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;
64 Cards in this Set
- Front
- Back
Research
|
The application of a specific set of techniques based on what is often called "The Scientific Method"
|
|
Social Scientific Research Steps
|
-Thorough review of what is know (lit review)
-A clear statement of the problem/sub problems -Hypothesis: Making of predictions about what is expected to be observed -After research, the observations and its relationship to the problem and the hypothesis described. -Researcher interprets observations, in light of original idea |
|
Three common variables
|
-Independent:manipulated
-Dependent: affected as result of manipulation on IV -Control: possible confounds that researcher tries to hold constant |
|
Purpose Statement
|
Go find an old one from Dr. Bower
|
|
Hypothesis
|
Null: There will be no significant difference between .............. and ....... in .......
Alternative: There is a significant difference |
|
4 Types of Sampling
|
-Simple Random Sampling
-Stratified Random Sampling -Cluster Sample -Systematic Random Sample |
|
Simple Random Sampling
|
-each item/subject in sample has equal, independent chance of being selected into the sample
|
|
Stratified Random Sampling
|
-Items/subjects divided into parts (grade, age, gender, etc), in each part, each item/subject has an equal chance of being selected into the sample
|
|
Cluster Sample
|
-Parts that go together are researched/studied together (class, town, etc.)
|
|
Systematic Random Sample
|
-A systematic rule of selection/predictable interval is employed (every odd number, every 4th, etc.)
|
|
Terms- Population
|
Contains all subjects having a common characteristic
|
|
Terms- Sample
|
Subset of a population, the subjects that are available to the researcher
|
|
Terms- Random Selection
|
Process of obtaining a sample from a defined population, where everyone has an equal chance of being selected
|
|
Terms- Random Assignment
|
After selection, when researcher divides the subjects into treatment groups
|
|
Threats to Internal validity
|
-History: Long study- events can be extraneous variables
-Maturation: subjects mature -Testing: Pre-post test issues -Statistical Regression: Regression to the mean -Subject Attrition: Drop out's |
|
Treats to External Validity
|
-Multiple-Treatment Interference: administering more than one treatment to same subjects
-Hawthorn (placebo) Effect -Novelty Effect -Experimenter/Rosenthal Effect: Researcher's behavior/appearance effects the subject -Halo Effect: researcher bias |
|
Experimental Research
|
-Researcher must be able to control/manipulate independent variables
-Subjects must be randomly assigned |
|
Solomon Four Group Design
|
Design
4 randomly assigned/selected groups -Two of them are experimental -Two of them are control -First two get a pre and post test, and one of those gets intervention -Second two get only post-test, and one of those gets intervention |
|
Quasi-Experimental research
|
-Only the first of the two criteria listed is met (usually not random assignment)
|
|
Correlational Researcher
|
Looks at relationships among variables
Results conveyed as correlation coefficients (not cause and effect) |
|
Descriptive Research
|
Non-experimental
The researcher only describes what already exists, studying the results of something that has happened already |
|
Action Research
|
Developing new skills/approaches with direct applications for counseling or education
|
|
Outcome research
|
what happens to a client as a result of counseling
|
|
Process research
|
Looks at nature of counseling interview, determines what factors lead to successful outcomes
|
|
AB Design
|
Simple
single subject design baseline(A) and intervention (B) |
|
ABAB design
|
More Complex
|
|
Sociogram
|
technique for studying interaction patterns among peers
|
|
Measurement Scales
|
Nominal: category
Ordinal: Ordered category Interval: Category with orders based on equal intervals Ratio: Has a true zero (lb, in, cents) |
|
Descriptive Statistics
|
Stigmatization of the data
|
|
Types of derived scores
|
-Grade Equivalent (GE)
-Percentile Rank -Standard Scores |
|
-Grade Equivalent (GE)
|
average raw score is given a grade-level value. Cannot tell if a child is actually preforming at a different grade level however
|
|
-Percentile Rank
|
Indicates the percentages of scores that fall at or below a given score
|
|
-Standard Scores
|
z- score
T-score Stanines |
|
z- score
|
Most basic, allows scores from different tests to be compared
-Mean = 0 -sd= 1 |
|
T-score
|
Widely used
-Mean = 50 -sd = 10 |
|
Stanines
|
Standard nine
divides the bell curve into nine (not equal) parts |
|
Types of statistics in tables
|
Frequency (f)
Proportion (p) Percentage (%) |
|
Frequency (f)
|
The number of subjects in a category
|
|
Proportion (p)
|
-ratio of a subgroup to the total group
-expressed as 0.0 to 1.0 |
|
Percentage (%)
|
-the proportion or a subgroup to the total group
-expressed 0% to 100% |
|
Graphs
|
Bar graph/histogram
Frequency polygon |
|
Measures of Central Tendency
|
describing a set of data with a single number (usually the mean)
Mean Median Mode |
|
Mean
|
Arithmetic average of the scores
-Add if the scores and divide the sum by the number of scores |
|
Median
|
The point in a distribution above and below which 50% of the scores fall (the middle)
-put the numbers in order, and find the middle number (if no one middle number, add the two numbers and divide by 2) |
|
Mode
|
Seeing which score occurs most frequently
Bimodel or multi-modal if there is more than one |
|
Measures of Variability
|
Range (R)
Standard Deviation (sd) Variance |
|
Range
|
the difference between the highest and the lowest score in the distribution
-subtract the lowest from the highest |
|
Variance
|
If you have the sd, just square it
-Get the mean -subtract the mean from each of the numbers -square the numbers (so they are positive) -sum the squares -Divide that number by how many there are |
|
Standard Deviation
|
The square root of the variance (positive)
|
|
Measures of relationship
|
The degree of relationship between two variables
-Expressed as a correlation coefficient +1.0 is perfect positive -1.0 is perfect negative 0 means no relation |
|
Pearsons product moment correlation
|
pearsons r
correlations used for interval or ratio measures |
|
Spearman rho
|
for ordinal data
correlations |
|
Skewed distributions
|
negative
positive |
|
Negative Skew
|
pulled in the low direction
tail on left mean is smaller than median |
|
Positive Skew
|
pulled toward the positive side
tail on right mean on positive side |
|
Amount of Skew
|
Mean - median = skew
|
|
what type of distribution do the following numbers represent
11,41,23,10,2,30,7,18,4,12 |
positively skewed
|
|
Inferential Statistics
|
Used to make inferences about larger populations
Generalizing from samples to poplations |
|
Level of significance
|
- .01 (.99 level of confidence) or
.05 (.95 level of confidence) -Says "There is only a 5 or fewer chance in 100 that this study result could be due to error" |
|
Types of error
|
-Type 1: null rejected when when no difference exists
-Type 2: The null is retained when a difference does exist (not as bad, better safe then sorry) |
|
Most common types of inferential statistics
|
Chi square
T-test ANOVA MANOVA ANCOVA |
|
Chi square
|
-normal data
-compares observed frequencies with expected frequencies -Can be sued with study that has only one group of subjects |
|
T-test
|
determines whether there is statistical sig between means from two different groups
-interval and ratio date |
|
ANOVA (and types)
|
Analysis of variance:like multiple t-tests, with three + groups
MANOVA: correlation between multiple iv's and a dv ANCOVA: how a covariate interacts with the dv |