## Glossary of National MFT Research

Created by AndieSjs

- Methodology
- Selection of measurement and choice of setting to conduct research.

- Ratio Scales
- Interval scales with an absolute zero point.

- Standard of deviation
- A measure of variability

- Dependent Variable
- One that is the consequence of another variable

- Threats to Internal Validity
- Maturation

Regression

Experimental Mortality

- Survey Research
- Either descriptive or ex post factor

- Event
- Specific collection of the possible outcomes of a random phenomenon

- Frequency of an event
- The number of times an event occurs in a sequence of repetitions of a random phenomenon.

- Relative Frequency of an event
- The fraction or proportion of repetitions during which the event occurs; always expressed as a number between 0 and 1

- Probability of an Event
- When the relative frequency of an event approaches a fixed number, that number is the probability of the event.

- Nominal Scales
- Naming Scales -

Scales which name data and places them into categories.

- Ordinal Scales
- Ordering Scales -

Scales which orders available data but does not measure.

1st 2nd 3rd etc

- Interval Scales
- Measuring Scales-

Measurable, positive and linear

- Ratio Scale
- Measurement provides for an absolute zero which is not an arbitrary point.

- Qualitative Scales
- Nominal and Ordinal Scales

- Quantitative Scales
- Interval and Ratio Scales

- Mean
- Mean is the arithmetic average. Can be used on interval and ratio scales

- Median
- The midpoint of the observations when data are arranged in increasing order.

- Mode
- The most frequent value.

- Bimodal
- A distribution with two most frequently occurring scores

- Multimodal
- Two or more most frequently occurring scores

- Absolute Zero Point
- A distinguishing feature of a ratio scale

- Standard Scores
- Observations expressed in the standard deviation units about the mean.

- Units
- The basic objects on which the experiment is done.

- Subjects
- Units which are human beings

- Variable
- A measured characteristic of a unit

- Dependable Variable
- A variable whose changes are being studied.

- Independent Variable
- A variable with an effect upon dependent variables being studied.

- Factor
- An independent variable in a study

- Treatment
- Any specific experimental condition applied to the units.

- Validity
- Ability of tests to measure what they are designed to measure

- Internal Validity
- The conclusion of the study for the subjects themselves

- External validity
- Generalization of the conclusion of a study to a larger population

- Double Bind Technique
- When both the subjects and those who evaluate the outcome of the experiment are ignorant of which treatment has been given.

- A Measurement Process
- unbiased if it does not overstate or understate the true value of a variable.

- Randomization
- The random allocation of experimental units among treatments, most simply by assigning a simple random sampling (SRS) of units to each treatment.

- Control
- Taking account of extraneous factors in the experiment design, most simply by the use of equivalent groups for comparison

- Parameter
- A number describing a population

- Statistic
- A number describing the sample data

- Duration Counts
- The measure of time a behavior last.

- Frequency Measurement
- The count of how many times a target behavior occurs

- Interval Measure
- Selects a discrete unit of time and observes the time block for the target behavior

- Frequency
- The number of times the value occurs in the data

- Line Graphs
- Show the trend of variables over time

- Bar Graphs
- compare the values of several variables

- Scatter Plots
- Used to graph bivariate data when both variables are measured on an interval/ratio or ordinal scale.

- Percentile
- derived from scores expressed in terms of percentages.

- Variance
- The mean of the squares of the deviation of observations from their mean.

- Standard Deviation (SD)
- The positive square root of the variance. Describes the variability found within the distribution. A larger SD means a greater number of scores around the mean.

- Range
- Highest score minus the lowest score plus 1

- T-Test
- A formula for evaluating the means of two groups.

- Association in Bivariate Data
- Systemic connection links changes in one variable and changes in another

- Face Validity
- Explores whether the item appears to reach the content desired.

- Logical Content Validity
- The method the developer engaged with to ensure the required content was included in the field test.

- Criterion Validity
- Seeks to know whether the measurement instrument correlates significantly with other variables that may be relevant

- Predictive Validity
- Questions whether or the instrument has correlation to a future event

- Concurrent Validity
- references the instrument's correlation to an event occurring simultaneous to the time the measure is taken

- Construct Validity
- asks if the instrument draws from its theorized psychological construct it proposes to measure

- Convergent Validity
- Explores if a construct, such as depression, correlates with a theoretically relevant variable.

eg; the amount of time a person spends sleeping, crying, etc

- Discriminant Validity
- References how theoretically non-relevant variables are not associated with scores on the measurement.

- Reliability
- The degree to which the test is consistent, dependable and repeatable

- Methods of assessing reliability
- test/retest

alternate form

internal consistency or split half method

brown formula

inter-rate reliability

- Factors that affect Reliability
- length of test

range of variability in scores

guessing

interpretation of reliability coefficient

- Kuder-Richardson Formula
- A mathematical formula used to estimate internal consistency reliability

- Skewed
- When scores pile up on one end of the scale or the other

- Z Scores
- Mean=0

SD=1.0

Range of SD scores is -3 to +3

Z=rawscore-mean/SD

- T Scores
- Mean=50

SD=10

- Correlation Coefficient
- Examines the degree to which variations or differences in one variable are related to variations or differences in another

- Perfection Correlation
- +1.00 or -1.00

- Line of Regression
- the straight line vector that connects those points

- Regression
- the primary statistical tool used for prediction

- Null Hypothesis (Ho)
- statement being tested