AT505 Quiz 2
Give an example of nominal data
1) Gender 2) Hair color 3) State you live in
Read the 10 commandments of data collection
1) Get IRB approval before you begin collecting data; Think about the type of data you will have to collect to answer your research question 2) Think about where/how you will obtain the data 3) Make sure the data collection form you use is clear and easy to use (or that the data collection process is clear and will "work") 4) Make a duplicate copy of your data file and keep it in a safe location 5) Do not rely on other people to collect or transfer your data unless you have trained them and trust them "completely" 6) Plan a detailed schedule of when/where you will be collecting your data 7) Be prepared for anything and allocate 25% to 50% more time in your schedule for unforeseen happenings 8) Cultivate possible sources for your participant pool - try to obtain a sample with less competition; 9) Try to follow up on subjects who missed their testing session or interview - call them back and try to reschedule 10) Never discard original data!!!!
Distributions of greater than _____ elements approach normality
30
What is the magic number for a sample size?
30 people
If the population is around 500 people _______% of the population should be samples If the population is around 1500 people, ________% of the population should be sampled At around 5,000 people, sample size reaches its terminal size, which is _________ people
50% 20% 500 people
One standard deviation above and below the median/median/mode encompasses how much of a normal distribution? Two standard deviations above and below the median/median/mode encompasses how much of a normal distribution? Three standard deviations above and below the median/median/mode encompasses how much of a normal distribution?
68% 94% 96%
What is a continuous variable? What is a discrete variable?
A continuous variable is one that can assume any value along some underlying continuum; A discrete, or categorical, variable is one with values that can be placed only into categories that have definite boundaries.
What is the most important thing to remember about protection from harm, and what's the general rule that applies?
Above all, participants should be protected from physical and/or psychological harm As a general rule, the risk involved in participating in a study should not be appreciably greater than the normal risks of day-to-day living!
What's the difference between confidentiality and anonymity?
Anonymity- records can not be linked with names Confidentiality - anything that is learned about a participant is held in the the strictest confidence
When is concurrent validity established? When is predictive validity established?
Concurrent validity is established when the scale discriminates individuals who are known to be different, that is, they should score differently on the instrument Predictive Validity indicates the ability of the measuring instrument to differentiate among individuals with reference to a future criterion
Give an example of a continuous variable. Give an example of discrete variable
Continuous - your weight (the decimals can go on forever) Discrete- how many cars are in a parting lot
What are the two types of variables?
Continuous vs. discrete
What are the 4 major steps in sampling
Define the population; Determining the sampling frame; Determining the sampling design; Determining the sample size;
What is simple random sampling?
Each member of the population has an equal and independent chance of being selected to be part of the sample
What is the important part about simple random sampling?
Equal and independent. equal because there is no bias that one person will be chosen rather than another and independent because the choice of one person does not bias the researcher for or against the choice of another.
How does systematic sampling work?
Every kth value is chosen; K = size of step = size of population/size of sample
What are the 4 sources of data
Focus groups; Interviews; Databases; and Experimental designs!
We want to generalize the results of a study from a _______ to a __________
From a sample to a population
If you're emailing a survey, what should you do to the number of people you send the survey to?
Increase by 40-60% to make up for non responders
What are 4 things you can do to increase reliability?
Increase the number of items or observations; Eliminate items that are unclear Standardize the conditions under which the test is taken Moderate the degree of difficulty of the tests Minimize the effects of external events (e.g., Spring vacation) Maintain consistent scoring procedures
How big should a sample size be?
It should be big enough to help answer the research question, but not so big that the process of sampling becomes uneconomical and inefficient!
How does systematic sampling compare to simple random sampling?
Less unbiased because systematic sampling reduces the chances of certain participants being selected;
Define interval measurement. Interval measurement not only groups but aslo measures. What does it measure? What does interval scale show us?
Lets us measure the distance between any points on the scale; The interval scale not only groups individuals according to certain categories and taps the order of these groups, it also measures the magnitude of the differences in the preferences among the individuals; Put simply, using an interval scale we can tell the difference between points along a continuum!
What are the 3 measurements for central tendency?
Mean, median, mode
Which levels of measurement do mean median and mode fall under?
Mode- nominal Median - ordinal Mean - interval or ratio
If a test is reliable is it inherently valid and vice versa?
No!
What are the 4 types of measurement? How does the scale flow?
Nominal, Ordinal, Interval, and Ratio degree of sophistication to which the scales are fine-tuned increases progressively as we move from the nominal to the ratio scale
When can a researcher use results from a sample to make inferences about a population?
Only when the sample is truly representative of the population
What does it mean that you can't use coercion? How does this apply to job and school obligations that require your participation in a study?
People should not be forced, for whatever reason, into participating in a study Yet many students must participate as a course requirement - If they do not want to participate, then an alternative way to fulfill a course or a job requirement should be provided
What are the 4 categories ethical considerations fall into?
Protection From Harm; Informed Consent; Right to Privacy; Honesty with Professional Colleagues.
What is a variable?
Quantity that has a changing value
What does a bell shaped curve/normal distribution represent?
Represents how variables are distributed
What must researchers do to make sure their informed consent is ethical? What's the most thing to tell participants?
Research participants should be told the nature of the study to be conducted and given the choice of either participating or not participating; They should be told that, if they agree to participate, they have the right to withdraw from the study at any time Most importantly, any participation in the study must be strictly voluntary.
What two things does the ethical consideration of Honesty with Professional Colleagues entail?
Researchers must report the findings in a complete and honest fashion; Under no circumstances should a researcher fabricate data to support a particular conclusion, o matter how seemingly noble that conclusion may be.
Name 4 of the 6 general rules applying to ethical research. (Last slide of power point)
Sharing Benefits Ensuring High Ethical Standards Publish all reports using group data (when possible) rather than individual data If you suspect that the treatment may have adverse effects = use a small, well informed sample The researcher is also responsible for ensuring ethical practices Researchers must respect a participant's choice to withdraw and must not coerce the subject to return the study
What are threats to external validity called?
Subject effect
Give an example of interval measurement
Temperature
What does the central limit theorem dictate? How big must our samples be for this to work? What's an essential component of the central limit theorem?
The Central Limit Theorem dictates that regardless of the shape of the distribution (normal or not) of the population, the means of the samples selected from the population will be normally distributed - The sample sizes must be greater than 30 for this to "work". - An essential component of the Central Limit Theorem is that the average of your sample means will be the population mean
When is a larger sample needed to reflect the population accurately?
The amount of variability within groups is greater, and The difference between the two groups gets smaller!
What is measurement?
The assignment of values to outcomes
What do you use to test reliability? Why?
The correlation coefficient - "r". For repeated test administrations, the more similar the scores, the higher the r, so the more reliable it is
What are 2 of the 4 reasons for using samples?
The economic advantage of using a sample in research obviously, taking a sample requires fewer resources than using the entire population A sample may provide you with needed information quickly There are some populations that are so difficult to get access to that only a sample can be used Qualified and expert staff for different purposes, highly qualified and expert staff may be required which could be sometimes almost impossible.
Define non-probability sampling strategy.
The elements in the population do not have any probabilities attached to their being chosen as sample subjects
The _____ the sample, the _______ the sampling error
The larger the sample the smaller the sampling error
All research must go through an Internal Review Board to maintain ethical standards. What kinds of things is the IRB looking to make sure you included in your briefing to participants?
The purpose of research Who you are What you're doing How long they will be involved An offer to withdraw from the experiment at anytime for any reason Potential benefits to them as well as society Potential harm or risks for discomfort to them An assurance the results will be kept in strictest confidence How they can get a copy of the results And how you can be reached should anybody have questions.
What is the most important concern with right to privacy? How is this maintained?
There should be no way that anyone other than the researchers that can match the findings of a study with a specific participant! Usually ensured through the use of code numbers!
How does sampling work for groups less than 100 people?
There's no point to sampling groups this small. Just survey the whole population
What do descriptives statistics allow for?
They allow the researcher to get an accurate first impression of what the data might look like
How does cluster sampling work?
Units of individuals are selected, rather than individuals themselves! 1) The target population is divided into clusters 2) Then a random sample of each cluster is drawn. (they might choose clusters 2 and 5 to use in the sample)
How do you decrease the likelihood of making a type II error? (3 things)
Use as a large sample size as reasonably possible Maximize the validity and reliability of your measures Use parametric rather than no-parametric statistics whenever possible
What are inferential statistics used for? What are they based on?
Used to infer something about a population from which the sample was drawn based upon the characteristics of the sample based on the assumption that one can accurately select a sample so as to maximize representativeness!
What are the 3 aspects of validity?
Validity refers to the results of a test, not to the test itself. We talk about validity only in light of the outcomes of a test Just as reliability (although validity is not easily quantified), validity is never a question of all or none. The results of a test are valid or not valid The validity of the test results must be interpreted within the context in which the test occurs
Give an example of ratio measurement
Weight or speed
When do we use probability sampling?
When the elements in the population have a known, nonzero chance of being chosen as subjects in the sample
What is a type I error ?
When we erroneous conclude that a result was not due to chance when in fact it was due to chance-when we incorrectly reject the Null hypothesis
When is debriefing required?
When you design a study (experiment) in which on group of participants is asked to do something for a reason (specific training) other than which they are told - When the experiment is completed it is your responsibility to inform them that they have been deceived to some extent for the purpose of the experiment
Give an example of quota sampling.
You have a group with people and you need all males over 50 in your sample so you pick all the men above 50 in the group infront of you
What is validity?
accuracy - the extent to which the instrument measures what it is supposed to measure.
What is reliability?
consistency of measurement- occurs when a test measures the same thing more than once and results in the same outcomes
What is a cluster?
groups of occurrences that happen together
What is the range?
indicates the spread of the data from lowest to highest.
What does purposive sampling mean?
instead of obtaining information from those who are most readily or conveniently available, it might sometimes become necessary to obtain information from specific groups
What is criterion validity and how can it be established?
is established when the measure differentiates individuals on a criterion it is expected to predict; This can be done by establishing concurrent or predictive validity
What is the median?
is the numerical center for a dataset, with exactly as many scores above it as below it
What is the mode?
is the single number or score that occurs most frequently.
What is quota sampling?
means to take a very tailored sample that's in proportion to some characteristic or trait of a population; It selects respondents in the same proportions that they are found in the general population, but not in a random fashion
Define ratio measurement. What does it posses ?
not only measures the magnitude of the differences between points on the scale but also taps the proportions in the differences; Ratio scale is the 4th level of measurement and possesses a zero point or character of origin!
What is nominal measurement? List 3 of the 6 defining factors for nominal measurement
one that allows the researcher to assign subjects to certain categories or groups; They differ in quality rather than quantity Observations can be placed into one, and only one, category Solely qualitative Numbers can be used, but they have no intrinsic value; Categories are mutually-exclusive If numbers are used as values, they have no meaning beyond simple classification
What is convenience sampling?
refers to the collection of information from members of the population who are convenient available to provide it
What is a sampling error?
refers to the statistical error occurred when the subset of the population (sample) deviates from the true characteristics, attributes and behavior of the total population
What is content validity and what does it ensure?
simplest, most straightforward type of validity! It ensures that the measure includes an adequate and representative set of items that tap the concept / construct of interest
What do descriptive statistics describe?
some of the characteristics of the distribution of the scores researchers have collected, such as the average score on one variable or the degree that one score varies from another
What is standard deviation?
the average amount that each of the individual scores varies from the mean of the set of scores
Define objectivity
the belief that their observations should be influenced as least as possible, ideally not at all- by their own perceptions, impressions, and biases
What it variability?
the degree of "spread" or dispersion that characterizes a group of scores; The degree to which a set of scores differs from some measure of central tendency, most often the mean
What does the central limit theorem state?
the distribution of sample means approximates a normal distribution (also known as a "bell curve"), as the sample size becomes larger, assuming that all samples are identical in size, and regardless of the population distribution shape IF THE CENTRAL LIMIT THEOREM IS NOT TRUE WE CANT USE INFERENTIAL STATS
What is construct validity?
the extent to which the results of a test are related to an underlying set of related variables. It links the practical components of a test score to some underlying theory or model of behavior
Define ordinal measurement. How does this compare to nominal measurement?
the ordinal variables describes variables that can be ordered along some type of continuum -Not only categorizes the variables in such a way as to denote differences among the various categories, it also rank-orders the categories in some meaningful way! With an ordinal scale of measurement, we can think in terms of the symbols > (greater than) or < (less than)
What is the mean?
the sum of a set of scores divided by the number of scores
Define plagiarism.
the use of another's original words, arguments, or ideas as thought they were your own, even if this is done in good faith, out of carelessness, or out of ignorance Purposefully misrepresenting someone else's work and plagiarism are fraud
The larger the standard deviation, the more __________ the set of scores
variable
What is a type II error?
we might conclude that a result is due to chance when in fact it is not; In such a circumstance, we have failed to reject the null hypothesis that actually is false
How does sampling error happen?
when the sample selected from the population differs from the actual attributes of the target population,
