Research Designs and Statistical Analysis

For a descriptive (non-experimental, observational) research design, the type of analysis you would use is

Descriptive statistics

For a correlational research design, the analysis you would use is

Pearson Correlation

For a pretest-posttest design, the type of analysis you would use is a

Paired t-test

For prediction research, the analysis you would use is a

Linear regression

With a repeated measures design, you would use _______ for analysis

Repeated measures ANOVA

For a pretest-posttest control group design, you would use what test for analysis

Independent t-test

For a multi-group pretest-posttest research design, you would use a __________ for analysis

One-way ANOVA

Identify the research design and analysis for the following:

"What are the characteristics of a pressure ulcer among adults with paraplegia?"

Descriptive design; Descriptive statistics

Identify the research design and analysis for the following:

"Is there a relationship between activity level and healing rate? You may believe that as activity level increases to reduce ischemia from prolonged weight bearing, so will healing rate."

Correlational design; Pearson Correlation

Identify the research design and analysis for the following:

"Does weight shifting reduce erythema (redness)? That is, does a difference exist between erythema before weight shifting and erythema after weight shifting?"

Pretest-posttest design; Paired t-test

Identify the research design and analysis for the following:

"Can you determine the healing rate based on the patient's degree of sensory impairment?"

Prediction research; Linear regression

Identify the research design and analysis for the following:

"Does frequency of weight shifting effect erythema status? You want to compare three weight-shifting programs with your patients: low frequency (every 2 hours); medium frequency (every hour); high frequency (every 15 minutes)."

Repeated measures design; Repeated measures ANOVA

Identify the research design and analysis for the following:

"Does use of a seat cushion increase the healing rate of pressure ulcers more than does use of no cushion? That is, is there a differencein healing rates between the no cushion and the cushion groups?"

Pretest-posttest control group design; Independent t-test

Identify the research design and analysis for the following:

"You want to evaluate three different seat cushions. Do three seat cushions differ in their ability to improve the rate of healing of pressure ulcers? That is, is there a difference in healing rates for the three cushion groups?"

Multi-group pretest-posttest design; One-way ANOVA

______________ research is characterized by controlled manipulation of variables by the researcher

Experimental research

_________-________ experimental designs have one independent variable

single-factor experimental design

This design is a randomized control trial. It involves measuring a dependent variable in two groups (treatment group and control group) before an intervention, administering the intervention to the treatment group, and measuring the dependent variable again in both groups after the intervention

pretest-posttest control-group design

The following is an example of what kind of research design:

R O X1 O

R O X2 O

R O O

multi-group pretest-posttest design

This experimental research design is used when researchers are unable to take pretest measurements (i.e., had a surgery)

posttest-only control group design

This is a type of research design that aims to establish cause-and-effect relationships by manipulating an independent variable but lacks random assignment of participants to treatment and control groups (or vice versa; lacks an IV but has random assignment)

Quasi-experimental design

When the same subjects are measured under all levels of the IV and/or each subject receives more than one actual treatment; within-subject designs as the effect of the IV is seen within subjects rather than between groups

Repeated Measures designs

Type of experimental design where each level of every independent variable is combined with each level of the other variables to form all possible experimental conditions; can be factorial or nested.

Multiple-factor experimental designs for independent groups

Type of multiple-factor experimental design for independent groups in which the factors are crossed, meaning that each level of one factor is combined with each level of another factor

Factorial design

This type of multiple-factor experimental design for independent groups occurs when not all of the factors cross one another

Nested design

For multiple-factor experimental designs, it is considered to be _________-subjects when different groups of participants are exposed to different conditions or treatments to measure the effect of an IV

Between-subjects design

For multiple-factor experimental designs, it is considered to be _________-subjects when all participants experience every condition of the IV

Within-subjects design

A combination of between-subjects and within-subjects design would be considered a ________ design

Mixed

To identify the ratio of the differences between the groups to the differences within the groups, you would use what test

Independent t-test

Nonparametric alternatives to the independent t-tests; rank the scores from the two groups, then rank sums are compared

Mann-Whitney or Wilcoxon Rank Sum Test

A statistical test used to determine if there are significant differences between the means of three or more independent groups based on a single IV; identifies that there is a difference between means, but not which ones

One-way ANOVA

Nonparametric alternative to the one-way ANOVA

Kruskal-Wallis test

A statistical test used to determine if there is a significant difference between observed frequencies (what you actually collected) and expected frequencies (what you would expect if a null hypothesis were true)

Chi-Square (χ²) Test of Association

Test used to determine differences between two dependent samples (i.e., pretest vs posttest scores)

Paired t-test

Nonparametric test used to determine differences between two dependent samples (i.e., pretest vs posttest scores)

Wilcoxon signed rank test

This statistical test would be used to find differences between two or more dependent samples (i.e., pretest, posttest, follow-up test)

Repeated Measures ANOVA