Chapter 1 - Intro - Flashcards
Descriptive Statistics
vs.
Inferential Statistics
- Organize, summarize, and communicate numerical information about a sample . Describes the sample! (ex: how many hours of sleep does this one group get?)
- Use samples to draw conclusions about a population (ex: based on that 1 group, how many hours of sleep does the population of Langara get?)
2 things about Inferential Stats that allow us to use these values?
- Develop a margin of error for a value ( ex: I am 95% certain that the average # of sleep is b/w 5.63 and 6.62)
- Make decisions about 2 or more values (‘hypothesis testing’) (ex: the average 1st yr student sleeps longer than your average 2nd yr student)
What exactly is Statistics though?
- A Methodology : a set of procedres and rules for reducing large masses of data to manageable proportions and for allowing us to draw conclusions from those data
- A Numerical Value : the result of arithmetic or algebraic manipulation applied to data
MUST know WHY I’m doing a certain test to find a value. HOW & WHY.
A reason why Statistics is used?
- Allows us to see patterns
- Allows us to see if differences exist between numbers
- Allows us to see if things are related
- All about probability
Make confidence statements in the face of uncertainty.
Sample vs. Population?
- Sample : a portion of the population (gather descriptive statistics. Then, infer parameters.)
- Population: a collection of subjects or events that share a common characteristic
The 4 variables that researchers use to quantify observations?
- NOMINAL - aka Categorical levels because they are in levels (‘best’ tv shows. Numbers are meaningless though)
- ORDINAL - number represents ranked order (top 10 books of 2022)
- RATIO - like an interval, with meaningful distances, but also has a true 0 point, with 0 being nothing. (Like 0 degrees kelvin)
- INTERVAL - numbers represent equal intervals (distances) between levels, but there is no true zero point. ‘Likert’ scales are also considered interval scales (the scales that are strongly disagree, somewhat disagree, neutral, etc)
CALLED THE SCALES OF MEASUREMENT
What is a variable?
any characteristic that can differ in some way, as in ‘a’ and ‘b’. also, variable vary meaning they can assume different values
Variable values can be quantifiable (numeric) or categorical ( ex: gender)
a + b = 12
2 ways that statisticians use to describe ‘scale’?
Discrete variable
vs.
Continuous variable?
- can only take on specific values, like whole numbers (how many kids do you have?)
- can take on a full range of values (with decimal numbers)
Difference b/w independent and dependent variable?
Does sleep impact academic performance? The independent variable (sleep) predicts the dependent variable (academic performance).
- Independent:
- dependent:
What are confounding (confounds) variables?
What is used to control these confounds?
Variables which could also account for the outcome (which were not controlled) We want to try for only 2 variables accounting for the outcome.
Control for these confounding variables by randomly assigning particiants.
Difference between reliability & validity?
How are they related?
What is an operational definition?
How is it used for dependent/independent variables?
Needs 2 things to be a good definition:
1. RELIABILITY - consistency of a measure (are the values close to each other? Like getting within 0.10 mL of the other values in a chemistry lab)
2. VALIDITY - refers to whether the operational definitions measures what it intends to measure (asking someone every few months if they are depressed, and they say it their depression varies with their ‘mood’. Well, this is valid, because it’s measuring what it’s supposed to be measuring!)
Something can be reliable but not valid! and vice versa. Both things to be present.
O = T + ME
Obtained score = ‘True’ (hypothetical) score + error in measurement
We get the O but we don’t know what’s on the right side of the equation.
Define, in a scientific way, the word experiment?
Experimental vs. Correlational research?
What is meant by between-groups research design
&
within-groups research design?
- Take participants from both groups (let’s say the 5hr sleep group and the 8hr sleep group) and test them. The word “between” means that you’re comparing different conditions between groups.
- Take participants from only the 5hr sleep group and test them. Then do the 8hr sleep group. The word “within” means you’re comparing different conditions within the same group.
Correct the wrong word:
In a study on exam prep, every participant had an equal chance of being assigned to study alone or with a group. This was a correlational study.
A psychologist was interested in studying the effects of the dependent variable of caffeine on hours of sleep, and she used a scale measure for sleep.
change dependent to INDEPENDENT
Correct the wrong word:
In a study on the effects of the confounding variable of noise level on the dependent variable of memory, researchers were concerned that the memory measure was not valid.
A researcher studied a population of 20 rats to determine whether changes in exposure to light would lead to changes in the dependent variable of amount of sleep.
What is meant by Data Ethics?
What is Open Science?
A set of principles related to all stages of working with data – research design, data collection, statistical analyses, interpretation of analyses & reporting of outcomes.
It is an approach to research that encourages collaboration, and includes the sharing of research methodology, data, and statistical analyses in ways that allow others to question and even to try to recreate findings
What is an example of unethical practices with researchers?
skewing the data to best fit what I want
What is HARKing and pre-registration?
Hypothesizing after the results ARE KNOWN (collect the data, develop the hypothesis, then test that hypothesis with that data – self serving data!)
Supposed to be: Develop Hypothesis –> Collect Data –> Test Hypothesis
Pre-register: scientists register their hypothesis so they remain accountable
Calculating Stats:
A researcher studies the number of hours 2500 Canadians exercise every week. Identify the sample and the population for this example.
Calculating Stats:
A bookstore employee asked 225 students to complete a customer satisfaction survey after these customers bought their books. The manager wanted to find ways to improve the customer experience. Identify the sample and population for this example.
Calculating Stats:
Over the course of 1 week, a grocery store randomly selected 100 customers to complete a survey about their favourite products. Identify the sample and population for this example.
Calculating Stats:
A researcher studies the average distance that 130 ppl living in urban areas in India walk each week.
1. Size of sample?
2. Population?
3. Is the ‘average’ a descriptive stat or an inferential stat (used to describe the 130 ppl)
4. How might you operationalize the average distance walked in 1 week as a scale measure?
Calculating Stats:
As they leave a grocery store, 73 ppl are stopped and the # of fruit and veggie items they purchased is counted:
1. Size of sample?
2. Identify the population.
3. If this # of itms counted is used to estimate the diets of all shoppers, is it a descriptive or inferential statistic?
4. How might it be operationalized for the amount of fruit/veggies purchased as a nominal measure?
Applications:
In the fall of 2008, the stock market plummeted several times, with grave consequences for the world economy. A researcher might assess the economic effect this situation had by seeing how much money people saved in 2009. That amount could be compared to the amount people saved in more economically stable years.
How might you operationalize the economic implications at a national level, across countries?
Suppose a researcher is interested in evaluating how pet ownership and social activity affect loneliness.
- Dependent and independent variable?
- If pet ownership is assessed as either owning pets or no pets, and that social activity is assessed as going out with friends or family never or at least once a week, then how many levels do the independent variables have?
- How to operationalize the indep. variable?
Calculating Stats:
A study of the effects of skin tone (light, medium, dark) on the severity of facial wrinkles in middle age might be of interest to dermatologists.
1. Independent variable?
2. dependent variable?
3. How many levels would the indep. variable have?
Application:
According to the WHO, more than 300 million ppl suffer from depression globally:
1. This stat based on a sample or a population? WHY?
2. Is 300 million a descriptive or inferential stat? WHY?
In Norway, 60,000 ppl were surveyed and they reported that gastrointestinal symptoms, depression, and anxiety disorders are strongly related:
1. Sample used by researchers?
2. Population that researchers would like to extend their findings?
Applications:
At the 2012 Olympics, Michael Phelps won 4 gold medals, bringing his Olympic career medal count to 18 gold medals. One of the events is the 100 -metre butterfly. Identify the type of variable (nominal, ordinal, or scale)
1. Phelps of the USA came in 1st and Chad Le Clos of South Africa and Evgeny K of Russia tied for 2nd.
2. Phelps finished in 51.21 sec and le Clos/Evgeny finished in 51.44 sec.
3. Phelps and Evgeny live in the northern hemisphere, while le Clos lives in the southern hemisphere.
Application:
The Kentucky Derby is perhaps the premier event in the US horse racing. Identify the type of variable (nominal, ordinal, scale):
1. As fans, we are interested in the variable finishing position. One year, Orb won, with Golden Soul 2nd, and Revolutionary 3rd.
2. Variable finishing time. Orb won in 2min, 2.89 sec.
3. Attendence was 151,616 that year, and the record was 165,307.
4. For gamblers, the variable payoffs: $2.00 was bet on Orb and the gambler won $12.80
5. We might be interested in the history of the derby and demographic variables of jockeys, such as gender or race. In the first 28 runnings of the Derby, 15 of the winning jockeys were black Americans.
6. We might be interested in the variable of hat wearing, observing how many women wear hats and how many do not.
Applications:
For the following, is the scale variable discrete or continuous?
1. The capacity for songs on an iphone.
2. The playing time of an individual song.
3. The cost to download a song legally.
4. The # of posted reviews that an album has on Amazon (US)
Applications:
For a wine store, how useful are those ratings? (the wines are rated from 50 to 100, with 100 being the top). It was studied whether wine experts are consistent. Knowing that the weather is the best predictor of price, the researchers looked into how weather affected the ratings. The variables include temperature, rainfall, and for the wine experts’ ratings, the # given to each wine.
1. Name one independent variable and what type it is and if it’s discrete or continuous.
2. Dependent variable. Type. and if it’s discrete or continuous.
3. How does the study reflect the concept of reliability.
4. Let’s say you agree with an expert’s ratings and his ratings are also found to be reliable. How does this observation reflect the concept of validity?
The website Rap Genius analyzed the rhyme density, which is the proportion of all syllables that rhyme with anothe syllable. Eminem’s ‘Without Me’ has a rhyme density of 0.49 (49%) because almost half of the lyrics rhyme with another syllable, whereas Notorious BIG;s ‘Juicy’ is 0.23. Rap Genius says “Over the course of a career, the rappers with the highest rhyme densities are basically the best technical rappers.”
1. How does the website operationalize the best rapper?
2. List at least 3 other variables that might be considered in determining the best rapper.
3. MF Doom came in first with an overall rhyme density of 0.44 and Cam’ron came in 2nd with 0.41. What kind of variable is the ranking, and what kind of variable is the rhyme density?
Applications:
Forbes reported the 10-top earning comedians (all men) for 2013. Journalists wanted to know why there were no women. Forbes explained their methodology: to compile the data, they used earnings, by talking to agents, lawyers, adn other industry insiders to coe up with an estimate for what each comedian would have earned. The caveat: their primary source of income had to come from concert ticket sales. One journalist (Erin Gloria Ryan) remarked that is “was a super weird definition of what constitutes a comedian”.
- Explain how Forbes is operationalizing the earnings of comedians.
- Explain why Ryan might have a problem with this definition.
- Ryan also said that if Dr Dre doesn’t need to record an album in order to be considered ‘a real hip hop artist’ than why does a female need to have a concert in order to be considered a real comedian. Offer at least one different way of operationalizing the earnings of comedians.
Applications:
Looking at increased weight across a population, researchers, nutritionalists, and physicians have worked to find ways to decrease obesity in countries. If there is a research study to examine the effects of an exercise program on weight loss compared to a program with no exercise:
- Describe how you could study the exercise program using a between-groups research design.
- Describe how you could study the exercise program using a within-groups design.
- What is a potential confound of a within-groups design?
Applications:
As vaping/e-cigarettes becomes more popular, researchers are realizing the potential negative effects of this behaviour. According to Scientific American, researchers have investigated the harmful effects of nicotine, including it’s links to heart disease, as well as the dangers of several carcinogens inhaled while vaping:
1. Why was this research necessarily correlational in nature?
2. What confounding variables might make it difficult to isolate the health effects of vaping?
3. How might the nature of this research and these confounds buy time for the e-cigarettes industry with regard to acknowledging the hazardous effects of smoking?
4. All ethics aside, how could the relation between vaping and health problems using a between-groups experiment?
Applications:
A researcher is studying the cultural values of individualistic and collectivist societies collects data on the rate of relationship conflict experienced by 32 people who test high for individualism and 37 people who test high for collectivism.
- Is the research experimental or correlational?
- What is the sample?
- Consider a possible hypothesis.
- How to operationalize the relationship conflict?
Applications:
A study in Argentina concluded that ppl were more likely to bring their own bags when plastic bags were charged. Imagine that you want to design a follow-up study in another country:
- Write a hypothesis for this researcher.
- Describe how you could design a correlational study to test this hypothesis.
- Describe how you could design an experiment to test this hypothesis.
Applications:
Australian psychologist Mark Rubin likened the unethical practice of HARKing to the tale of the Texas sharpshooter. Rubin explains that the sharpshooter “aims and fires his gun at [a] target on a barn wall but misses. He then walks up to the wall, rubs out the initial target, and draws a second target around his bullet hole in order to make it appear as if he is a good shot”.
- Why is this a good analogy for HARKing in research?
- How could preregistration help with the problem of HARKing in research?
Applications:
A large research project in the UK stated “while it’s true that cohabiting parents are more likely to split up than married ones, there is very little evidence to suggest that this is due to a causal effect of marriage. Instead, it seems simply that different sorts of people choose to get married and have children, rather than to have children as a cohabiting couple, and that those relationships with the best prospects of lasting are the ones that are most likely to lead to marriage”.
- Sample?
- Likely population?
- Correlational or experimental study?
- Independent variable?
- Dependent variable?
- 1 possible confounding variable? Suggest a way the confounding variable might be operationalized?
Applications:
A large study analyzed data from a national longitudinal survey called NLSY79, including 12,000 men and women in the US from 14-22 yrs in 1979. The study reported that ability is related to wages in earlier career jobs for university graduates (but not for high school graduates). Also, research has found that racial discrimination with respect to wages is more prevalent against high school graduates than college graduates, because when ability is not the main reason for determining wages, other factors irrelevant to ability (race, for example) come into play. Researchers suggest this as a reason that a black person is more likely to get a uni degree than a white person of the same ability level.
- Independent variables.
- Dependent variables.
- Sample?
- Population conclusions were drawn from?
- What is meant by ‘longitudinal’?
- The Armed Forces Qualification Test (AFQT) was used as the measure. It uses word knowledge, paragraph comprehension, math reasoning, & math knowlege subscales. Suggest at least 1 confounding variable between ability and wages, when comparing uni and high school graduates.
