Exam 2 Flashcards
What are the two types of Variables?
Independent Variable (IV) and Dependent Variable (DV)
What is a variable?
construct that takes on different values
What is an Independent variable?
the variable that is thought to influence changes in another variable
What is a Dependent variable?
the variable thought to be changed by another variable
What is the definition of causal relationships?
the assumption that changes in the independent variable cause observed changes in the dependent variable
What is the definition of Recursive causal model?
a variable relationship where one variable influences another but not the other way around
What is the definition of Nonrecursive causal model?
a variable relationship where a variable can be both the cause and effect
What is the definition of non-causal relationships?
the assumption that variables are associated but don’t cause changes in the other
What are Ordered or continuous variables?
variables that can be assigned numerical values such as age, weight, temperature and income
What are Nominal or Categorical variables?
variables that can be differentiated only on the basis of type such as gender and race
What is main effect?
effects due to multiple independent variables working alone to affect the dependent variable(s)
What is interaction effect?
effects due to multiple independent variables working together to affect the dependent variable(s)
What are Research Questions?
formal question posed to guide research
What are 2 things research questions can accomplish?
describe communication behavior and relate communication behavior to other variables
What does a descriptive question do?
Attempt to categorize a concept and measures how it varies in type or amount
What is an example of a descriptive question
What factors impact writing assessment practices of writing faculty?
What does a relationship question do?
measures relationships between variables
What is an example of a relationship question
What is the relationship between years of teaching experience and level of confidence in assessing writing?
What is a hypothesis?
predicts a relationship between independent and dependent variables
What are the 2 types of relationships between variables
positive and negative relationship
What is a Positive Relationship?
This type of variable relationship shows that an increase in an independent variable increases the dependent variable. This is also known as direct relationship
What is a Negative Relationship?
This type of variable relationship shows that an increase in an independent variable decreases the dependent variable. This is also known as inverse relationship
What is a one-tailed hypothesis?
a hypothesis that specifically predicts the specific nature of the relationship
What is an example of a one-tailed hypothesis?
I predict that the longer years of experiences a teacher has the more confident they will be in assessing students’ writing. This implies a positive influence and relationship between the 2 variables.
What is a two-tailed hypothesis?
a hypothesis that does not specifically predict the nature of a relationship between variables
What is an example of a two-tailed hypothesis?
I predict that years of experience will have an impact on levels of confidence.
What is the form and example of a nominal independent variable question?
-Is there a difference between a and b in relation to C?
-Is there a difference between teachers with 1 year and 5 years of teaching experience in relation to what they assess in student writing?
What is the form and example of a nominal independent variable hypothesis?
-A is greater on C than B. or A is lower on C than B.
-Teachers with 5 years of experience have more confidence than teachers with 1 year of experience. Or Teachers with 1 year of experience have less confidence than teachers with 5 years of experience.
What is the form and example of an ordered independent variable question?
-Is there a relationship between x (IV) and y (DV)?
-Is there a relationship between years of teaching experience and confidence?
What is the form of an ordered independent variable hypothesis?
-There is a (positive/ negative) relationship between x and y.
-There is a positive relationship between years of teaching experience and confidence.
What is Statistical data analysis?
the process of examining what quantitative data means to researchers
What is Statistics?
numeral indicator assigned to a set of data
What is Descriptive statistical data analysis?
an approach used to create simple descriptions about the characteristics in the data set
What are 3 ways to describe data?
-Create summary statistics ⇒ numerical indicators that summarize the data in terms on mean or variance
-Convert raw scores into standard scores
-Create visual displays of data
What 2 ways are Inferential statistical data analysis used?
-To estimate the characteristics of the population samples
-To test for differences in the relationships among variables
What are the 3 central tendency?
mode, median, and mean
What is mode?
indicates the score or value that occurs most frequently
Pros of using mode?
very easy to determine and great with nominal data
Cons of using mode?
not very useful when using ordinal, interval, or ratio data; also there could be multiple modes
What is Bimodal?
when there are 2 modes (a.k.a. 2 variables scores the same high amount)
What is Multimodal?
when there are 3+ modes (a.k.a 3+ variables scored the same high amount)
What is median?
divides data exactly in half
Pros of using median?
describes the center point of ordinal, interval, and ratio data; looks are more variables than mode; not affected by outliers
What is the outlier effects?
when there is an extreme score, it can impact mean
What is mean?
the average score of data rounded up to 2 decimal points (9.285 = 9.29)
Pro of using mean?
the most effective measure of central tendency of data
Con of using mean?
affected by extreme scores
What are Measures of Dispersion?
report how much vary from each other or how they are spread out from the center point of data set
What are the 3 measures of dispersion?
range, variance, and standard deviation
What is Range?
reports the distance between the highest and lowest scores in a distribution
How is the range calculated?
by subtracting the lowest number from the highest number also called the extreme values
Pros of range?
can help show how spread out the data is and if the variables studied varied
Con of range?
affected by extreme scores
What is Lowspread?
the range of values between the median and the lowest score
What is Highspread?
the range of values between the median and the highest score
What is Interquartile range?
the range of values between the 25% and 75% percentile
What is Semi-interquartile range?
the total calculated after the interquartile range is divided in half
What is Variance?
the average distance of the scores in a distribution in square units
What is Deviation score?
the amount one score differs from the mean
What is the variance formula?
Σ(x-ẋ)2/ N
Σ = stands for…
sum of scores
X = stands for…
score
Ẋ = stands for…
mean
N = stands for…
total # of scores
What are the Steps for calculation variance?
- Get mean
- Subtract each score from the mean
- Square the difference
- Add them all up
- Divide by the total # of variables
What is standard deviation?
average from the mean in original measurement units
What is the Standard deviation formula?
√variance ⇒ you take the square root of the variance score
What are Frequency distributions?
tally of the number of times particular values on a measurement scale occur in a data set
What are Frequency tables?
a visual display in table form of the frequency of each category on a scale
What are Inferential statistics?
statistical procedures that allow you to make claims about a population based on sample characteristics
What are the purposes of using inferential statistics?
-Estimation
-Significance testing
Whats is Estimation in inferential statistics?
is used to generalize the results obtained from a sample to its parent population
Whats is Significance testing in inferential statistics?
examines how likely differences between groups and relationships between variables occur by chance
What are the Basic Assumptions when using Inferential Statistics?
-Make sure you have a random selection in the sample
-Variable should be “normally” distributed in the population
What is the The Normal Curve?
-chance events in large quantities tend to distribute themselves in the form of a bell curve
-Theoretically mean, median, mode all occur in the same place
-The sides never touch the base lines
-Probability
What are the percentages that fall between each standard deviation on the normal curve?
-2.1%, 13.5%, 34.1%, 34.1%, 13.5%, 2.1%
-68.2%, 99.4%, 99.7%
How are the standard deviations organized in a curve bell?
(-3, -2, -1, X, +1, +2, +3)
If a sample distribution has a mean of 48 and a standard deviation of 6, what is the probability of obtaining a score from 42 to 54?
A) 14%; B) 68%; C) 5%; D) 98%
B) 68%
If a sample distribution has a mean of 0 and a standard deviation of 10, what is the probability of someone scoring between 0 and 20?
A) 48%; B) 68%; C) 95%; D) other
A) 48%
What is Skewness as it relates to the Normal Bell Curve?
skewness means that there is unequal distribution of data because of extreme scores
What are the names of the 2 basic types of skewness?
Positive skewed distribution and negatively skewed distribution
How is skewness determined?
Skewness is distributed to the side where the extreme score are (left = negative; right = positive)
What does a negative skew mean?
this means most scores are high and there are some extreme scores that are low
What does a positive skew mean?
this means that most scores are low and there are some extreme scores that are high
What is Kurtosis?
height (tall or short) of curve bell tells you how the scores are distributed in the curve bell
What are the 3 basic types of Kurtosis?
leptokurtic, mesokurtic, platykurtic
What is Leptokurtic distribution?
curve is tall ⇒ this tells you that scores are relatively similar
What is Mesokurtic distribution?
curve is normal
What is Platykurtic distribution?
curve is short ⇒ this means that scores are all over the place
What is the null hypothesis?
-this means there is no pattern in the data;
-it is all random;
-it’s all a coincidence
How does the null hypothesis relate to a researcher’s hypothesis (or research question)?
they have to proof it wrong and proof that there is are patterns and relationships
What is the Significance level or p value?
probability that a hypothesis is wrong
What is the industry standard for what researchers should use as a p value in analyzing statistical results?
5% that a researcher is wrong
What are the 3 Steps for significance testing?
-Pose a question and hypothesis
-Do the study and collect data
-Test the null (is there no relationship
How do you test the null hypothesis?
*Set significance level (5% or 0.05)
*Compute calculated value (statistical test is done to test it out)
*Compare calculated to critical value (calculated should be the same or more)
What is a Type I error?
Occurs when researchers reject the null hypothesis and accept a researcher hypothesis when in fact the null hypothesis is possibly true and should have been accepted.
What can you do with your significance level thresholds to prevent a Type I error?
lower the significance level (.01 lowers to 1% chance of committing a type 1 error)
What disadvantages to the type I error remedy?
by lowering the level, it can increase the likelihood of committing a type II level error.
What is a Type II error?
occurs when researchers accept a null hypothesis when it was probably false and rejected their hypothesis
What can you do with your significance level thresholds to prevent a Type II error?
higher the significance level such as .10
What disadvantages to this remedy?
by increasing the level, it increases the chance of committing a type I error.
