Psych 209 Exam 1

For a variable on the nominal scale, which central tendency?

mode

qualitative variable

varies by *class* represented as a *label*, describes *nonnumeric data* ex: socioeconomic class(lower, middle, upper)

The z distribution is normally distributed with a mean of 0 and a standard deviation of ____

1

Since the normal curve never actually touches the horizontal axis (i.e., the tails are asymptotic)

very extreme observations are possible

real range

*ONE MORE THAN* difference between largest and smallest number, ex range:7 real range: 8

experimental method

*Randomly assigning to different groups* to ensure that *manipulations of the independent variable* are *measured on similar groups* is necessary in

normal distribution

*bell shaped* scores are *symmetrically* distributed and below the mean

population parameter

*characteristic*(usually numeric) that *describes a population*

weighted mean

*combined mean* of two or more groups of scores in which the number of scores in each group is disproportionate or unequal.

histogram

*continuous data* (heights, temperature, time in months) can be measured in *fractions and decimals*

bar graphs

*discrete, whole units*, bars or categories, are spread out(ethnicity, amount of family members, number of naps)

ogive

*dot and line* used to summarize cumulative percents

skewed distribution

*includes outliers* that fall above or below the mean

quasi experimental

*preexisting* variable that is often characteristic inherent to individual, *differentiates* the groups or conditions being compared in research study. *not possible to randomly assign groups* Ex: A researcher studies the *development of cognitive flexibility* by testing children of *different age groups on a problem-solving* task. This is an example of a:

intervals

*scores of groups*, discrete range of values

central tendency

*statistical measurements* locating a single score that is most representative or descriptive of all scores in a distribution (mean, median- preferred used when there are a lot of outliers, mode)

simple frequency distribution

*summary display* for 1. frequency of each individual score or categorized in a distribution 2. frequency of scores *falling with defined groups* or *intervals* in a distribution

ordinal; bar graph

A researcher is interested in getting some background information about mothers in her study. The data for mothers' education level is measured by asking them to select whether they completed: (1) some schooling, (2) high school, (3) associate's degree, or (4) college degree or higher. This data would be considered measured on the _________scale and can be displayed using a _____________.

not likely (i.e., atypical)

If data are *more than 2 standard deviations* away from the mean, they are considered

interval width

In a simple frequency distribution, to determine _______________, we divide the observed range of data by the number of intervals, *real range/# of intervals*

nominal scale

Measurements which a *number is assigned* to represent *someone or something* Ex: Data from airline passengers were ranked by their *country of origin*

Interquartile Range

Q3 - Q1, obtain a distribution with a handful of *very extreme scores that cause you concern*, which measure of variability would be the most helpful?

semi interquartile range

Q3-Q1/2, measure half distance

cumulative frequency

SUMmary display that distributes sum of frequencies across series of intervals, *add up frequencies* pg 38 in textbook, bottom to top

what will result in no change to the value of the mean?

adding a score exactly = to the mean

correlational method

can determine if there is a *relationship existing between variables*, lacks controls needed for cause and effect Ex: Is children's vocabulary related to their parents' education level? To answer this, researchers measured the number of words 3-year-old children knew, and their parents education (in number of years).

sample statistic

characteristic, *usually numeric* describes a sample.

negative skewed

everyone has *higher scores*, want exam scores to be like this *peak on right side*

sum of squares (SS)

for *population variance*- measure of variability for average squared distance that scores in population deviate from mean SS/N,

probability

frequency of times *outcome occurs* divided by total number of possible outcomes

interval scale

have *NO TRUE ZERO* distributed in equal units ex: In blinded studies, consumers' rankings of the effectiveness of brand name painkillers *did not differ from generic painkillers* that had the same key ingredients, on a *5-point scale*.

ratio scale

have a *TRUE ZERO* and are distributed in = units.

For data on an interval or ratio scale, which central tendency is preferred?

mean

variability

measure of the dispersion or *spread of scores* ranges from 0 to infinity

sample variance

measure of variability for average squared distance that scores in a *sample deviate* from the mean SS/n-1

variance

measure of variability for average squared distance that scores in a population deviate from the mean

continuous variable

measured along a continuum at *any place beyond the decimal point*, and can be positive *(e.g., height)* or negative *(e.g., temperature)* in value.

discrete variable

measured in *whole units* not distributed along a continuum ex: number of siblings you have

ordinal scale

measurements convey *order or rank alone* RANKING ex: Listeners to a specific radio station were asked to *rank one hundred songs for popularity.*, not equidistant range such as 0-20, 21-40, more than 80

For data that falls on skewed distribution with outliers, what central tendency is preferred?

median

positive skewed

more people fall on *lower end* *peak on left side*

Inferential Statistics

procedures used that *allow researchers to infer or generalize observations* made with *samples to the larger population* from which they were selected. Example: A librarian at a university is interested in looking at how many undergraduate students use the library. He records *student use of different library resources in one month* and *extrapolates* this information for the *year-round usage*

Descriptive Statistics

procedures used to *summarize, organize, and make sense of set of scores*, typically presented *graphically, in tables or single values*. Example: A librarian at a university is interested in looking at how many undergraduate students *use the library*. He *records student use* of different library resources and *tabulates this usage*

relative frequency

put in a *proportion* then percentage

population

set of *all individuals, items, or data of interest*

grouped data

set of scores *distributed into intervals*, where frequency of each score can *fall into any interval*

quantitative variable

varies by *amount* measured *numerically* and is collected by *measuring and counting* ex: calories we take in, pieces of food we eat

pie chart

summarize *relative percent* of *discrete and categorical* data

standard deviation

the *average amount* that scores deviate from either side of the mean

What measure of central tendency is sensitive to the effects of extreme observations?

the mean

interval boundary

upper and lower limits for each interval in a grouped frequency distribution

z score

value on x axis of a standard normal distribution, numerical value *specifies distance or number of standard deviations above or below the mean.* z= x-m/SD

true zero

when the value of *0* indicates nothing on a scale of measurement.