ARA Info Flashcards
What is a hypothesis?
The researcher proposes an educated “guess” about the outcomes of the study – this “guess” is presented as a statement called the hypothesis. The hypothesis is a declarative statement that predicts the relationship between the independent and the dependent variables, specifying the population that will be studied
Simply a statement of the relationship between variables
The purpose of a study is…
to TEST the hypothesis and ultimately to provide evidence so that the researcher can accept or reject the hypothesis
What is a null hypothesis?
The null hypothesis is “simply a statement of no difference or no relationship between the variables in the study”
The proposition that implies no effect or no relationship between phenomena or populations. Any observed difference would be due to sampling error (random chance) or experimental error. It may be easier to think of it as anullifiablehypothesis or one the researcher seeks to nullify.
What is experimental research?
Experimental research compares two or more conditions to determine a cause and relationship and allows the researcher to draw conclusions about observed differences
- RCT
What is descriptive resesarch?
Descriptive research simply describes populations
Descriptive research is “designed to document the factors that describe characteristics, behaviors and conditions of individuals and groups”
Descriptive research:
- Serves to explore an observation
- Leads to greater understanding of a problem or phenomena
To be considered a basic experimental design the design must include these characteristics:
One sample
One independent variable (IV)
Participants must be randomly assigned to groups
IV must be administered as planned
Confounding variables are minimized & variables are controlled by the researcher
One dependent variable (DV) on which all subjects are measured
The hypothesis is attempting to show a cause & effect relationship between the IV and the DV
What is a construct?
A construct is an abstract idea, theme, or subject matter that a researcher wants to measure. Because it is initially abstract, it must be defined.
Ex: : The researcher would like to determine if “XYZ technique” is effective in increasing shoulder AROM in patients with a total shoulder replacement.
The study sample includes…
the people who are the subjects in the research study
Describe the study sample.
The chosen sample should be a “subset” of the population you are studying. The subset should be a representative sample (target sample) of the population.
Population is a set of people who share common features, i.e., age, diagnosis, etc…
The sample being studied should be representative of the population from which they were selected.
What is inclusion criteria?
The primary traits of the target population (representative population)
- Age
- Gender
- Sex
- Geographic location, etc.
What is exclusion criteria?
Factors that would preclude someone from being a subject in the study
The factors that generally are considered confounding to the results (that is they are likely to interfere with interpretation of the findings)
What are dependent variables?
Dependent variable (DV) – This variable is the response or outcome related to the effect of the IV.
The dependent variable can be described as the behavior that may change.
Also known as an outcome variable.
The dependent variable is the possible effect.
What is an independent variable?
Independent Variable (IV) – A variable that will predict or cause an outcome
Also known as the active or predictor variable
The IV is the possible cause
A condition, intervention, or characteristic that will predict or cause a given outcome
The IV can be described as a condition that can change behavior
What are outcome measures?
It is the tool, assessment, or instrument used to test and see if the dependent variable was affected or changed by the independent variable
When selecting an outcome measure to assess the dependent variable, we must choose one that is responsive, or sensitive, to change. Otherwise, we will not learn anything from the research because changes will not be detected.
In selecting an outcome measure for a study, the researcher has to be especially concerned about its responsiveness.
What are the scales of measurement?
Nominal Scales
Ordinal Scales
Interval Scales
Ratio Scales
What is a nominal scale?
A nominal scale is used to categorize characteristics of subjects.
Ex: Gender would be assigned to a category by a number. Females may be categorized as “1” and males as “2”
This type of scale has no other function other than to classify or categorize subjects.
Gender, ethnicity/race, religion, diagnosis
What is an ordinal scale?
Used to classify ranked categories
These are numbers assigned to rank or quantify an observation, behavior, etc. that has no true “quantity”
The intervals between the ranks are not necessarily the same
Ordinal scales can be subjected to mathematical operations. They are treated like interval scales.
A good example of an ordinal scale is the FIM scale. Therapists observe patient’s skills and rate the performance by assigning a numerical value (Ex: A score of “7” can be given for feeding for a pt who can independently feed themselves and swallow).
What is an interval scale?
Interval scales have equal distances between units of measurement
Allows the researcher to determine relative difference
Do not contain an absolute true zero point that indicates the absences of a characteristic. If there is a zero point identified in an interval scale, it has been randomly assigned.
Example of an interval scale is a calendar year.
What is a ratio scale?
Demonstrate equal distances between units of measurement and they have an absolute zero point.
They indicate absolute amounts of measure.
All forms of mathematical and statistical operations can be performed with a ratio scale.
What is parametric statistics?
Statistical procedures for estimating population parameters and for testing hypotheses based on population parameters. With assumptions about the distribution of variables, and for the use with interval or ratio measures
What is nonparametric statistics?
A set of statistical procedures that are not based on assumptions about population parameters, or the shape of the underlying population distribution; most often used when data are measured on the nominal or ordinal scales
What is a t-test?
a parametric test for comparing 2 means (also called student’s t-test)
What is a paired t-test?
a parametric test for comparing 2 means for correlated samples or repeated measures; also called a correlated t-test
What is an unpaired t-test?
a parametric test for comparing 2 means for independent samples; also called an independent t-test
What is ANOVA?
Analysis of Aariance
Statistical procedure appropriate for comparison of three or more treatment groups or conditions, or the simultaneous manipulation of 2 or more independent variables, based on the F statistic
What is ANCOVA?
Analysis of Covariance
Statistical procedure used for 2 or more treatment groups while controlling for the effect of 1 or more confounding variables (called covariates)
What is MANCOVA?
Multivariate Analysis of Variance
An advanced multivariate procedure that provides a global test of significance for multiple dependent variables using analysis of variance
What is the Mann-Whitney U test?
a nonparametric statistical test for comparing 2 independent groups; analogous to the unpaired t-test
What is the Bonferroni adjustment?
a correction often used when multiple t-tests are performed, to reduce Type I error. The desired level of significance is divided by the number of comparisons. The resulting value is then used as the level of significance for each comparison to reject the null hypothesis.
What is a Phi coefficient?
a nonparametric correlation statistic for estimating the relationship between two dichotomous variables
What is a one-tailed test?
a statistical test based on a directional hypothesis, in which critical values are obtained for only one tail of a distribution
What is a two-tailed test?
a statistical test based on a nontraditional alternative hypothesis, in which critical values represent both positive and negative tails of distribution
What is the Kruskal-Wallis (ANOVA) by ranks (H)?
a nonparametric statistical procedure for comparing more than 2 independent groups representing levels of one independent variable
What is a one way ANOVA?
analysis of variance with one independent variable
What is a two way ANOVA?
analysis of variance with 2 independent variables
What is a chi-square?
a nonparametric test applied to nominal data, comparing observed frequencies within categories to frequencies expected by chance
What is the Friedman ANOVA?
nonparametric statistical procedure for repeated measures, comparing more than 2 treatment conditions of one independent variable; analogous with the one-way ANOVA
What is the Wilcoxon signed-ranks tests (T)?
a nonparametric statistical procedure, comparing 2 correlated samples (repeated samples); analogous to the paired t-test
What is the Pearson product-moment coefficient of correlation?
a parametric statistical technique for determining the relationship between two variables
What is the Spearman rank correlation?
a nonparametric correlation procedure for ordinal data
What is the McNemar test?
nonparametric statistical test for nominal level measures, for correlated samples, a form of the Chi test
What is the Fisher exact test?
nonparametric procedure applied to nominal data in a 2x2 contingency table, comparing observed frequencies within categories to frequencies expected by chance. Used when samples are too small for chi-square test