Psych Test 1 Flashcards
Descriptive Statistic
Used to organize or summarize a set of data
Inferential Statistic
Used to make interpretations based on data
example: Which brand of cola do people prefer?
Sample
a small subset of a population that is
intended to be representative of the larger population
Population
a group of people or things that have
some critical characteristic in common
Raw Score
a datum point or value that has not been altered in any way. Raw scores are original measurements from surveys, tests, or other instruments that have not been weighted, transformed, or converted into any other form. Raw scores are also called observed scores.
Random Sampling
In principle, all members of the population are equally likely
to become part of the sample
* Hard to do this unless the population is small and manageable
Convenience Sampling
Sample from among individuals who are conveniently available to study
independent variable
A variable that the experimenter manipulates
example: suppose you want to know how the time to
find an object is affected by the number of other objects present
* IV = number of objects present
quasi-independent variable
A variable that the researcher thinks will predict scores on the DV, but that the researcher does not
manipulate
dependent variable
A variable that the experimenter measures
examples: Response time, Accuracy, Score on Depression Scale
continuous variable
A theoretically infinite number of values exist between adjacent units
example: reaction time, length, age
discrete variable
No values exist between adjacent units
* Data are typically whole numbers or category labels
* e.g., college major; number of correct responses on an exam; number of people in household
frequency distribution
Shows the number of times each score occurs within a data set
cumulative frequency distribution
is calculated by adding each frequency from a frequency distribution table to the sum of its predecessors. The last value will always be equal to the total for all observations, since all frequencies will already have been added to the previous total
percentile
values that divide a set of observations into 100 equal parts. The percentile rank is the proportion of values in a distribution that a specific value is greater than or equal to
percentile rank
?
scatterplot
Used to represent relationship between two measured variables
Bar Graph
Categories (levels of the independent variable) are located on the X axis
Histogram
Like bar graphs, but used to represent frequency distributions composed of interval or ratio data
- the bars touch each other
frequency polygon
Very similar to histogram
*Point is plotted at mid-point of each interval
*Points are joined with a line
*Extended to intervals just above and just below end
points of the distribution
positively skewed distribution
most of the scores are found at the
lower values
- looks like this: n___
negatively skewed distribution
most of the scores are found at the
higher values
- looks like __n
Mean
Score below which 50% of the scores in the distribution are found
* i.e., the median splits the distribution exactly in half
* Can be calculated in multiple ways
Median
Score located at the exact mathematical center of a distribution
* Calculated by adding all the scores and dividing by the number
of scores:
Mode
number that occurs the most often
Range
highest minus lowest score
Variance
is SD squared
Standard deviation
the amount by which a score differs from the mean
The scales that variables can be measured using:
nominal scale
ordinal scale
interval scale
ratio scale
Nominal Scale
used to indicate category membership only.
examples: hair color, occupation, major, preferred cuisine
Ordinal Scale
rank an order. they are also categories but they represent relative magnitudes
example: singing ability of favorite 5 artists
Interval Scale
each score represents an actual value
example: fahrenheit scale
can include zero but not a true zero
example: 0 degrees F foes not = the absence of heat
Ratio Scale
Similar to an interval scale, except that it contains a true zero, and does not contain negative values
ex: kelvin temp scale, exam score, length
- can make ratio statements: the length of A is twice the length of B
What is the difference between descriptive statistics and inferential statistics
Descriptive statistics describes sets of data.
Inferential statistics draws conclusions about the sets of data based on sampling.
Why do we study samples instead of directly studying populations?
quicker and more time efficient
What is the most important reason that we wish to learn about the properties of samples?
To draw inferences about the larger population. If this is true of the sample, then it is also likely to be true of the population.
What is random sampling, and why is it so important?
Random sampling ensures that results obtained from your sample should approximate what would have been obtained if the entire population had been measured. The simplest random sample allows all the units in the population to have an equal chance of being selected.
Why does one manipulate an independent variable?
To determine whether changing the IV has any effect on the DV.
Why do the bars in a bar graph not touch each other?
The intervals in a bar graph are not continuous
What are the advantages and disadvantages of the mode, the median, and the mean?
Mode: Adavantages- Can be used with nominal variables, represents a score that actually did occur w/in the data, a score picked at random from the data set would be more likely to be equal to the mode than any other single value. Disadvantages- Many scores in a distribution may have the same frequency, mode doesn’t take into account any other scores in the distribution.
Median: Advantages- Relatively unaffected by extreme scores in the distribution, useful in situations in which extreme scores are possible and have no real significance, sometimes more meaningful than other measures, requires no assumptions about interval properties of the scale. Disadvantages- Based on counts and not values of scores, difficult to manipulate algebraically, not very stable from one sample to another.
Mean: Advantages- Reflects all the scores in the distribution, tends to be a better estimate of the population mean, can be manipulated algebraically and included in other equations. Disadvantages- All scores in the distribution contribute to it.
Under what conditions might it be better to use the median than the mean to represent a
distribution?
The median is useful in situations in which extreme scores are possible, but have no real significance (highly skewed distributions).
How does the mean compare to the median when representing a positively (or negatively)
skewed distribution?
the median is better to represent skewed distributions
Why is the range typically not considered the best measure of variability?
It is the simplest and the least informative measure of variability. It is based only on the most extreme scores, so it is not very informative about the distribution.
Why can one not calculate standard deviation by simply summing the deviations of raw scores around the mean?
The sum of the deviation always equals zero, so the average deviation will always be zero. Also some deviations are negative.
