What are dependent variables and what are examples?

The outcome variable measured

May be changed or influenced by manipulation of the independent variable

What are conceptual defined dependent variables?

Conceptual variable - the general idea of what needs to be measured in a study: i.e. strength

Must be defined in specific measurable terms for use in the study (once defined, becomes the operational variable)

What are the levels of precision of measurement and what are examples?

The level of measurement/precision of the dependent variable is one factor that determines the choice of statistical tests that can be used to analyze the data

- Nominal (Count Data)
- Ordinal (Rank Order)
- Interval
- Ratio

What is reliability and why is it important?

Reliability: An instrument or test is said to be reliable if it yields consistent results when repeated measurements are taken

3 Forms of Reliability:

- Intra-rater reliability
- Inter-rater reliability
- Parallel-forms reliability

All three forms require comparisons of two or more measures taken from the same set of subjects

Requires a statistical measure of this comparison – correlation

Results of these statistical tests are 0 to 1, with 1 being a perfect correlation and 0 being no correlation

For a reliable comparison the association must be as close to 1 as possible and at least > 0.8

What is validity and why is it important?

Validity - the measure or instrument (measuring tool) is described as being valid when it measures what it is supposed to measure

A measure/instrument cannot be considered universally valid.

- Validity is relative to the purpose of testing
- Validity is relative to the subjects tested

Validity is a matter of degree; instruments or tests are described by how valid they are, not whether they are valid or not

Validity assessments can be made by judgment (judgmental validity) or by measurements (empirical validity)

Judgmental Validity

Based upon professional judgment of the appropriateness of a measurement or instrument

2 principle forms:

- Face validity
- Content validity

What are Sensitivity, Specificity and Predictive Values?

Clinical research often investigates the statistical relationship between symptoms (or test results) and the presence of disease

There are 4 measures of this relationship:

- Sensitivity
- Specificity
- Positive Predictive Values
- Negative Predictive Values

What are extraneous/confounding variables and what are examples?

Confounding or Extraneous Variables: Biasing variables – produce differences between groups other than the independent variables

These variables interfere with assessment of the effects of the independent variable because they, in addition to the independent variable, potentially affect the dependent variable

Analysis of the Dependent Variable

A single research study may have many dependent variables

Most analyses only consider one dependent variable at a time

Univariate Analyses- each dependent variable analysis is considered a separate study for the purposes of statistical analysis

What are operationally defined dependent variables and what are examples?

The specific, measurable form of the conceptual variable

The same conceptual variable could be measured many different ways; defined in each study

i.e: to define strength = Maximum amount of weight (in kilograms) that could be lifted 1 time (1 rep max)

Nominal Level of Precision

Score for each subject is placed into one of two or more, mutually exclusive categories

Most commonly, nominal data are frequencies or counts of the number of subjects or measurements which fall into each category.

Also termed discontinuous data because each category is discrete and there is no continuity between categories

There is also no implied order in these categories

Examples:

- Color of cars in parking lot
- Gender of subjects
- Stutter – yes/no

Can only indicate equal (=) or not equal (≠)

Ordinal Level of Precision

Score is a discrete measure or category (discontinuous) but there is a distinct and agreed upon order of these measures, categories

The order is symbolized with the use of numbers, but there is no implication of equal intervals between the numbers

Examples include any ordered scale

Can say = & ≠, and greater than (>) or less than (

Interval Level of Precision

Numbers in an agreed upon order and there are equal intervals between the numbers

Continuous data ordered in a logical sequence with equal intervals between all of the numbers and intervening numbers have a meaningful value

There is no true beginning value – there is a 0 but it is an arbitrary point

Examples:

- Temperature
- Dates
- Latitude (from +90° to −90° with equator being 0

Interval level can say = or ≠; < or >; and how much higher (+) or how much lower (−)

(Interval does not have a true 0 value; Ratio does)

Ratio Level of Precision

Numbers in an agreed upon order and there are equal intervals between the numbers

Continuous data ordered in a logical sequence with equal intervals between all of the numbers and intervening numbers have a meaningful value

There is a true beginning value – a true 0 value

Ratio level – can do everything with interval but also can us terms like 2X or double (×) or half (÷) when comparing values

(Interval does not have a true 0 value; Ratio does)

Mathematical Comparison of Precision Levels

Nominal level – can only indicate equal (=) or not equal (≠)

Ordinal level – can say not only = & ≠ but also greater than (>) or less than (< or >; and how much higher (+) or how much lower (−)

Interval level can say = or ≠; < or >; and how much higher (+) or how much lower (−)

Ratio level – can do everything with interval but also can us terms like 2X or double (×) or half (÷) when comparing values

Statistical Reasoning for the Precision Levels

Nominal level – unit of central tendency is the mode and any variability is assessed using range of values

Ordinal level – unit of central tendency is the median and any variability is assessed using range of values

Interval or Ratio (Metric) - unit of central tendency is the mean and any variability is assessed using standard deviation if normally distributed

Intra-Rater Reliability

Tested by having a group of subjects tested and then re-tested by the same person and/or instrument after an appropriate period of time

Inter-Rater Reliability

Reliability between measurements taken by two or more investigators or instruments

Different instruments or different investigators

Objective Testing

Usually has both high intra-rater and inter-rater reliabilities

Example: isokinetic dynamometer to measure muscle force (torque)

Raters are trained in the use and calibration of the instrument

Parallel Forms Reliability

Specific type of reliability used when the initial testing itself may affect the second testing.

Two separate forms of the exam covering the same material, or testing the same characteristic, are used

Investigators must first do testing to demonstrate that the two forms of the test are, in fact, equivalent

Face Validity (Judgmental)

Judgment of whether an instrument appears to be valid on the face of it - on superficial inspection, does it appear to measure what it purports to measure?

To accurately assess this requires a good deal of knowledge about the instrument and what it is to measure.

That is why professional judgment is emphasized in the definition of judgmental validity

Content Validity (Judgmental)

Judgment on the appropriateness of its contents.

The overall instrument and parts of the instrument are reviewed by experts to determine that the content of the instrument matches what the instrument is designed to measure

Empirical Validity (Criterion-Related Validity)

Use of data, or evidence, to see if a measure (operational definition) yields scores that agree with a direct measure of performance

2 forms of Empirical Validity:

- Predictive
- Concurrent

Predictive Validity (Empirical)

Measures to what extent the instrument predicts an outcome variable.

Concurrent Validity (Empirical)

Measures the extent to which the measures taken by the instrument correspond to a known Gold Standard

Correlation statistics are also used to measure the validity

Inter-Relationship between Reliability and Validity

For an instrument or test to be useful it must be both valid and reliable

Sensitivity

Formula: Sensitivity = TP/TP+FN

Definition: the probability that a symptom is present (or screening test is positive) given that the person does have the disease

Patient Relevance*: “I know my patient has the disease. What is the chance that the test will show that my patient has it?”

Specificity

Formula: Specificity = TN/TN+FP

Definition: the probability that a symptom is not present (or screening test is negative) given that the person does not have the disease

Patient Relevance: “I know my patient doesn’t have the disease. What is the chance that the test will show that my patient doesn’t have it?”

Positive Predictive Value

Formula: TP/TP+FP

Definition: the probability that a person has the disease given a positive test result

Patient Relevance: “I just got a positive test result back on my patient. What is the chance that my patient actually has the disease?”

Negative Predictive Value

Formula: TN/TN+FN

Definition: the probability that a person does not have the disease given a negative test

Patient Relevance: “I just got a negative test result back on my patient. What is the chance that my patient actually doesn’t have the disease?”