relation to the mean)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How does variance (or standard deviation) change if you increase your sample size?

A
  • The larger the sample size, the smaller the variance of the sampling distribution of the mean
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What does impact factor mean?

A

It is the average in a journal of how many times the article has been cited in that year

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What does inductive reasoning mean?

A

It doe not use explicitly use the hypothesis but it creates a generalization

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What does deductive reasoning mean?

A

It does use the hypothesis and is used to produce a prediction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the scientific method?

A

Scientific method is away to seek more knowledge by forming/testing a hypothesis to answer a variety of questions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is meta-analysis

A

it is a one of the four ways to test a hypothesis, it compares results of other studies that have been done

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is a observational test?

A

They are collected and compared to the predicted results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

what is a controlled experiment?

A

you are measuring a response variable that you choice to manipulate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is a mathematical model?

A

using various mathematical structures like graphs and equations to represent real world situations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are the similarities of the 4 ways to test a hypothesis?

A

1) Most seek to explain some observations
2) Most invoke hypotheses and use experiments
3) Many base conclusions on comparisons
between actual results and predictions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What are the differences of the four ways to test a hypothesis?

A

4) Differences largely cosmetic and involve
jargon
5) There really isn’t any, their very similar

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Why do we use the classic scientific method?

A
  • its simply and logical
  • it applies to every branch of science
  • has a high success rate
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

How do we decide if claims are believable?

A
  • Evaluate their evidence
  • Evaluate conflicting interests
  • Consider views of certified (and nonbiased) experts
  • Determine effects of action vs. nonaction
18
Q

What is an argument?

A

when you use reasoning to support your conclusion

19
Q

What is a supporting reason also know as?

A

a premise

20
Q

how many premises are used for support?

A

one or more

21
Q

What must arguments have?

A

they need to have at LEAST one premise and one conclusion

22
Q

What are the six steps to the scientific method?

A

1) observe
2) Generate an alternative explanation
3) Generate a test for the explanation
4) Deduce a prediction
5) do the test and compare results with the prediction
6) make a conclusion

23
Q

What constitutes a well designed test?

A
•relevant to the hypothesis
•has a clearly defined response variable
•controlled (isolates the effect of one
variable, accounts for other variables)
•produces unique predictions
•replicated (examines more than one test
subject)
•practical and ethical
24
Q

How to make a model?

A

1.Decide on what you are trying to explain
2.Determine variables and constants that
could affect response variable
3.Carefully think about assumptions of
model system
4.Use above to generate mathematical
representation of system of study
5.Find parameter values for variables and
constants
6.Explore model dynamics

25
Q

What are the two type of modeling?

A
  • Empirical

- Theoretical

26
Q

What is the empirical model?

A

Describes the statistical relationship among variables

27
Q

What is the theoretical model?

A

uses a mathematical framework to explore the sensitivity of a given response variable to changes parameter values

28
Q

What is the theoretical approach?

A
  • uses logic and knowledge to create mathematical representation
  • seeks mechanisms underlying relationship
  • tests hypothesis by comparing quantitative predictions with actual data
29
Q

What are the positives of a mathematical model?

A

1) Useful for testing all kinds of hypotheses
2) Complements empirical approaches
3) Quantitative method to link theory with
knowledge
4) Independence can be guaranteed
5) Can be relatively inexpensive and can be
completed by anyone
6) Simple models can lead to unexpected and
complex dynamics

30
Q

What are the negatives of the mathematical model

A

1)Simple models can lead to unexpected and
complex dynamics
2) Open to bias by modeler
3) If poorly constructed, models may
produce meaningless results
4) Mathematics are highly abstract and can
limit understanding
5) Not feasible for many questions due to
lack of information

31
Q

What are the positives of the meta analysis test?

A
•Powerful and robust (based on
many studies)
•Wide scope (high applicability)
•Can account for many confounding
variables
•Can be inexpensive
32
Q

What are the negative of the meta analysis test?

A
  • Uncontrolled variables can be problematic
  • Not feasible for many questions due to lack of information
  • Can be difficult to standardize results among many studies
  • Publication bias
33
Q

How do we estimate variance?

A
  • Look at distribution of values (graphs)
  • Look at range (difference between highest and lowest value)
  • Estimate the average deviation from the mean (or something similar)
34
Q

What affects the estimates standard deviation?

A
  • The amount that is observe differs from the mean

- The number of observations made

35
Q

What is retraction?

A

Its when a journal withdraws a publication. More/less it means the published
paper is not published anymore

36
Q

What are the five reasons retractions happen?

A

1) Inadvertent mistakes.
2) Fraud
3) Misattributing authorship or affiliation
4) Falsifying reviews
5) Conflicts of interest (usually unstated)

37
Q

What is ‘Basic Science’?

A
  • contributes to general knowledge and an understanding of nature and its laws
  • motivated simply by curiosity
  • little or no concern about value of results for humans
38
Q

What is applied science?

A
  • does not typically add to general understanding of the world
  • uses knowledge and information to address specific problems
  • motivated by desire to improve technology
39
Q

Replication versus Realism

A

<>Small experimental systems advantageous due to high replication and repeatability.
<>Bottle systems have little natural relevance
<>Large experimental systems advantageous due to realism
<>Very costly to study and usually limited replication, few design options, and no
repeatability

40
Q

What are the primary sources of uncertainty?

A

1) Lack of data
2) Poor scientific framework
3) No/inadequate models

41
Q

What are the forms of research?

A
  • Undergraduate honors
  • Graduate (MSc and PhD)
  • Postdoctoral
  • University faculty
  • Industrial
  • Government