Term
|
Definition
| a field in mathematics that deals with the organization, analysis, and presentation of numerical information |
|
|
Term
|
Definition
| a characteristic or value that does not change, but rather is the same in all situations |
|
|
Term
|
Definition
| a characteristic that can take on different values, either across individuals at a single point in time or within a given individual at different times |
|
|
Term
|
Definition
| a characteristic that cannot be observed directly, but which manifests itself in observable behaviors |
|
|
Term
|
Definition
| the process of defining a given construct in terms of a specific set of measurements taken on observable behaviors or events associated with that construct |
|
|
Term
|
Definition
| numerical information resulting from measurement of a behavioral science characteristic |
|
|
Term
|
Definition
| a collection of data with a common basis, such as information collected in a research study or scores on some test. |
|
|
Term
|
Definition
| the entire collection of everyone who possesses a given characteristic or a specified combination of characteristics |
|
|
Term
|
Definition
| any numerical characteristic or feature of a population |
|
|
Term
|
Definition
| any subset of a given population |
|
|
Term
|
Definition
| any numerical characteristic or feature of a sample |
|
|
Term
|
Definition
| the process of organizing and summarizing data |
|
|
Term
|
Definition
| the process of forming conclusions about a population based on results of studying a sample taken from that population |
|
|
Term
|
Definition
| the difference between the characteristics of a sample and those of the population from which it was drawn |
|
|
Term
|
Definition
| a variable which is measure using either whole numbers or distinct categories with no intermediate values or levels |
|
|
Term
|
Definition
| a variable that can be measured (at least theoretically) with an infinite number of levels between whole values |
|
|
Term
|
Definition
| the boundary interval that surrounds a given value on the scale for a continuous variable |
|
|
Term
|
Definition
simple categorization of a characteristic without reference to quantity, quality, or any other consideration that would make one category "better" than another category
Examples: hair color, major, gender, favorite food |
|
|
Term
|
Definition
simple categorization of a characteristic but where reference is made to one category being more or better than another
Examples: military hierarchy, seniority in a job, year in college |
|
|
Term
|
Definition
numerical description of a characteristic based on a scale with equal intervals
Examples: temperature, IQ score |
|
|
Term
|
Definition
numerical description of a characteristic based on a scale with equal intervals and an absolute zero
Examples: weight, time, length |
|
|
Term
|
Definition
| a research method where one variable is manipulated under carefully controlled conditions in order to observe changes in a second variable |
|
|
Term
|
Definition
| the variable that is directly manipulated in a laboratory experiment |
|
|
Term
|
Definition
| the variable that is observed in a laboratory experiment to determine how it was affected by changed in the independent variable |
|
|
Term
|
Definition
| a research method where self-reported information is collected directly from a sample of people |
|
|
Term
| Informal Observation and Analysis |
|
Definition
| research conducted to identify the essential properties, dynamics, and structures of a given situation or characteristic |
|
|
Term
|
Definition
| the process of changing the results of a division to a specified number of decimal places |
|
|
Term
|
Definition
| the numeric place where the results of a given division should end |
|
|
Term
|
Definition
| a tabular display showing the number of times each score or value in a dataset occurred |
|
|
Term
|
Definition
| the ratio of the number of values for one particular scale point divided by the total number of values in the dataset |
|
|
Term
|
Definition
| the total number of values at or below a given scale point |
|
|
Term
|
Definition
| the percentage of scores in a dataset that are at or below a particular scale value |
|
|
Term
| Grouped Frequency Distribution |
|
Definition
| a frequency distribution where scores are placed in various groups rather than being listed individually |
|
|
Term
|
Definition
| the scores or values placed together in one grouping |
|
|
Term
|
Definition
| a display where each axis represents a variable and each individual is represented by a point at the intersection of their scores on the two variables |
|
|
Term
| Although not always possible, a good guideline is to try to have at least --- times as many total values (N) as class intervals |
|
Definition
|
|
Term
|
Definition
| a visual display made by connecting the dots with a continuous line rather than drawing bars |
|
|
Term
|
Definition
| the first part of a score in a stem-and-leaf plot |
|
|
Term
|
Definition
| the more formal name for the horizontal axis on a scatter plot |
|
|
Term
|
Definition
| the number of values at a given scale point in a grouped frequency distribution |
|
|
Term
|
Definition
| one way to present interval or ratio data that involves breaking each score into two parts |
|
|
Term
|
Definition
| the total number of values at or below a given scale point |
|
|
Term
|
Definition
| vertical axis in a scatter plot |
|
|
Term
|
Definition
| graphical display that does not leave a space between the bars also good for displaying ratio data |
|
|
Term
|
Definition
| a display where each axis represents a variable and each individual is represented by a point at the intersection of their score on the two variables |
|
|
Term
|
Definition
| the percentile rank computed form a grouped frequency distribution that represents the score or person in that class interval |
|
|
Term
|
Definition
| display that is good for showing nominal or ordinal data |
|
|
Term
|
Definition
| visual display that is an alternative to bar charts with nominal or ordinal data |
|
|
Term
|
Definition
| the last part of a score in a stem-and-leaf plot |
|
|
Term
|
Definition
| grouped frequency distributions should have around this many class intervals |
|
|
Term
|
Definition
| the "middle" or "center" of a group of scores. also a primary feature of data distributions and the one that is typically described first |
|
|
Term
|
Definition
| how "spread out" or "dispersed" the scores are relative to the center of a distribution. Also an essential component of data description, and is a close companion to central tendency |
|
|
Term
|
Definition
| how a distribution of data looks when plotted as a frequency distribution. also is one of the most important yet often overlooked aspects of research |
|
|
Term
|
Definition
| the mathematical average of a group of score or values |
|
|
Term
|
Definition
| the difference between any individual score and the mean of the distribution |
|
|
Term
|
Definition
| the score that is at the 50th percentile point in a distribution |
|
|
Term
|
Definition
| a score for which the value is unknown, often the result of a task that the person could not complete outright or within the allotted time. |
|
|
Term
|
Definition
| a characteristic which is measured with specific values up to a certain point and then with a summary category for all remaining values |
|
|
Term
|
Definition
| the most frequently occurring score ina distribution |
|
|
Term
| Full Information Approach |
|
Definition
| properties of data where every score is used in the computation. |
|
|
Term
| Limited Information Approach |
|
Definition
| properties of data where not all of the scores are used in the computation, which can be advantageous in certain situations |
|
|
Term
|
Definition
| when the extreme score is on the high side of the scores |
|
|
Term
|
Definition
| when the extreme score is on the low side of the scores |
|
|
Term
|
Definition
| an extreme score that is present on one side of a distribution |
|
|
Term
|
Definition
| a common visual technique for detecting outliers that involves identifying the middle 50% of the data |
|
|
Term
|
Definition
| a mean computed such that some values are given more influence or weight than other values |
|
|
Term
|
Definition
| a range of values that a given parameter is likely to fall within, at least to a reasonable degree of certainty |
|
|
Term
|
Definition
| Letters used to denote population characters |
|
|
Term
|
Definition
| acronym to help remember the three measure of central tendency |
|
|
Term
|
Definition
| the average squared distance the scores in a distribution are from the mean |
|
|
Term
|
Definition
| the square root of the average squared distance the scores in a distribution are from the mean |
|
|
Term
|
Definition
| a sample statistic that, on average, does not return the corresponding value in the population |
|
|
Term
|
Definition
| a sample statistic that, on average, does return the corresponding population parameter |
|
|
Term
|
Definition
| the range of values encompassing the middle 50% of a distribution |
|
|
Term
|
Definition
| the range of values encompassing one of the two middle 25% segments of a distribution, either from the 25th to the 50th percentile or from the 50th to the 75th percentile |
|
|
Term
|
Definition
| the range computed after an extreme value, one that does not fit with the general trend of the rest of the date, is removed |
|
|
Term
|
Definition
| Formulas that do not show the inner nature of the standard deviations ad variance, but rather provide an efficient means to compute them |
|
|
Term
|
Definition
| formulas that show how the standard deviation and the variance operate mathematically |
|
|
Term
|
Definition
| acronym that can be used to help remember the three measure of variability |
|
|
Term
|
Definition
| one of the three measure of variability that is the most sensitive to extreme scores. also a limited information approach |
|
|
Term
|
Definition
| the number of areas in a distribution with a heavy concentration of scores, which is a key aspect of the characteristic being studied because one with a single area of concentration is very different than one with two or most such areas |
|
|
Term
|
Definition
| a graphical display with a continuous line showing the frequency to which various scores in a distribution occurred. it shows the same data as the frequency distribution from which it was created, just in a different way. |
|
|
Term
|
Definition
| the degree to which the pattern of frequencies for one half of a distribution is a mirror image of that for the other half |
|
|
Term
|
Definition
| a condition where there are a small number of extreme values residing on one side of a distribution |
|
|
Term
|
Definition
| how quickly the frequency drops off as you move away from the center of a distribution |
|
|
Term
|
Definition
| a specific form of kurtosis, one in which the frequency drops quickly as you move away from the center of a distribution |
|
|
Term
|
Definition
| a specific form of kurtosis, one in which the drop in frequency is gradual as you move away form the center of a distribution |
|
|
Term
|
Definition
| a specific form of kurtosis where the drop in frequency is gradual as you move away from the center, then steep, and then gradual again |
|
|
Term
|
Definition
| distribution that has three distinct peaks |
|
|
Term
|
Definition
| the informal name for a mesokurtic distribution |
|
|
Term
|
Definition
| distribution that looks somewhat like the top-end portion of a normal curve |
|
|
Term
|
Definition
| occurs when the center is closer to one end of a scale with fixed limits |
|
|
Term
|
Definition
| changing the way a set of data looks without changing the basic properties of that data |
|
|
Term
|
Definition
| resulting values when a distribution is transformed to have a mean of zero and a standard deviation of one |
|
|
Term
|
Definition
| the number of standard deviations that a score is away from the mean of its distribution |
|
|
Term
|
Definition
| the number of standard deviations that a score is away from the mean of its distribution |
|
|
Term
|
Definition
| a transformation based on percentile rank where each grouping of 10% of the scores (e.g. 10-20) is assigned a number from 1 to 10. |
|
|
Term
|
Definition
| score that is one standard deviation above the mean |
|
|
Term
|
Definition
| the height of a curve at any scale point that represents to which that point occurred |
|
|
Term
|
Definition
| found in the range bounded by the mean plus two standard deviations on the high side and the mean minus two standard deviations on the low side |
|
|
Term
|
Definition
| the percent of scores below a given score |
|
|
Term
|
Definition
| one half of a normal distribution |
|
|
Term
|
Definition
| % of sores found in the range bounded by the mean plus and minus one standard deviation |
|
|
Term
|
Definition
| % of scores in a normal distribution will fall between the mean and two standard deviations on either side of it |
|
|
Term
|
Definition
| the process of forming conclusions about a population based on results of studying a sample taken from it |
|
|
Term
|
Definition
| condition where the sample that is being tested is different in distinct and identifiable ways from the population to which an inference is being made |
|
|
Term
|
Definition
| the condition where the sample that is being tested is not totally representative of the population to which an inference is being made due to random chance in the sampling process |
|
|
Term
| Null Hypothesis Significance Testing |
|
Definition
| one of two major methods for making inferences about populations based on sample data |
|
|
Term
|
Definition
| formal statement that there is no effect of difference in the population for the characteristic being studied |
|
|
Term
| Two-Tailed Alternate Hypothesis |
|
Definition
| a prediction that there is an effect or difference in a target population, but without reference to the specific direction or nature of that difference |
|
|
Term
| One-Tailed Alternate Hypothesis |
|
Definition
| prediction that incorporates a specific direction for the effect or difference |
|
|
Term
|
Definition
| a single value which summarizes the results of a given reseach study |
|
|
Term
| Standard Error of the Mean |
|
Definition
| the denominator of the z (and t) test statistic for a one-sample test |
|
|
Term
| Critical Value of a Test Statistic |
|
Definition
| the value of a test statistic that corresponds to a specified level of chance probability |
|
|
Term
|
Definition
| the critical level of probability at which we change our inference from the absence of an effect in the target population to the presence of an effect |
|
|
Term
|
Definition
| a concept from basic math referring to the number of scores that are free to vary after some critical feature of a group of numbers is specified |
|
|
Term
|
Definition
| occurs when a researcher incorrectly concludes there is an effect in the target population when in reality there is not. only applicable when the null hypothesis is rejected |
|
|
Term
|
Definition
| when a researcher incorrectly concludes there is not an effect in the targe population when in reality there is one. only applicable when the null hypothesis is retained |
|
|
Term
|
Definition
| the capability of a study to reject the null hypothesis correctly when there is a true effect or difference in the population |
|
|
Term
|
Definition
| the actual value does not meet or beat the critical value |
|
|
Term
|
Definition
| the symbol for the probability of a Type II Error |
|
|
Term
| Independent Two-Sample Design |
|
Definition
| comparing one group of subjects directly against another group of subjects to determine if the characteristic that differentiates the groups makes a difference |
|
|
Term
|
Definition
| a technique for picking subjects where each one has an equal chance of being selected |
|
|
Term
| Repeated Measures Two-Sample Design |
|
Definition
| testing the same group of subjects twice, once under each condition of the experiment |
|
|
Term
| Standard Error of the Difference |
|
Definition
| the standard error component in the two-sample design |
|
|
Term
|
Definition
| an experimental treatment that looks real but in actuality is not |
|
|
Term
|
Definition
| the group of subjects who do not get the true experimental treatment |
|
|
Term
|
Definition
| the group of subjects who get the real treatment in a study |
|
|
Term
|
Definition
| an experimental design that allows you to include three or more samples in the same experiment |
|
|
Term
|
Definition
| a measure of how dispersed the scores are inside the samples or conditions of an experiment |
|
|
Term
|
Definition
| a measure of how much dispersion there is in the means of the samples or conditions of an experiment |
|
|
Term
|
Definition
| the overall mean of the scores in an experiment collapsed across the various samples or conditions being tested |
|
|
Term
|
Definition
| procedures that help identify which samples in a research study come from and represent a different population than the other samples |
|
|
Term
|
Definition
| statistical procedures that focus on estimation of one or more population parameters and requires interval or ratio data |
|
|
Term
|
Definition
| statistical test designed to handle frequency (i.e.,nominal) data, which typically involve few if any assumptions |
|
|
Term
|
Definition
| most common nonparametric test |
|
|
Term
|
Definition
| the number of observations tat would occur in a given category if there were absolutely no differences among the categories |
|
|
Term
|
Definition
| a procedure which compares observed results against a set of expected results to determine if they represent the same or different populations |
|
|
Term
|
Definition
| a mathematical index that indicates the strength and direction of the association between two variables |
|
|
Term
|
Definition
| the variable that is being used to predict the other variable in a correlation analysis |
|
|
Term
|
Definition
| the variable that is being predicted by the other variable in a correlation analysis |
|
|
Term
|
Definition
| the deviation score for the first variable multiplied by the deviation score for the second variable |
|
|
Term
|
Definition
| the degree to which scores on one variable follow a consistent pattern in relation to the other variable, either positive or negative |
|
|
Term
|
Definition
| an inferential technique that allows you to derive characteristics of a population by mathematically combining results from a group of existing studies |
|
|
Term
|
Definition
| a test statistic used in meta-analysis. denoted as d, it reflects the degree to which the mean of one group is different from the mean of another group (e.g., experimental versus control) |
|
|
