Term
| Allows comparison of multiple groups. 2 or more. |
|
Definition
|
|
Term
| What is the significance of variance due to treatment and variance due to error. |
|
Definition
|
|
Term
| Would you rather have a large or small sample size? |
|
Definition
|
|
Term
| Name 4 ways in which you might have variance due to error. |
|
Definition
-Small sample size (you want large)
-Diff btw subjects in same group (you want them to be similar)
-Diff in accuracy of measurement
-Diff in tx of subjects (treating them the same is best) |
|
|
Term
| An ANOVA that has 1 IV and 2 or more levels |
|
Definition
|
|
Term
| When performing an ANOVA, if the probability obtained in less than an alpha level is that significant or not? |
|
Definition
|
|
Term
| If ANOVA indicates significant different, but you do not know where, then what do you do? |
|
Definition
|
|
Term
| This will tell you which differences are significant |
|
Definition
|
|
Term
| When is post hoc test appropriate? |
|
Definition
| When you are doing more than 2 groups |
|
|
Term
| Name the 2 most common post hoc tests |
|
Definition
|
|
Term
DV = MS 1 grade
IV = Sex
Levels = Male, Female
Is a post hoc test needed? |
|
Definition
| No because there are only 2 levels |
|
|
Term
| An ANOVA that has 2 IV, multiple levels, and interaction |
|
Definition
|
|
Term
| An ANOVA that has 3 IV, multiple levels, and interactions |
|
Definition
|
|
Term
| What is it called when you have more than 1 DV? |
|
Definition
| MANOVA (Multiple Analysis of Variance) |
|
|
Term
| Measurements are repeated on same individual |
|
Definition
|
|
Term
| Different groups such as male/female |
|
Definition
|
|
Term
| Same groups such as pre/post test |
|
Definition
|
|
Term
| A test or instrument is reliable if it consistently measures similar values upon repeated application under the same conditions |
|
Definition
|
|
Term
| Repeat test under same circumstances. High correlation = Reliable Test. This is the most common way to test reliability. |
|
Definition
|
|
Term
| Reasons why you might have poor reliability is called sources of inconsistencies. Name 4 |
|
Definition
Intra-subject
Intra-rater
Inter-rater
Instrument |
|
|
Term
| Consisency of subject performance. May be based on pain, swelling, fatigue, or motivation. |
|
Definition
|
|
Term
| Consistency of one rater to assign same score under the same condition |
|
Definition
|
|
Term
| Consistency of assignment of score by different examiners under the same conditions |
|
Definition
|
|
Term
|
Definition
|
|
Term
| Name 2 types of quantifying reliability |
|
Definition
|
|
Term
| Scores may fluctuate from one measurement to another, but remains in realtively the same order. So if you had the most ER in the class the first time, you should also have the most the second time. |
|
Definition
|
|
Term
| Quantified by correlation. PT measures - r>.8 |
|
Definition
|
|
Term
| This is how the 2 scores agree. Consistency, agreement, similarity |
|
Definition
|
|
Term
| T-test (dependent) or ANOVA; Should be no significant difference. If 2 scores agree then there is no significant difference |
|
Definition
|
|
Term
r>.8
No significant difference. |
|
Definition
|
|
Term
R<.8 (relative)
p<.05 (absolute)
or BOTH |
|
Definition
|
|
Term
| This tells about both relative and absolute reliability. Single index. Calculated using variance (ANOVA). Provides a correlation. +1.0 to -1.0 |
|
Definition
|
|
Term
| Name 3 advantages of ICC over Pearsons |
|
Definition
-Allows correlation of multiple measurements.
-One index that takes into account absolute and relative reliability
-Corrects for systematic error |
|
|
Term
| That is an interpretation of ICC |
|
Definition
| Let ICC stand alone. If sig diff exists then the correlation will be lowered |
|
|
Term
| The extent to which a test measures what it is supposed to measure. If a test is valid then it must be reliable. If a test is reliable, it does not have to be valid. |
|
Definition
|
|
Term
| Radial Pulse - Cardiac Cath |
|
Definition
|
|
Term
| Impedence - Underwater Weighing |
|
Definition
|
|
Term
| The extent to which the conclusions of research are believeable and useful. "Threats" to internal validity. "Threats" to external validity |
|
Definition
|
|
Term
| Name 3 categoris of measurement validity |
|
Definition
Face
Content
Criterion-Related |
|
|
Term
| When an instrument appears to test what it is supposed to measure. The lowest form of validity. "Scientifically weak" |
|
Definition
|
|
Term
| The extent to which a measure is a complete representation of the concept of interest. Is the content of the test appropriate for measuring that skill |
|
Definition
|
|
Term
| Useful for questionnaires and surveys. Usually involves panel of experts. Subjective quantification of validity |
|
Definition
|
|
Term
| Target test (new) can be substituted for "gold standard". Quantified with statistics (correlation). |
|
Definition
| Criterion-Related Validity |
|
|
Term
| Reflects the patient's presence or absence of a condition. May be: a concurrent test or obtaines as an outcome measure |
|
Definition
|
|
Term
| Tests ability to obtain a positive test when condition is present |
|
Definition
|
|
Term
| Test is positive and the dz is present |
|
Definition
|
|
Term
| Test is negative and there is no dz |
|
Definition
|
|
Term
| Saying the pt has a dz when they do not |
|
Definition
|
|
Term
| Test's ability to obtain a negative test when the condition is absent |
|
Definition
|
|
Term
| Saying the pt does not have a dz when they do not |
|
Definition
|
|
Term
| Another term for a likelihood ratio |
|
Definition
|
|
Term
| Used to report diagnostic test results in a uniform way |
|
Definition
|
|
Term
| What are the clinical prediction rules |
|
Definition
Diagnosis
Prognosis and Risk
Response to intervention |
|
|
Term
| The anatomic, biochemical, physiologic, or psychologic derangement |
|
Definition
|
|
Term
| Names the primary dysfunction toward which the PT directs the tx |
|
Definition
|
|
Term
| Name 3 strategies of clinical dx |
|
Definition
1. Pattern Recognition
2. Complete history and physical exam
3. Hypothetico-deductive strategy |
|
|
Term
| Instantaneous realization that the pt conforms to a previously learned pattern of dz. Usually reflexive, not reflective. Usually cannot be explained to others. Argued to be "learned" on pts and not "taught" in lecture halls |
|
Definition
|
|
Term
| The pain-staking search for (but paying no immediate attention to) all the facts about a patient. The method of a novice. |
|
Definition
| Complete hisotry and physical (Exhaustion) |
|
|
Term
| The formulation, from the earliest clues of a "short list" of potential diagnoses. Subsequent tests are performed which will most likely reduce the length of the list. Requires an understanding of probability. |
|
Definition
| Hypothetico-deductive method |
|
|
Term
| Name 4 ways in which you can gather diagnostic data for a hypothesis-driven approach |
|
Definition
-Complete vs exhaustive data gathering
-Must know what is good data
-The importance of confirmatory and disconfirmatory data
-Rarely is one test sufficient |
|
|
Term
| Name 2 ways to appraise the literature regarding diagnostic tests |
|
Definition
-The effectiveness of a hypothesis-driven approach hinges on appropriate selection and interpretation of diagnostic tests.
-The clinician must be able to appraise the literature regarding diagnostic tests |
|
|
Term
| -Increase the odds favoring the diagnosis given a + test. Helpful for ruling in the condition. True Positive |
|
Definition
|
|
Term
| Reduce the odds favoring the diagnosis given a - test. Helpful for ruling out the condition. True negative |
|
Definition
|
|
Term
| If you rule a diagnosis with a test, you want the LR to be __ that you are right and __ that you are wrong |
|
Definition
|
|
Term
| When integrating diagnostic info into practice what 4 things do you need to do? |
|
Definition
-Decide what you are diagnosing
-List all possible variables
-Decide on the gold standard
-Measure everyone |
|
|
Term
| More valuable than sensitivity and specificity |
|
Definition
|
|
Term
| Expressed as a percentage (proportion). + value is the likelihood that a person who tests positive actually has the dx. - value is the likelihood that a person who tests negative actually does not have the dx |
|
Definition
|
|
