Midterm Flashcards
reinforce basic research concepts
Operational Definition_1
Defines something (e.g. a variable, term, or object) in terms of the specific process or set of validation tests used to determine its presence and quantity.
Operational Definition_2
Operational definitions are also known as indicators, they help social scientists continue to move from a broad but somewhat refined conceptual definition, to a more specific definition that they will use to form their research question.
Conceptual Definition
a working definition a researcher uses as a concept.
Elements of a good research question
Should be the result of an observation, not an ethical/procedural question. Should identify variables and the relationship and/or difference. Cause & effect
How to identify a bad research question?
Vague constructions or broad definitions. It is difficult to identify the variables and/or the relationship.It comments about the topic and or the variables.Value questions not observable. General topics. Provides some opinion/judgement about the topic,
What is the purpose of the IRB?
International review boards are responsible for making sure that the benefits to society outweighs any potential costs to participants and that the procedures used in the research methodology include adequate safeguards to protect the identity, safety and general well being of the participants.
Which are the ethical research principles contained in the Belmont Report?
a) Respect for the person: recognizes that people are autonomous individuals and have the right to make decisions for themselves. If those individuals cannot make informed consent, they are entitled to be protected and it is the researcher obligation to ensure they are protected.
b) Principle of beneficence: ensures the research does not harm the participants and the researcher works to maximize the social, individual and/or scientific benefits of the research wile minimizing any potential harm.
c) Principle of justice: the benefits or burdens of the research are distributed equally among the selection of subjects.
How Deduct Reasoning works?
Works from general to specific. Formally it starts from a theory, generates hypothesis, observes reality against the hypothesis, performs observation and develops conclusions that will enrich the theory.
How Induct Reasoning works?
From specific to general. Starts from an Observation. It generates a Hypothesis as explanation of the observation. Created a Theory
What is an (IV) Independent Variable?
Variable manipulate by the researcher.Variable that is producing the change in the dependent variable – the cause. Experimental research – researcher can manipulate this variable- e.g control groups/placebo. Non-experimental research – interest on IV but cannot be manipulated.
What is a (DV) Dependent Variable?
Variable experimenting the effect of the IV manipulation. Outcome the researcher is interested to study – the effect. Whatever is measure by the operational definition.
What is a (EV) extraneous Variable?
Variables that affect the relationship in the variables under study.All variables that may affect the results.
Describe Descriptive Statistics
Univariate statistics – statistics that summarize a sample or population one variable at a time. The technique produces measures of central tendency and dispersion which represents how the values of the variables in the sample or population. Summarizing the sample of the scores you have actually measured. Only refer to sample statistics.
Describe Inferential Statistics
Generalizes the statistics obtained from a sample to the general population to which the sample belongs. The measures of the population are termed as parameters. There is always some uncertainty compared to the real values of the population. You are suing the statistics of the sample to infer (assume) or estimate the corresponding population parameters. Generalizing about the population of interest.
What is Experimental research?
Variable control and manipulation of the IV and extraneous variables. What cannot be controlled, can be randomize. Group assignment Time order: pre-test and post-test.
What is Non-Experimental research?
Simple measurement, no variable manipulation. Some statistical controls involved.
Characteristics all measurements
exhaustive and mutually exclusive
What exhaustive means in a measurement characteristic?
There is an answer for every possible characteristic of the variable.
What mutually exclusive means in a measurement characteristic?
There is only one answer per people (measurement)
What are the characteristics of the nominal measurements?
Exhaustive and Mutually Exclusive
What are the characteristics of the ordinal measurements?
Exhaustive + Mutually exclusive + Ranked. Attributes or values can be logically ranked.
Example of nominal measurements
Gender, yes/no question, sport list (football, basketball, soccer, gold, swimming, other).
Example of ordinal measurements
Likert scale: always/often/usually/seldom/never. Salary brackets.
What are the characteristics of the Interval measurements?
Exhaustive + Mutually exclusive + Ranked + Intervals that have fixed quantifiable meaningful distances between them. Imply scale creation or index and a ranking question.
Example of interval measurements
IQ normally ranked between 50-150. In this case there is no real value for zero
What are the characteristics of the Ratio measurements?
Exhaustive + Mutually exclusive + Ranked + Intervals that have fixed quantifiable meaningful distances between them + have a true zero point! Zero is meaningful and real.
Example of ratio measurements
number of welfare payments received? 0 (zero) means never received a welfare payment. Years of education, years of experience, drinks a week.
Mean definition
Arithmetic average. Sum of the measurements (set) divided by the number of measurements.
Median definition
It’s the value in the middle of the range of the sample/population. The number or score that divides the distribution into equal halves. 50th percentile. Must first rank the order of scores.
Mode definition
It is the most frequently occurring score in a distribution.
In a normal distribution, what is the relationship between the mean, mode and median?
They are the same mean=mode=median
List reason for a skewed (not normal) distribution
Extreme values or outliers Overlap of two or more processes Insufficient date discrimination Sorted data Sorted bottle volume data Data follows a different distribution
What is the formula for the deviation scores?
X (measurement) – M (mean)
Definition of variance
A single number that represents the total amount of variation in a distribution. Is the mean of the sum of all the squared deviation scores (sum of squares).
S^2 = Σ (Xi – M)^2 / N (or N-1…we’re using N-1)
Definition of the standard deviation SD
(represented by the Greek letter sigma, σ) – is a measure that is used to quantify the amount of variation or dispersion of a set of data values.
SD = √s^2
In a normal distribution, how much (%) of the measurements are included at +- 1 σ (standard deviation) from the mean?
68.2% of the measurements fall into plus or minus 1 standard deviation from the mean.
What is a z-score?
Z-scores convert raw scores into a standardize measure which allows for the comparison across distributions. Where the score falls relative to the mean.Z-scores tells in std dv units, how far the mean of the distribution score falls.
How do you calculate a z-score?
A z-score (aka, a standard score) indicates how many standard deviations an element is from the mean. A z-score can be calculated from the following formula.
z = (X - μ) / σ
where z is the z-score, X is the value of the element, μ is the population mean, and σ is the standard deviation.
What is statistical significance?
Also known as statistically significant result, is attained when a p-value is less than the significance level.
Significance level definition
Significance level is the degree of probability of error we accept in a test
What means that a result was statistically significant?
What is the probability that what we think is a relationship between two variables is really just a chance occurrence?
The null hypothesis is rejected if the p-value is less than the significance or α level. The α level is the probability, p value, of rejecting the null hypothesis given that it is true (type I error) and is most often set at 0.05 (5%).
5% (or less) doubt/uncertainty in the results or we are 95% confidence about the results.
Difference between random sampling and random assignment
Random sampling is the aleatory selection of measurements/items/people from a population. Random assignment is the creation of groups in our sample
Main Properties of a normal distribution
- It is bell shaped. When approaching the axis, it is extreme but it never touches it.
- It is symmetrical around the mean of the distribution
- If a set of observations are normally distributed, then mean-median and mode are the same.
- The normal curve can be specified completely once the mean and the standard deviation are knowen
- The area underneath the curve is directly proportional to the relative frequency of observations.
What is the difference between descriptive and inferential statistics?
Descriptive statistics enable us to summarize the essential characteristics of a group of scores. Inferential statistics enable us to infer, with some degree of error, the characteristics of the population from a sample.
Define Random sampling method
The sampling is the method that enable us to approximate the selection of a representing sample.
Define sampling distribution
Enables us to handle the error that is inevitably made when inferring a population from a sample
Define random sample
a sample in which every member of the population has equal likelihood of being included. Events are independent.
Define random sampling without replacement
Once chosen, score, event or participant cannot be returned to the population to be selected again.
Define random sampling with replacement
Once chosen, score, event or participant can be returned to the population to be selected again.
Why random sampling without replacement is preferred in behavioral sciences?
Because we do not want the same person to appear more than once in a group.
As the size of the sample increases, the sample mean resembles more the population mean and the error ….
in estimating the population mean from the sample mean become ls less.
Central Limit Theorem
Approximation to normal becomes increasingly closer as the sample size increases.
Another way to say “our results are significant at p is ….
“we are 95% confidence in generalizing these results to the population”
