stats exam 1

Statistics

Refers to range of techniques and procedures for analyzing, interpreting, displaying, and making decisions based on data

Why do we study stats?

Communication in science and helps critically process info

Data

Represents measured value of variables

Variable

Characteristic or feature of thing we are trying to understand

Independent variable

Variable that is controlled

Dependent variable

Variable that is a measure of the effects of the IV

Qualitative variable

Variable that expresses a quality

Quantitative variable

Variable that gives a number or amount of

Coding

Part of qualitative variables where words are turned into a number

Two types of quantitative variables

Discrete, continuous

Discrete variable

Variable that cannot have intermediate or middle values (cannot have decimals)

Continuous variable

Value can be anything between the upper and lower limits (can have decimals)

Nominal scale of measurement

Categorizes items, no ordering

Ordinal scale of measurement

Categorizes and rank orders items, subjective and unequal intervals

Interval scale of measurement

Numerical scale with equal intervals, no absolute zero

Ratio scale of measurement

Scale that has equal intervals and has a true zero

Population

Collection of all people that have some characteristic in common

Sample

Small subset of population, used to generalize population

Simple random sampling

Requires every member of population to have an equal chance of being selected, independent sampling and may not always be representative

Stratified random sampling

Target population is divided into subgroups (strata) and random samples are taken from each subgroup

Convenience sampling

Use participants that are available, non representative

Experimental research

Uses random assignment for treatment conditions and manipulation of IV, uses both random assignment and random sampling

Quasi-experimental research

Getting as close to true experiment when true isn’t possible, manipulation of IV without random assignment, can’t determine causation

Non-experimental research

Correlational research, observing events as they occur naturally, finds relationship between variables but not causality

Descriptive stats

Number that conveys a characteristic of a set of data, summarizes a set of data with one number or graph

Inferential stats

Uses small sample and probability to make conclusions and inferences about larger unmeasured population, takes change factors

Frequency tables

All grains derived from these, shows frequencies of responses, can be done for all scales of measurement

Pie charts

Category represented by slice of pie, useful for small number of categories, not good for small sample sizes

Bar chart

X axis is names of variable categories, Y is frequencies, use when comparing distributions of responses

Stem and leaf plots

Numbers on left are stems and represent 10’s digit, right numbers are leaves

Histogram

Use with one distribution, shows shape, x axis is clsss interval midpoint values, y axis is frequency of scores, bars touching represents continuation of scores

Frequency polygon

Graphically displays shape of distribution, can be used with multiple sets of data, x axis is midpoint values, y axis is frequency

Box plots

Identifies outliers and compares distributions, shows range IQR, skew, median, mean

Line graph

Shows relationship between two variables

Symmetrical distribution

Mirror image of self, bell shapes

Bimodal distribution

Two distinct humps

Right/positive skew

Greater amount of low scores

Left/negative skew

Greater amount of higher scores

Central tendency

Type of descriptive stats that indicate a typical or representative score, show empirical data sets

Mean

Arithmetic average scores and values do numerical DV

Median

Point that divides a distribution scores in equal halves, hypothetical point

Mode

Score that occurs most frequently in a distribution

Mean < median

Left skew

Mean>median

Right skew

Variability

Refers to how spread out a group of scores is. Includes range, Interquartile range, sum of squares, variance, standard deviation

Range

Used to see how variable data is, can be used with ordinal, ratio, or interval

Interquartile range

Range of middle 50% of scores in distribution, communicates where bulk of scores lie

Percentile score

Point which a specified percentage of the distribution falls below

Sum of squares

How close the scores in distribution are to the middle of the distribution

Variance

Average squared difference of scores from mean, population or sample, exhibits more robustness than range

Standard deviation

Descriptive measurement of dispersion of scores around the mean, root of variance, tells width of distribution proportions of distribution near the mean and far from the mean