SAFMEDS key words Flashcards
Central tendency
A genetic term describing the centre of a frequency distribution of observations, measured by mean, mode and median
Confounding variable
A variable (that may or may not have been measured), other than the independent variable/s , which influences the outcome of the variable
Content validity
Evidence that the contents of a test corresponds to the content of the construct it was designed to cover
Correlation coefficient
A measure of the strength and direction of the association between two variables. There are two common variants - Pearson’s for parametric, and spearman’s for non-parametric data. In both cases, coefficients range from between -1 and 1
Raw data
A set of data which is yet to be screened for analysis
Repeated measures / with subjects t-tests
A test using the t-statistic that establishes whether two means collected from the same sample differ significantly
Independent samples / between subjects t-tests
A test using the t-static that establishes whether two means collected from independent samples differ significantly
Ecological validity
Evidence that the results of a study, experiment, or test can be applied, and allow inferences.to real-world conditions
Experimental hypothesis
The prediction that there will be an effect (ie, that an experimental manipulation will have some effect on the dependant variables, or that certain variables will relate to each other)
Null hypothesis
The reverse of the experimental hypothesis - that there will be no effect from your experimental manipulation or that certain variables are not related
Fit
The degree to which a statistical model is an accurate representation of the observed data. These range from basic models (eg. the mean) to more complex models (eg. T-test and correlations)
Frequency distribution
A graph plotting values of observations on the Y axis, and the frequency with which those values occur on the X axis, commonly called a histogram. Used to assess the distribution of data
Homogeneity of variance
An assumption for parametric testing in between-groups designs, where the variance of one variable is stable (roughly equal) at all levels of another variable
Hypothesis
A prediction about the state of the world
Independent design
An experimental design in which different treatment conditions use the same participants, resulting in related of repeated data
Interval data
Data measures on a scale along which all intervals are equal, for example pain rating on a scale of 1 to 10
Repeated design
An experimental design in which different treatment conditions use the same participants, resulting in related or repeated data
Ratio data
Interval data, with the additional property that ratios are meaningful. For example, when assessing pain on a scale of 1 to 10, for the data to be considered ratio level,a score of 4 should genuinely represent twice as much pain as a score of 2
Nominal data
Data where numbers represent categories or names
Ordinal data
Data that tells us not only that something occurred, but the order in which it occurred. Examples include data represented as ranks, for example placements for participants in a race
Kurtosis
Measures the degree to which sources cluster at the tails of a frequency distribution; positive kurtosis indicates too many scores in the tails, resulting in a peaked curve. Negative kurtosis indicates too few scores in the tails, resulting in a flattened curve
Likelihood
The probability of obtaining a set of observations given the parameters of a model fitted to those observations
Mann-whitneytest
A non parametric test which examines differences between two independent samples. The non-parametric equivalent of an independent t-test
Mean
A simple statical model on the centre of a distribution of scores; a hypothetical estimate of a ‘typical’ score, calculated by summing the observed scores and dividing by the number of observations
Median
The middle score of a test of ordered observations
Mode
The most frequently occurring score in a set of data
Non-parametrictests
A family of statistical tests that do not rely on the restrictive assumptions of a parametric test. In particular they do not assume sampling distribution is normal. Normally considered less powerful
Parametric tests
A family of statistical tests that require data to meet certain assumptions, in particular around the distribution of the data and the inter-relation between variables levels. The basic assumptions for parametric test are; data are normally distributed, homogeneity of variance, interval or ratio dataand independence of scores
Population
In statistical terms, this refers to the group from which we draw a sample, and to which we want to generalise results
Qualitative methods
Extrapolating evidence for a theory from what people say and write (in contrast to qualitative methods)
Quantitative methods
Inferring evidence for a theory through measurement of variables that produce numeric outcomes (in contrast to qualitative methods)
Quartiles
A generic term for the three values that cut an ordered data set into four equal parts. The three sections are known as the lower, middle, and upper quartiles. The space between the lower and upper quartile is known as the inter-quartile range
Sample
A smaller (but hopefully representative) collection of units from a population, used to determine truths about that population (eg. How the populationbehaves under certain conditions)
Skew
A measure of the symmetry of a distribution, with a skew of 0 representing perfect symmetry. When scores are clustered at the lower and of the distribution, the skew is positive. When scores are clustered at the higher end of the distribution, the skew is negative
Standard deviation
An estimate of the average variability (spread) of a set of data, measures in the same unit of measurement as the original data. It is the square-root of the variance
Test statistic
A statistic for which we know how frequently different values occurin random samples. The observed value of such a statistic is usually used to test a hypothesis
Validity
Evidence that a study allows correct inferences about the question it was designed to answer, or that a test measures what is set out to measure
Variance
An estimate of the average variability (spread) of a set of data. it is the sum of the squares divided by the number of values on which the sum of the squares is based, minus 1
Wilcoxon’s signed-rank test
A non-parametric test that looks for differences between related samples. A non-parametric equivalent of the related t-test
Z-score
The value of a observation expressed in standard deviation units, calculated by taking the observed score and subtracting the sample mean, then dividing the result by the standard deviation of all observations. Z-scores can be used to assess the likelihood of obtaining certain scores on a measure
