Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
48 Cards in this Set
- Front
- Back
|
What are characteristics of correlational research? |
(2 variables are observed to see whether there is a relationship) observation in a natural state, no manipulation of variables, does not explain the cause and effect mechanism of the relationship. |
|
|
What are characteristics of an Experiment?
|
random assignment to treatment groups. establishes a cause and effect relationship between two variables. methos is inteneded to show that changes in one variable are caused by changes in the other variable. Must:
1)the researcher manipulates one of the variables (independent variable). a second variable is observed to determine whether or not the manipulation causes changes to occur. 2) the researcher must exercise some control over the research situation to ensure that other, extraneous variables do not influence the relationship being examined |
|
|
What are advantages relative to correlational research? |
can determine causation |
|
|
What is random assignment?
|
each person has an equal chance of being assigned to each of the treatment conditions. ensures equality of groups b4 study starts
|
|
|
What are advantages versus non-random assignment? |
advantage is to distribute the participant characteristics evenly between 2 groups. can also be used to control environmental variables. |
|
|
What is random sampling? |
Every person or entity in the population has an equal chance of being selected for the sample: to get approximation of representative sample |
|
|
What is a representative sample? |
Sample has individuals who vary on attribute n same way as in population, difficult to get a representative sample because we don’t know distribution of all relevant variables in the populations, “not what researchers typically do” ( A subset of a statistical population that accurately reflects the members of the entire population.) |
|
|
What are independent variables |
is the variable that is manipulated by the experimenter |
|
|
What are dependent variables? |
is the variable that is observed for changes in order to asses the effect of the treatment. |
|
|
What is a confounding variable? |
an unexpected and uncontrolled variable that upsets the experiment so you can no longer say with certainty that the change in the independent variable did in fact cause the change in the dependent variable.(is an extraneous variable in astatistical model that correlates (directly or inversely) with both the dependent variable and the independent variable.) |
|
|
What is a population? |
the set of all the individuals of interest in a particular study. |
|
|
What is a sample? |
a set of individuals selected from a population, usually intended to represent the population in a research study. |
|
|
What are characteristics of Populations called? |
parameters( a value usually a numerical value that describes a _________. a parameter may be obtained from a single measurement, or it may be derived from a set of measurements from the ______. |
|
|
What are characteristics of samples called? |
Statistics( a value usually a numerical value, that describes a _______. A statistic may be obtained from a single measurement or it may be derived from a set of measurements from the _____ |
|
|
What are descriptive statistics? |
are statistical procedures that are used to summarize, organize, and simplify data: frequency, mean, median, mode, range, standard deviation: very concrete |
|
|
What are inferential statistics? |
Allow us to use sample data to make generalizations about the populations form which they were selected: z,t,f |
|
|
What is sampling error? |
Discrepancy between sample statistics and true underlying population parameter
|
|
|
When does sampling error occur? |
it the discrepancy, or amount, of error that exists between a sample statistic and the corresponding population parameter. |
|
|
What is a construct? |
are internal attributes or characteristics that cannot be directly observed but are useful for describing and explaining behavior. |
|
|
What is an operational definition |
identifies a measurement procedure(a set of operations) for measuring an external behavior and uses the resulting measurements as a definition and a measurement of a hypothetical construct.
*** 2 components first it describes a set of operations for measuring a construct. Second it defines the construct in terms of the resulting measurements. |
|
|
What are characteristics of the four types of scales of measurement: Nominal, Ordinal, Interval, Ratio?
|
Nominal - consissts of a set of categories that have different names; example male or female
Ordinal - Observations are ranked in terms of size/magnitude.** do not allow you to determine the magnitude of the difference between two individuals.(shows who has more but not how much more) Example: drinks small, medium, large
Interval - equal intervals between numbers reflect equal differences in magnitude. ***Ratios of magnitudes are not meaningful.
Ratio - equal intervals between numbers correspond to equal difference in attribute: there is an absolute zero, physical variables often; example height, number of students in class, counts, etc. |
|
|
What is the difference between discrete versus continuous measurement? |
Discrete: numbers are indivisible separate categories. An example of discrete measurement is the number of children in a family. Continuous: not limited to fixed set of categories- always rounding. An example of continuous measurement would be time taken to complete task. |
|
|
In frequency tables: what do f, p, cf, cp indicate. Know how to compute and interpret each. |
f is the frequency of a value in a data set, p is the proportion of a value in a data set, cf is the cummalative frequency of each value and all values below in a data set, cp is the cummalative proportion of each value and all values below in a data set. Compute frequency by counting how many times a number is represented in a data set. Compute Proportion by f/n where n is the total of the numbers in a data set Compute cummalitive frequency by counting how many times a number is represented along with all values below the value requested. Compute cummalitive proportion by cf/n
|
|
|
Know how to make a grouped frequency table – and how to interpret f, p, cf, and cp for a grouped table.
|
Standard frequency table will have the 5 columns: from left to right score, frequency, proportion, cf, cp Grouped Frequency table is the same except column 1 is the interval, column 2, frequency of all numbers within interval, etc… Interval width rule: low end of lowest interval should be the number that is closest to the lowest observed value and is evenly divisible by interval width. cf and cp in grouped tables, the number refer to the upper end of the interval. Only works with ordinal, interval, and ratio
|
|
|
What is the goal for a measure of central tendency? |
to find the single score that is most typical or representative of the entire group. |
|
|
What do the 3 measures of central tendency (mean, median, mode) each measure? |
Mean measures the average of all data in the data set, mean of population = and mean of sample = M
Median measures where the middle of the data set lies
Mode measures which value is the most frequent value in a data set.
|
|
|
How are they interpreted?
|
Mode - Most frequent or typical score, only measure of Central Tendancy for nominal score, most sample dependent, mode is most variable from sample to sample
Mean - most stable from sample to sample, measure of Central Tendancy for interval or ratio
Median - Ordianal, interval, or ratio. Interpreted as the 50th percentile
|
|
|
How are they computed?
|
Mean N/N Median PG 55
|
|
|
Which one is “best” overall? (that is, which one is most stable from sample to sample?) |
mean |
|
|
Which one is best if there are extreme values (outliers)?
|
median |
|
|
Where do the mean, median, & mode fall in skewed distributions?
|
In a positively skewed distribution: Mean>Median>Mode
In a negatively skewed distribution: Mode>Median>Mode |
|
|
What is skewness? What is kurtosis?
|
Skewness is the departure from symmetry. Kurtosis is how pointy or flat a distribution is.
|
|
|
What is the goal for a measure of variability? |
The goal is to find a measure of variability that tells (with single value) how spread out a set of scores are.
1) they tell us how meaningful central tendency is 2)they help identify outliers 3)they can be interesting stats in themselves |
|
|
***What are homogeneous versus heterogeneous scores? |
Homogeneous:They relate to the validity of the often convenient assumption that the statistical properties of any one part of an overall dataset are the same as any other part. In meta-analysis, which combines the data from several studies, homogeneity measures the differences or similarities between the several studies
Heterogeneous:Ideally, the studies whose results are being combined in the meta-analysis should all be undertaken in the same way and to the same experimental protocols: study heterogeneity is a term used to indicate that this ideal is not fully met. |
|
|
How do you compute the range? |
upper real limit of the highest score - lower real limit of the lowest score = range
|
|
|
What are its good and bad points? |
Bad points: Very strongly affected by outliers and Very insensitive to distributions of scores.
|
|
|
What is a Sum of Squares? |
SS, is the sum of squared deviations
definitional formula: SS=∑(X-µ)^2
computational formula: SS= (∑X^2)-[(∑X)^2/N)] |
|
|
What does a variance measure? |
mean squared deviation. Variance is the mean of the squared deviation scores.
Sum of squared deviations/Number of scores
Variance: SS/N
Pop variance=σ^2=SS/N |
|
|
How do you compute the variance for a population? |
Pop variance=σ^2=SS/N |
|
|
How do you compute a variance for a sample? |
s^2=SS/(n-1) |
|
|
How is a standard deviation interpreted? |
Is the square root of variance
√SS/N
Population Standard Devaition= σ=√SS/N
Sample Standard deviation=s=√(SS/n-1) |
|
|
*** What is the effect of outliers with the range? |
outliers define range |
|
|
*** What is the effect of outliers with the standard deviation? |
outliers pull up SD |
|
|
Interpretation of standard scores. |
Shape of a distribution of standard scores is exactly the same as the shape of raw scores.
|
|
|
**** Know what data transformations are appropriate for counting data & reaction time data
|
square root used for counting, log(x) used for reaction time |
|
|
*** Know how to find a probability in a very simple context – e.g., a uniform distribution
|
... |
|
|
Characteristics of the normal distribution |
... |
|
|
**** Know how to compute probabilities in the normal distribution with a standard normal table.
|
... |
