psych 2910 midterm 2, 2910 mc for midterm 2, Research Stats 2910 midterm 3 MC/ fill ins, final stats MC review

ethical research

informed consent, confidentiality, debriefing, deception.

what is considered ethical has evolved over time and continues to change

often no correct answer

You have data that is rounded to the nearest whole number. You want to create a frequency table, starting at 20 (which was the lowest score that you had, with an interval width of 4. What are the real limits of your first interval?

19.5 - 23.5

The mean on an exam is 68, with a standard deviation of 14. If 2 points were added to everyone's score (n=30), the standard deviation would be:

14 (unchanged)

What type of correlation should be used if you have 2 continuous variables

pearson's r

The mean on an exam is 68, with a standard deviation of 14. If everyone's score (n=30) were divided by 2, the standard deviation would be:

7 (divided by 2)

What type of correlation should be used if you have 2 ordinal variables

spearman's

You are reading an article regarding scores on an academic test that are rounded to the nearest percent. The data for this test is listed in a frequency table with an interval width of 10. You want to know the precise median, so you calculate it using linear interpolation and the information from the frequency table. You get a score of 72.5%, but the author (who has access to all the data) reports that the precise median is 74.0%. What is the most likely explanation for this discrepancy?

Your calculation of the precise median is less precise than the author's because you only know how many data points are within each interval, not the actual data points themselves

Tri-Council Policy Statement

In Canada, the official statement of ethical conduct for research involving humans; researchers and institutions are expected to adhere to this document to receive federal research funds.

CIHR- Canadian institutes of health research

NSERC-Natural sciences and engineering research counsil

SSHRC-social sciences and humanities research counsel of Canada

History of Ethics

a series of mostly medical studies have driven ethical concerns

ex: the US deliberately infected people in Guatemala with syphilis.

Experiments conducted in Germany during WW2 led to: Nuremberg code of ethics (1947), Helsinki Declaration (1964) , Belmont Report (1979)

IQ scores are normally distributed, and the mean is 100 and the standard deviation is 15. Using the "rule of thumb" guide I presented in class (and which your text calls the "empirical rule"), which of the following is a reasonable statement:

Approx. 95% of the IQ scores fall between 85 and 115

What type of correlation should be used if you have 2 dichotomous variables

phi ( circle with vertical line through it)

In terms of research ethics, what is the difference between withholding information and deception?

The former is not mentioning something that would not affect decision to participate whereas the latter is active misrepresentation and is typically more ethically problematic

Milgram Study

Leaner: actually a confederate

Teacher: actually the subject

Experimenter:ordered the teacher to correct learner by administering increasingly high levels of electric shock.

Results : FULL obedience up to the highest shock level. Overall 65%

Before conducting a correlation, i recommended you look at a scatter plot to determine if any of 3 conditions are present that would make a correlation inappropriate. What are those 3 conditions

1. Not linear

2. Outliers

3. limited range

July notices that every time she opens a particular website, the ads on the website are related to her last google search. She reasons that Google must be sharing information with that website is such a way that allows it to choose the ads she sees. This is an example of:

inductive reasoning

You have two competing theories that explain why gentleman prefer blonds (for the sake of this example, assume this is true). Theory A posits that blonds smile more. Theory B posits that, historically, depictions of blondness have many several different connotations, that are both positive and negative, but given our current historical setting, these different factors sum to indicate a positive preference for blonds. Both Theory A and Theory B are equally accurate are predicting the degree of attractive of blonds to gentlemen. Which theory should you go with and why?

Theory A because of the principle of Parsimony

A major distinction between quantitative and qualitative methods is that quantitative techniques use _____________ while qualitative techniques involve______________.

numerical descriptions; verbal descriptions

Real life version of milgram study

- Nurses were telephones by a physician they did not know

- Ordered to administer a non-prescribed drug in double the maximum dosage to a patient

- 21/ 22 ( 95.5%) followed the doctors' orders

Core Principles

- Respect for persons: choose participation freely and without interference

- Concern for Welfare: Minimize risks and maximize benefits, individuals should be free to decide whether the balance of risks/ benefits is acceptable

- Justice: treat people fairly and equitably

Risk VS Benefit analysis

- Psychological and Physiological harm

- Benefits to both individual and society

Potential Risks

- Physical Harm: Sleep deprivation, injecting drug or placebo

- Stress: providing unfavourable feedback about personality, intelligence etc to lower self esteem . asking about traumatic events

- Loss of privacy and confidentiality: Privacy - right to control information, confidentiality- keep info secret and/or anonymous

Informed consent

an ethical principle that research participants be told enough to enable them to choose whether they wish to participate

. One frequent criticism of experimental research designs in general is

artificial settings

A researcher wants to gather information on a citizens feelings about the building of a new airport in their neighbourhood. She gathers groups of citizens and engages them in a discussion bout the advantages and disadvantages of this airport. This type of data gathering is best referred to as a(n)____________ approach

Qualitative

Two researchers tested the hypothesis that college students' grades and happiness are related. One researcher operationally defined happiness as the number of hours spent at leisure activities. The other researcher operationally defined happiness as the amount of achievement one feels as measured on a 10 point scale. Which of the following statements is accurate?

The difference in operational definitions of happiness could lead to different results.

The goal of naturalistic observation is to

Conduct experiments in real, rather than artificial environment

A person has an IQ of 145; this score is 3 standard deviations above the normative mean. Approximately how many people have IQs within 3 standard deviations of the mean?

99%

A research is likely to choose a non-experimental method if

The goal of the research is predictive

Vulnerable populations

infants, children, older adults, the ill, the physically and mentally disabled, the illiterate, the poor, students, prisoners ...

explicit coercion

offering an incentive " 200$ for 1 hour" " reduced prison sentence"

Should an observe conceal or disclose that fact that observations are being made?

The type of observation must be decided on a case by case basis

The mean on an exam is 70, with a standard deviation of 16. If 2 points were subtracted to everyone's score (n = 40), the standard deviation would be:

16 (unchanged)

implicit coercion

guilted into it basically

According to your instructor, a type of validity that is essentially useless (i.e., it doesn't matter if a measure is high or low on this type of validity) is

Face validity

a major difference between systematic observation and naturalistic observation is that systematic observation

observes specific behaviours in a specific setting; naturalistic observation does not.

The mean on an exam is 70, with a standard deviation of 16. If everyone's score (n = 40) were divided by 2, the standard deviation would be:

8 (divided by 2)

Joanne and Carole are conducting a systematic observation study on children's aggressive playground behaviour. Joanne concludes that boys display more aggressive behaviours than girls, Carole concludes the opposite. based on these conclusions, which methodological issue would be of most concern in this study?

Reliability

IQ scores are normally distributed and the mean is 100 and the standard deviation is 15. Using the "rule of thumb" guide I presented in class (and which your text calls the "empirical rule"), which of the following is a reasonable statement:

Approximately 66% of the IQ scores fall between 85 and 115

Deception

- Active misrepresentation of information

- Ex: Milgram study: purpose was on obedience not memory, use of confederate

- Most common in social psychology

- Usually in form of a cover story, usually not nearly as severe as Milgram( because ethics boards wont allow it)

debreifing

- Opportunity for Researcher to deal with the potentially harmful effects of withholding information, deception and effects due to participation itself

- If research alters physiological or psychological state, debriefing process is when original state is restores or additional help ( medical, psychological is offered)

A person has an IQ of 145; this score is 3 standard deviations above the normative mean. Approximately how many people have IQs within 3 standard deviations of the mean?'

99%

In survey research, when individuals tend to respond to all questions from a particular perspective rather than to the content of the questions, they are displaying?

a response set

Which of the following indicates the strongest correlation?

r = - 0.80

Jack has a difficult time answering the question "Are you in favor of increasing tuition in order to increase the number of classes and parking spaces offered?" because it is a _____ question.

Double barrelled

Which is the largest z-score value you are likely to see in real data:

3.0

Ethics boards at MUN

- HERB: Health Research Ethics Board; all health related research, provincial law regulates health research and oversees

- ICEHR: Interdisciplinary Committee on Ethics in Human Research; all non- health research involving humans

- ACC- Animal Care committee - research involving animals

What constitutes Research

- No clear- cut rules on what constitutes research

- Most likely is research if the researcher intends to publish ( paper, talk, thesis, presentation , etc)

- Most likely not research if the instructor intends it only as a class exercise

Two researchers tested the hypothesis that college students' grades and happiness are related. One researcher operationally defined happiness as the number of hours spent at leisure activities. The other researcher operationally defined happiness as the amount of achievement one feels as measured on a 10-point scale. Which if the following statements is accurate?

The difference in operational definitions of happiness could lead to different results

are you in favour of programs designed to help lower the unreasonably high rent in the city? is an example of a(N) ________ question?

Loaded

One frequent criticism of experimental research designs in general is

the use of artificial settings

Risk levels

- Exempt: Publicly, and legally available; Observation ; no interaction or intervention; data already collected and anonymous

- Best practice is for an independent determination. REB decided not researcher

- Minimal Risk: Risks of harm are no greater than those encountered in everyday life

- Greater than Minimal Risk: Vulnerable populations, sensitive questions

In order to eliminate the problem of a person always agreeing or disagreeing on all items in a questionnaire, a researcher would

word half the questions in a positive way and half the questions in a negative way

A researcher is likely to choose a non-experimental method if

the goal of the research is descriptive AND the goal of the research is predictive

A researcher found that as the amount of violence watched on TV increased, the amount of playground aggressiveness increased. Based on these findings, it can be said that

knowing the amount of violence children watch on television allows prediction of their aggressiveness

When constructing a survey, it is a good idea to ask the most interesting and important questions________________

scattered throughout the survey

Animal Research

- Canadian Council on Animal Care

- Sponsored by CIHR and NSERC to " oversee the ethical use of animals in science in Canada"

- Animal Care Committee: Must have at least one of each of the following on the committee: experienced scientist, institutional member who does not use animals, experienced veterinarian, community member

Animal research 3rs

- Replacement: replace use of animals with other techniques if possible, Modelling , meta-analysis, simulation

- Reduction: Minimize number of animals used

- Refinement: Refine procedures to minimize stress and pain

. A researcher investigated the relationship between test length and grades in a Western Civilization course. After randomly assigning students to groups, she found that students who took longer exams received better grades than students who took shorter exams. The dependant variable was

test grades

In general, the lower the response rate for a survey, the

more likely biases exist to distort the findings

fraud, plagiarism and data

Other issues : Fraud

- Diederik A. Stapel: A Dutch social psychologist who made up dozens of papers

- Mark Hauser: Evolutionary biology and cognitive neuroscience at Harvard

- Daryl Bem: US psychologist reported evidence that people could predict the future at a better-than-chance rate under some circumstances

Other Issues: Plagiarism

- Using someone else's' work without giving credit to the original source

- A phrase or sentence or paragraph or idea

- Doesn't matter if the original source is a book, journal article, web site or another person

- It's still plagiarism even if you paraphrase or rearrange the order of the words

- To avoid plagiarism, cite the original source

Other Issues: Data

- Not making data available: hinders independent re-analysis, prevents additional analyses ( meta-analysis)

- However: Does releasing data to others cause other ethical issues ( privacy or confidentiality)

- Many Journals require that data be made available

- Anonymize

Your instructor showed you that there is a positive linear relation between the number of people using Internet Explorer (variable A) and the number of homicides (variable B). there are 4 interpretations of this correlation. Which is the most appropriate interpretation based on this correlation?

a third variable causes A and B

a _______ sample size will ________ the size of the confidence interval

Larger; Expand

A researcher investigated the relationship between test length and grades in a Western Civilization course. After randomly assigning students to groups, she found that students who took longer exams received better grades than students who took shorter exams. The independent variable was:

length of test

Your instructor showed you that there is a positive linear relation between the number of people using Internet Explorer (variable A) and the number of homicides (variable B). There are 4 interpretations of this correlation. Which is the most appropriate interpretation based solely on this correlation?

It is a spurious correlation

Law

a universal statement of the nature of things that allows reliable predictions

Sarah stands outside of a grocery store on the west side of town and surveys exiting shoppers about their preference for frozen desserts. What type of sampling technique does Sarah's survey represent?

Non- probability

. Your instructor showed you that there is a positive linear relation between socioeconomic status (SES; variable A) and academic achievement (variable B). there are 4 interpretations of this correlation. Which is the most appropriate interpretation based solely on this correlation?

A causes B

Theory

a general statement about the relation between two or more variables.

Organize and explain

• Provides a framework for organizing otherwise

disparate findings and offers explanation

• Generate new knowledge

• If you cannot change action, will change belief

Probability sampling techniques are most important for

Generalization of results to a population

Your instructor showed you that there is a positive linear relation between socioeconomic status (SES; variable A) and academic achievement (variable B). There are 4 interpretations of this correlation. Which is the most appropriate interpretation based solely on this correlation?

Not enough information presented to determine an answer

Hypothesis

testable prediction about specific events

The head of the psychology department in a university is interested in finding the attitudes of her students toward implementing an internship as a requirement for completion of the degree. She obtains a list of all students who are psychology majors, randomly selects 100 students from the list, and surveys those who are selected. What type of sampling technique has she employed?

Simple random sampling

A type of validity that focuses on the extent to which the measure is measuring what it is supposed to be measuring and nothing else is

content validity

If you want to assess political allegiances amongst registered voters in St John's classified by social class and age, you might randomly select voters from each subgroup according to their proportion in the entire city. This sampling technique is called______

Stratified random

Festinger's Cognitive Dissonance

When two beliefs or beliefs/actions are

dissonant (inconsistent), people

experience an adverse state of arousal

• Highly motivated to reduce aversive

arousal by changing beliefs/actions

• Usually cannot undo actions

•Therefore, change beliefs

Example

• Core belief: I'm a smart person

• Version 1

• Public Action: Pay $1 to see an awful play

• No conflict: Only paid $1

• Judgment: Play was awful

• Version 2

• Public Action: Pay $100 to see an awful play

• Conflict: Smart people don't waste $100

• Judgment: Play was actually quite good

Francis Bacon (1561-1626)

Method of induction: reasoning from

specifics to general principles

• careful, systematic observations

• e.g., how cats and dogs interact, develop general

explanation, can predict future interactions

• Reason from specific to general

Cohen's d is a measure of size effect that can be best interpreted as

describing effect size in terms of SD units

Questionnaires in magazines or on internet websites usually

are neither reliable nor valid AND have unknown reliability and validity

David Hume (1711-1776)

Problem of induction: How many

observations are needed?

•The next observation could disprove the

previous ones

• Accounts based on observations can be

erroneous

• This sheep is white, this sheep is white ... All sheep are white

Inferential Statistical tests always examine a null hypothesis( Ho) that is expressed negatively ( There is no effect, no difference ) why?

It is easy to disprove a negative Ho

Assume you are conducting your honours research. You find two tests that purport to measure IQ. Measure A has a large negative correlation with scores on a personality test and Measure B does not correlate with the personality test. Which IQ test is likely to have better discriminant validity?

Measure B

A Human Resources director believes that people who regularly use math as part of their job will have higher math test scores than people who do not regularly use math professionally. The director would be most concerned with what type of validity?

Concurrent validity

What is a type 1 error

A type one error is when the researcher rejects the null hypothesis but it is actually true.

Deduction

• Complement induction with deduction

• Reasoning from the general to the

specific

• If P, then Q (modus ponens)

• Use a general statement (theory) to make

a prediction (hypothesis) that is then

tested against observations

• It is possible to disprove a theory, but it is

impossible to prove a theory

Science

Goal is to develop increasingly more

accurate theories and accounts

or

• Goal is to develop increasingly less

inaccurate theories

What is a type II error?

When the researcher retains the null hypothesis but it is actually false

I attached a fancy gadget to my large truck's OBD-II port, and it allows me to calculate precisely my fuel economy (in litres per 100 km). Most trucks use about 10 litres per 100 km in highway driving. I drive the truck to Gander and back twice, and the 4 estimates are: 42 litres/100 km; 41 litres/100 km; 43 litres/100 km; and 41 litres/100 km. What should I conclude about the gadget?

It is reliable but not valid

Parsimony

Occam's razor:

• Choose the more simple of two competing theories

that do an equally good job of explaining the data

• C. Lloyd Morgan's Canon:

• "In no case is an animal activity to be interpreted in

terms of higher psychological processes, if it can be

fairly interpreted in terms of processes which stand

lower in the scale of psychological evolution and

development." (Morgan 1903, p. 59)

Good samples have two characteristics. Describe them

Using a random selection group from the sample population as it makes the results more generalizable and it eliminates the possibility for experimenter biases

2. A large sample size

Dr. Jamal is correlating gender (male or female) to a 1 to 100 rating of happiness. Which correlation coefficient should they use?

Point biserial correlation

Step 1: Recognize or identify a problem (Process of Parsimony )

Step 1: Recognize or identify a problem

• A recognized gap in knowledge or an important

question in response to some event/issue

• What are you interested in?

• Does unemployment lead to poorer psychological / physical

health status?

• How does this occur?

• Under what circumstances?

• How can this be remedied?

Dr. Jones is correlating class ranking in a group of Law students to their ranked salary five years later. Which correlation coefficient should they use?

Spearman correlation

Dr. James is correlating preference for daylight savings time (yes or no) to whether you live in an urban or rural environment. Which correlation coefficient should they use?

Phi coefficient

Step 4: Hypothesis Development ( process of parsimony)

Step 4: Hypothesis Development

• A more specific version of a theory that tries to

organize particular data and independent/

dependent variables relations within a portion of a

larger, comprehensive theory

• Research hypothesis: An even more specific version

that makes a prediction

• Cognitive Dissonance:

• Alcohol consumption will lead to decreased arousal and thus reduced

expressions of dissonance

Step 2: Review the literature (process of parsimony)

• Once a question has been identified, researchers

must determine whether similar studies have been

conducted

• Focus on peer-reviewed journals

• PsycINFO, Web Of Science, Scopus, etc

• What is already established about the issue?

• How have studies been conducted?

• What can new studies add?

Dr. Smith measured a sample of 60 redheads on a mental rotation task. The mean of this sample was 15 and the standard deviation was 5. The mental rotation task is known to have a mean in the population of 13 and a standard deviation of 6. If Dr. Smith wants to know if redheads are different from the population on this mental rotation task, which test should she conduct:

Z-test

Step 3: Theoretical Considerations ( process of parsimony)

• During literature review, learn about particular

theories associated with the issue

• Organize:

• What do all the findings relating to unemployment and health

have in common? ... (stress, anxiety, low self esteem, etc.)

• Generate Predictions:

• Provide a "road map" to relevant areas of study: Do health

outcomes of unemployment vary by gender, type of work, social

support, income relief, etc?

One way to increase the power of a t-test is to increase the alpha. What else would increase if you increase alpha?

Type I Error

Problems with parismony

People -- including researchers -- aren't

very good at logical reasoning

• People have a tendency to propose tests that

confirm rather than disconfirm a belief/hypothesis

• Also known as confirmation bias, positive bias

• Superstitions

• Scientific reasoning

• These numbers follow a rule: 2 4 6

• Self-fulfilling prophecy

• Child labeled as "bright" or "dumb"

A researcher compared a group of 70 right-handed university students to a group of 30 left- handed university students on a continuous measure of creativeness. A Levene's test indicates the variances can be assumed to be equal. The researcher conducts an independent samples' t-test and finds that the p-value for the test is below the alpha level. What should this researcher conclude?

They should reject the null hypothesis and say there is a significant difference between the groups.

Wason Selection Task

If a card has a vowel on one side, it

must have an even number on the other.

• Which 2 cards to you turn over to

disprove this rule

Logic vs. Experience

If a person is drinking beer, that person

must be at least 19

• Which 2 cards do you turn over to

disprove?

A researcher compared a group of 70 right-handed university students to a group of 30 left- handed university students on a continuous measure of creativeness. A Levene's test indicates the variances cannot be assumed to be equal. The researcher conducts an independent samples' t-test and finds that the p-value for the test is below the alpha level. What should this researcher conclude?

They should not make any conclusions because the t test is not trustworthy in this particular circumstance.

A researcher compared a group of 50 right-handed university students to a group of 50 left- handed university students on a continuous measure of creativeness. A Levene's test indicates the variances cannot be assumed to be equal. The researcher conducts an independent samples' t-test and finds that the p-value for the test is below the alpha level. What should this researcher conclude?

They should reject the null hypothesis and say there is a significant difference between the groups.