PSY302-300218221
From PsychWiki - A Collaborative Psychology Wiki
TESTS
Two-sample t-test: between (independent)
Definition: Testing the relationship between a categorical independent variable and a continuous independent variable, in which the categorical independent variable is a between-subjects design with two levels.
Application: This study involved testing the best prosthesis for treating osteoarthritis (OA) of the hip in young, highly active patients. The categorical variable is patients with prosthesis. The levels are those treated with hip resurfacing and those treated with custom uncemented stems. The continuous independent variable is the level of patient satisfaction. This makes it a two sample t-test:between.
Two-sample t-test: within (related)
Definition: Testing the relationship between a categorical independent variable and a continuous independent variable, in which the categorical independent variable is a within-subjects design with two levels.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001266
Application: This study concerns "the potential benefits and risks of the use of dual antiplatelet therapy beyond a 12-month period in patients receiving drug-eluting stents...". Because this study used a categorical independent variable of "patients who had received drug-eluting stents and had been free of major adverse cardiac or cerebrovascular events and major bleeding for a period of at least 12 months" and the continuous independent variables of receiving clopidogrel plus aspirin or aspirin alone, it is an example of a two-sample t-test; within.
One-Way ANOVA test
Definition: Testing the relationship between a categorical independent variable and a continuous independent variable, in which the categorical independent variable is a between-subjects design with three or more levels.
Example: http://bjp.rcpsych.org/cgi/content/abstract/196/3/200
Application: This study used the categorical independent variable of women. The three levels of this were: women with recurrent major depressive disorder who had experienced one or more postnatal episodes, healthy women (control group), and women with recurrent major depressive disorder who experienced no postnatal depression. The continuous independent variable was personality/cognitive style. These factors were utilized in a one-way ANOVA test.
Two-Way ANOVA test
Definition: Testing the relationship between two categorical independent variable and a continuous independent variable.
Application: This study measured the angle of a portion of the spine of subjects. The two categorical variables were subjects WITH upper body symptoms and subjects WITHOUT symptoms and the independent variable was the measurement of the angle of the spinal area. Since the study was a measuring the relationship between those variables, it is an example of a two way anova test.
Correlation test
Definition: Testing the relationship between two continuous variables, either of which can be considered the independent or dependent variable.
Example: http://www.reuters.com/article/idUSTRE62759S20100308
Application: In the article, women who drank in moderation had reduced weight. The amount of alcohol is a continuous variable, and weight is a continuous variable. Since the article is about the relationship between those two continuous variables, the article concerns correlation.
Chi-square test
Definition: Testing the relationship between two categorical variables, either of which can be considered the independent or dependent variable.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001282
Application: This study tested the relationship between the two categorical variables of diabetes patients that were receiving simvastatin to receive (1)fenofibrate or (2) a placebo. They investigated whether combination therapy with a statin plus a fibrate, as compared with statin monotherapy, would reduce the risk of cardiovascular disease in patients with type 2 diabetes mellitus who were at high risk for cardiovascular disease. "Baseline characteristics were compared between study groups with the use of the chi-square test."
Concepts
Standard Score
Definition: A score obtained by using the transformation z=(X-XBAR)/S
Example: http://www.beavertonvalleytimes.com/news/story.php?story_id=126767362743259400
Application: This article shows a standard score being used in a study to evaluate the efficacy of milkshakes as a food substitute for oncology patients.
Confidence Interval
Definition: A range of score values expected to contain the value mu with a certain level of confidence.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001282
Application: This study tested the relationship between the two categorical variables of diabetes patients that were receiving simvastatin to receive (1)fenofibrate or (2) a placebo. They investigated whether combination therapy with a statin plus a fibrate, as compared with statin monotherapy, would reduce the risk of cardiovascular disease in patients with type 2 diabetes mellitus who were at high risk for cardiovascular disease. The annual rate of the primary outcome was 2.2% in the fenofibrate group and 2.4% in the placebo group (hazard ratio in the fenofibrate group, 0.92; 95% confidence interval [CI], 0.79 to 1.08; P=0.32). This states that the researchers are 95% confidant that the range of scores above contains the value mu.
Parametric Test
Definition: A statistical test involving hypotheses that state a relationship about a population parameter.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001266
Application: This study concerns "the potential benefits and risks of the use of dual antiplatelet therapy beyond a 12-month period in patients receiving drug-eluting stents...". It found that the "use of dual antiplatelet therapy for a period longer than 12 months in patients who had received drug-eluting stents was not significantly more effective (significantly different) than aspirin monotherapy in reducing the rate of myocardial infarction or death from cardiac causes".
Nonparametric Test
Definition: A statistical test involving hypotheses that do not state a relationship about a population parameter. AKA distribution-free test.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001282
Application: This study tested the relationship between the two categorical variables of diabetes patients that were receiving simvastatin to receive (1)fenofibrate or (2) a placebo. They investigated whether combination therapy with a statin plus a fibrate, as compared with statin monotherapy, would reduce the risk of cardiovascular disease in patients with type 2 diabetes mellitus who were at high risk for cardiovascular disease. "Baseline characteristics were compared between study groups with the use of the chi-square test." The chi-square test is a nonparametric test.
Statistically significant difference
Definition: The observed value of the test statistic falls into a rejection and null hypothesis is rejected.
Application: This article discusses the benefits of the MitraClip versus open heart surgery. "9.6% suffered major adverse events compared with 57% in the surgery group, a highly statistically significant difference." This means that the null hypothesis was rejected and the alternative hypothesis was accepted.
Nonsignificant difference
Definition: The observed value of the test statistic does not fall into a rejection region and the null hypothesis is not rejected.
Example: http://www.medscape.com/viewarticle/718401
Application: This article discusses the results of a study of the drug latrepirdine (brand name Dimebon)in the treatment of Alzheimer's Disease. The results showed no significant difference between this new drug and a placebo for the treatment of Alzheimer's Disease. Therefore, the test statistic did not fall into the rejection region and the null hypothesis was not rejected.
Between-subjects Design, with two groups
Definition: An experiment in which two or more groups are created.
Example: http://www.ojr.org/ojr/stories/070312ruel/
Application: This study observed differences in two groups, males and females, in eyetracking points within media (news articles, advertisements and photographs). Because it is between two different groups, it is a between-subjects design.
Between-subjects Design, with three or more groups
Definition: An experiment in which three or more groups are created.
Example: http://bjp.rcpsych.org/cgi/content/abstract/196/3/200
Application: This study used the categorical independent variable of women. The three groups were: women with recurrent major depressive disorder who had experienced one or more postnatal episodes, healthy women (control group), and women with recurrent major depressive disorder who experienced no postnatal depression.
Random sampling
Definition: A sampling method in which individuals are selected so that each member of the population has an equal chance of being selected for the sample, and the selection of one member is independent of the selection of any other member of the population.
Example: http://www.gallup.com/poll/126614/Americans-Say-Jobs-Top-Problem-Deficit-Future.aspx
Application: This report states that unemployment is the most important problem facing the country, according to randomly sampled adults nationwide.
Random Assignment
Definition: A method of assigning subjects to treatment groups so that any individual selected for the experiment has an equal probability of assignment to any of the groups and the assignment of one subject to a group does not affect the assignment of any other individual to that same group.
Example: http://www.medscape.com/viewarticle/718401
Application: In this article's discussion of a study on a new drug for the treatment of Alzheimer's Disease, subjects were randomly assigned to two groups: the group taking the new drug, latrepirdine (brand name Dimebon) and the group taking a placebo.
Independent Variable
Definition: A variable manipulated in an experiment to determine its effect on the dependent variable.
Application: This study measured the angle of a portion of the spine of subjects. The independent variable was the measurement of the angle of the spinal area on subjects WITH upper body symptoms and subjects WITHOUT symptoms. Since the variable was manipulated to test the effect of the measure of the spinal angle on these different subjects it is an example of an independent variable.
Levels of the Independent Variable
Definition: One value of the independent variable. To be a variable, an independent variable must take on at least two different levels.
Application: This study concerns "independent mobility, perceptions of the built environment and children's participation in play, active travel and structured exercise and sport". The variables of "weekly self-reported frequency of participation in outdoor play, structured exercise/sport and mode of travel home from school" are examples of independent variables.
Confounds
Definition: An extraneous variable that is covarying with the independent variable, potentially masking the true effects of the independent variable on the dependent variable.
Application: This article concerns the effects of vaccines on autism rates in infants. It cites the effect of mercury exposure as a confounding variable in thimerosal exposure when given in a vaccine to infants and pregnant women.
Dependent Variable
Definition: The variable in an experiment that depends on the independent variable. In most instances the dependent variable is some measure of a behavior.
Application: This study showed the effect of independent variables of "weekly self-reported frequency of participation in outdoor play, structured exercise/sport and mode of travel home from school" on the children's perceptions of the environment. Because this perception depends on the independent variables and is a behavior, it is an example of a dependent variable.
Within-subjects Design, with two groups
Definition: An experiment in which two or more groups are created and tested against each other.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001266
Application: This study concerns "the potential benefits and risks of the use of dual antiplatelet therapy beyond a 12-month period in patients receiving drug-eluting stents...". Because this study used a categorical independent variable of "patients who had received drug-eluting stents and had been free of major adverse cardiac or cerebrovascular events and major bleeding for a period of at least 12 months" and the continuous independent variables of receiving clopidogrel plus aspirin or aspirin alone, it is an example of a within subjects design.
Within-subjects Design, with three or more groups
Definition: A research design in which one group of subjects is exposed to and measured under each level of an independent variable. In a within-subjects design, each subject receives each treatment condition. Also known as a repeated mesures design or as a treatment-by-subjects-design.
Example: http://bjp.rcpsych.org/cgi/content/abstract/196/3/200
Application: This study used the categorical independent variable of women. The three levels of this were: women with recurrent major depressive disorder who had experienced one or more postnatal episodes, healthy women (control group), and women with recurrent major depressive disorder who experienced no postnatal depression. The continuous independent variable was personality/cognitive style. These factors were utilized in a one-way ANOVA test.
Main effect
Definition: The effect of the change in level of one factor in a factorial experiment measured independently of other variables.
Application: This article describes rushing sororities and the possible negative negative effects on members'body image and self esteem. There was a significant main effect of the women who chose to rush versus those who did not.
Interaction
Definition: A situation in a factorial design in which the effect of one independent variable depends on the level of the other independent variable with which it is combined.
Example: http://content.nejm.org/cgi/content/full/NEJMoa1001282
Application: This study tested the relationship between the two independent variables of diabetes patients that were receiving simvastatin to receive (1)fenofibrate or (2) a placebo. They investigated whether combination therapy with a statin plus a fibrate, as compared with statin monotherapy, would reduce the risk of cardiovascular disease in patients with type 2 diabetes mellitus who were at high risk for cardiovascular disease. They found that sex had a significant interaction with treatment: men seemed to benefit from fenofibrate therapy over women.
Strength of Effect (Eta squared)
Definition: A statistic that is a measure of the strength of effect.
Example: http://content.nejm.org/cgi/content/full/355/16/1647
Application: This article discusses the results of a study of DHEA and testosterone on aging. When men and women were combined, the DHEA group had a slight but significant increase in fat-free mass (less than 0.5 kg) and a decrease in the proportion of body fat (less than 1.5%) The word "slight" shows that the strength of increase in fat-free mass has been measured.
Scatterplot
Definition: A plot of a bivariate distribution in which the X variable is plotted on the horizontal axis and the Y variable is plotted on the verticle axis.
Example: http://content.nejm.org/cgi/content/full/353/5/498
Application: This article discusses the importance of physicians knowing what pathologists or laboratory hematologists are looking for and should be looking for in a blood smear. It cites a scatterplot as a visual representation of red-cell characteristics.
Positive relationship
Definition: A relationship between two variables in which, as the value of one variable increases the value of the other variable tends to increase also.
Example: http://content.nejm.org/cgi/content/short/356/24/2496
Application: This article discusses "emerging concern that the methods used to measure the quality of care unfairly penalize providers caring for patients with multiple chronic conditions". They studied the "relationship between the quality of care and the number of medical conditions a patient has". They found a positive relationship between the quality score and the number of conditions.
Negative relationship
Definition: A relationship between two variables in which ., as the value of one variable increases, the value of the other variable tends to decrease.
Example: http://content.nejm.org/cgi/content/full/351/11/1081
Application: Elevated levels of plasma factor VIII and D-dimer predict recurrent venous thromboembolism in adults. The researchers "sought to determine whether an elevation of factor VIII, D-dimer, or both at diagnosis and persistence of the laboratory abnormality after three to six months of anticoagulant therapy correlate with poor outcomes of thrombosis in children". They found that there may even be a negative relationship with the post-thrombotic syndrome in adults.
No relationship
Definition: No relationship exists between the two variables.
Example: http://content.nejm.org/cgi/content/short/360/14/1395
Application: This study researched the benefit of statins on reducing the incidence of cardiovascular events in patients at high cardiovascular risk patients who are undergoing hemodialysis. "There was no relationship between the primary cardiovascular end point and either baseline LDL cholesterol levels."
Linear relationship
Definition: A relationship between two variables that can be described by a straight line.
Example: http://www.prisonplanet.com/the-logarithmic-effect-of-carbon-dioxide.html
Application: This article discusses the differences between a linear relationship and a logarithmic one. It explains that if the relationship of increase in greenhouse gasses to increase in temperature were a linear relationship, we would all fry!
Curvilinear relationship
Definition: A relationship between two or more variables which is depicted graphically by anything other than a straight line.
Example: http://www.cherwell.org/content/9998
Application: This article cites a study that found that there isn't real, scientific evidence to prove that "the sequence of drinks over the course of a night out is key to one’s intoxication and subsequent hangover". Instead of this linear relationship, A later set of experiments testing out a wider range of concentrations however argued for a ‘curvilinear’ relationship. Here, scientists found that alcohol drunk at concentrations more closely resembling those of wine (15%) or neat spirits (45%) were absorbed more slowly than a mid-range concentration of 30%. The relationship between type of drink and intensity of hangover is not a perfect ratio, thus it is not a straight line.
Coefficient of Determination
Definition: The value of r2 indicating the common variance of variables X and Y.
Example: http://content.nejm.org/cgi/content/short/357/2/135
Application: This study looked at changes in the "prevalence of neural-tube defects in Canada before and after food fortification with folic acid was implemented". They showed the common changes in neural-tube defects before and after food fortification with folic acid.
Correlation does not equal causation
Definition: Correlation between two variables does not inherently mean that one causes the other. It only says that they are related in some way.
Example: http://www.eurekalert.org/pub_releases/2010-03/dumc-wtr031410.php
Application: This study from Duke University asked whether the recent US Stock Market drop was accompanied by more an increase in heart attacks. They initially found that there was an increase in incidences. "However, when more rigorous testing was used to specifically test the correlation with stock market values and eliminate the seasonable variability, the research question could no longer be answered." "The stock market declined during the winter, and previous studies show more MIs occur during the winter," says Fiuzat. "Therefore, we can't say definitively that there is an association. There is the possibility that there is no relationship."
Extra-Credit (3 points each)
Normal Distribution
Symmetrical
Asymptotic
Continuous
Sampling Error
Null Hypothesis
Alternative Hypothesis
Significance level
Two-tailed test
One-tailed test
Degrees of Freedom
Type I Error
Type II Error
Power
Pairwise comparisons
Post-hoc comparisons
◄ Back to Winter 2010 - Inferential Statistics - PSY302 page
