1/22
Vocabulary flashcards covering cognitive verbs, data types, descriptive measures, inferential statistics, and hypothesis testing rules for the Psychology IA1 Data Test.
Raw data
A table of individual scores collected from each participant or condition before any summary statistics have been calculated.
Processed data
Data that has already been summarised into descriptive or inferential statistics, including means, standard deviations, error bars, confidence intervals, and p-values.
Correlational data
Data evaluating the linear relationship between two naturally occurring co-variables without experimental manipulation, typically plotted on a scatterplot.
Nominal data
Categorical data without an inherent numerical order (such as condition names or eye colour), which can only be summarised using counts and the mode.
Ordinal data
Ranked data where the relative gaps between ranks are unknown (such as Likert scales or grades), best described using the median and interquartile range.
Interval data
Numerical data with equal gaps between points but no true absolute zero (such as temperature in degrees Celsius or IQ scores), suitable for mean and standard deviation.
Ratio data
Numerical data with equal intervals and an absolute true zero where zero means none (such as reaction time or number of words recalled).
Mean
A measure of central tendency found by dividing the sum of all scores by the number of scores (N); appropriate for symmetrical interval or ratio data without outliers.
Median
The middle score in an ordered dataset that is resistant to outliers; the preferred measure of central tendency for ordinal, skewed, or outlier-affected data.
Mode
The most frequently occurring score in a dataset, and the only measure of central tendency applicable to nominal data.
Range
A measure of dispersion calculated as the highest score minus the lowest score, which can be severely distorted by extreme outliers.
Interquartile range (IQR)
A measure of spread representing the middle 50% of data, calculated as Q3−Q1, which resists the influence of outliers.
Standard deviation (SD)
A measure of variability that indicates, on average, how far each score sits from the mean of the dataset.
Standard error (SE)
An estimate of how much a sample mean is likely to differ from the true population mean, calculated as SE=nSD.
95% confidence interval (CI)
A statistical range calculated as mean±margin (where margin=1.96×SE) that is 95% likely to contain the true population mean.
Confidence interval overlap rule
A decision rule stating that if two 95% confidence intervals do not overlap, the difference between groups is statistically significant; if they overlap, it is not.
Null hypothesis
A statement predicting that there is no real difference between conditions or no relationship between variables, with any observed differences being due to chance.
Alternative hypothesis
A statement predicting a specific, real difference between experimental conditions or a relationship between co-variables.
p-value
The probability of obtaining the observed results if the null hypothesis were true, where a value of p<.05 denotes statistical significance.
Unpaired t-test
A parametric statistical test used to compare the means of two independent groups consisting of different, unrelated participants.
Paired t-test
A statistical test used to compare the means of two related sets of scores, used in repeated measures or matched pairs designs.
Pearson's correlation coefficient (r)
A standardized measure ranging from −1 to +1 that indicates the direction and strength of a linear relationship between two variables.
Correlation is not causation
A foundational research principle stating that an observed association between two variables does not prove that one variable causes changes in the other.