- Shuffle
Toggle OnToggle Off
- Alphabetize
Toggle OnToggle Off
- Front First
Toggle OnToggle Off
- Both Sides
Toggle OnToggle Off
Front
How to study your flashcards.
Right/Left arrow keys: Navigate between flashcards.right arrow keyleft arrow key
Up/Down arrow keys: Flip the card between the front and back.down keyup key
H key: Show hint (3rd side).h key
PLAY BUTTON
PLAY BUTTON
70 Cards in this Set
- Front
- Back
|
Hypothesis
|
statement about the proposed relationship between two or more variables.
|
|
Hypothesis Process includes __ steps:
|
Six
1)State the hypothesis 2) Set a level of risk 3) Choose sample size 4) Determine critical value 5) Compute test statistic 6) Accept or reject hypothesis |
|
Descriptive Statistics
|
Summarize or describe data. Do not make inferences about the population.
|
|
Inferential Statistics
|
Make conclusions about the population from data. Make inferences
|
|
When stating the hypothesis, researchers consider two opposing viewpoints
|
Null Hypothesis and Alternative Hypothesis.
|
|
Null Hypothesis
|
States that there is no relationship between the groups or variables.
|
|
Alternative Hypothesis
|
States that there will be a difference between the groups relative to the specific variable examined.
|
|
Alpha
|
The probability of a type 1 error.
|
|
Beta
|
The probably of a type 2 error.
|
|
Power
|
The probability that your research will correctly reject the null hypothesis when it is false.
|
|
How can the critical value be found?
|
Using a table for standard normal distribution and student t distribution.
|
|
The critical value depends on:
|
alpha level and alternate hypothesis.
|
|
Two types of alternative hypothesis?
|
One tailed and Two Tailed
|
|
Test Statistic
|
Statistical Test used to analyze data.
|
|
Distribution
|
A pattern of scores: distribution of a variable provides information about individual cases as well as info about the group of scores.
|
|
Normal Distribution has 3 important characteristics
|
1)Symmetrical and uni modal.
2) Continuous 3) Asymptomatic |
|
Standard Normal Distribution
|
All normal distribution can be converted to a common distribution with the same mean and standard deviation (mean of 0 and standard deviation of one).
|
|
Transformed Standard Scores
|
Z scores include negatives and decimals so you would transform scores into a distribution of standard scores with a mean of 100 and SD of 15.
|
|
Z-Score
|
Standard score. A measure of individual location telling us where individual scores are located within a distribution of scores.
|
|
Negatively Skewed
|
Larger values to the right tail.
|
|
Positively Skewed
|
Large values towards the left tail.
|
|
Kurtosis
|
Measure of peakedness: tells us how fat or thin tails are relative to normal distribution.
|
|
Central Limit Theorem
|
Even if variable is not normally distributed in the population, the sampling distribution will be approximately normal with a large sample.
|
|
Interval Estimation
|
Range of values that you can say with confidence include the population parameter; range of values is confidence interval.
|
|
Student T Distribution
|
Bell shaped, symmetrical, centered on the mean however distribution change as sample sizes change.
|
|
Majority of quantitative analysis in CSD are:
|
Student T Test and ANOVA (these are inferential statistical procedures)
|
|
Related Samples Test
|
Test that matches pre and post test designs for difference between two conditions. Same participants are observed before and after treatment.
|
|
Random Sampling
|
Each member of population has an equal chance of being selected.
|
|
Nonparametric Statistic Example
|
Chi Square Test
|
|
Unrelated Samples Test
|
2 groups of subjects are partcipants. Examine differences between groups by comparing the means.
|
|
Z statistic
|
Statistic that is appropriate for larger samples (more than 30). Based on normal distribution of scores.
|
|
T statistic
|
Statistic that is appropriate for smaller samples (less than 30)
|
|
Leptokurtic
|
Narrower in terms of bell-shaped curve.
|
|
T ratio
|
difference between the means of 2 groups divided by the SED.
|
|
Standard Error of Difference
|
Variability of Scores due to error.
|
|
Nonparametric Test for two Unrelated Samples
|
Mann Whitney U
|
|
Nonparametric Test for Related Sample
|
Wilcoxon Test for Paired Data.
|
|
The most common approach to statistical analysis in CSD research is:
|
ANOVA
|
|
ANOVA outcome is __ Statistic
|
F Statistic
|
|
ANOVA separates Variance into:
|
Within Group Variability
Between Group Variability |
|
Within Group Variability
|
Portion of Total Variance that cannot be explained by research design.
|
|
Between Group Variability
|
Portion of Total Variance that can be attributed to group membership.
|
|
Nonparametric Alternative to One Way ANOVA is:
|
Kruskal Wallis Test
|
|
In Complex ANOVA Procedures, researchers evaluate what effects?
|
Main Effects and Interaction Effects.
|
|
Main Effects
|
Effects of the Variables.
|
|
Interaction Effects
|
Interaction between the variables.
|
|
Significant Interaction
|
One variable is influencing another variable.
|
|
Post Hoc Comparisons
|
Analyze pairs of means for significance.
|
|
Nonparametric Alternative to two-way ANOVA is:
|
Friedman's Test
|
|
Contingency Tables
|
rows by columns, tables used to organize data in chi square analysis.
|
|
Phase 1 of Clinical Outcome Research
|
Exploratory. Tentative Treatment Protocol. Lacking external controls.
|
|
Phase 2 of Clinical Outcome Research
|
Exploratory. Finalizing operational definition, defining population of interest, refining methodology. Exploring treatments effects in terms of extent and maintenance.
|
|
Phase 3 of Clinical Outcome Research
|
testing research hypothesis and answering research question. Study done with larger samples and control group added.
|
|
Phase 4 of Clinical Outcome Research
|
Bridge between research and practice. Going from efficacy in the lab to effectiveness in the clinical setting.
|
|
Phase 5 of Clinical Outcome Research
|
cost benefit ratio, consumer satisfaction, quality of life issues.
|
|
Synthesis Review Approaches
|
Narrative Review and Qualitative Analysis
|
|
Narrative Review
|
Thorough search of pertinent literature. Qualitative analysis of results of past studies. Conclusion based on synthesis of results.
|
|
Quantitative Review
|
Existing Literature is Sufficient in number and type thus often superior to narrative review.
|
|
Quantitative Review Methods
|
Vote Counting Method
Combined Probability Method |
|
Vote Counting Method
|
results of selected studies are placed into categories: positive, negative, nonsignificant. Category with largest population of finding is identifies as supporting/refuting research hypothesis.
|
|
Combined Probability Method
|
Probability included in synthesis, do not quantify size of experimental effects, and do not identify heterogeneity among studies.
|
|
Modern Meta Analysis
|
Effect Size Combined, Overall measure of effect, significance of overall effects.
|
|
Modern Meta Analysis Step 1
|
1) Develop a research hypothesis and eligibility criteria.
|
|
Modern Meta Analysis Step 2
|
Develop a search strategy and choose studies for inclusion.
|
|
Modern Meta Analysis Step 3
|
Convert test statistic to common effect size metric.
|
|
Modern Meta Analysis Step 4
|
Compute cumulative effect and interpret results.
|
|
Moderator Variable
|
independent variable other than the treatment variable that can explain significant amount of variance between studies.
|
|
Statistical Models to represent data
|
Fixed Effects and Random Effects
|
|
Fixed Effects Model and Example
|
Variability of results between studies is due to random variation alone. Randomized Controlled Trials.
|
|
Random Effects Model and Example
|
Variability of results between studies is due to random variation and other confounding variables such as experimenter bias and others. Quasi Experimental Research
|
