Psy 190 Exam 1

A group of individuals from an area

A smaller group from the group of the population taken out

It could be as too small of a sample to accurately represent the full population. Not an actual actual "error"

(Summarize and describe data) Uses the data to provide descriptions of the population; either through numerical calculations, graphs, or tables

(From a sample to make conclusions about a population) Makes inferences and predictions about a population based on a sample of data taken from population in question

When it's not as obvious. They are separate and distinct categories with no values in between. Only particular values.

Ex: the # of kittens in a litter, # of threads in the sheet, # of stars given for an energy rating (you can measure continuous data)

An infinite number of possible values fall between any two observed values

Ex: are you really 4'11" or are you more like 4'11.3" and you round it down.. ? etc.

Defined as a relationship between two variables. Whole purpose is to figure out which variables are connected

Involves manipulating one variable, to determine if changes in one variable cause changes in the another variable(s)

(Irrelevant or unrelated to the subject being dealt with variables) related to individual characteristics of each participant

Ex: background differences, mood, anxiety, intelligence

Factors that exist in an individual's physical environment

Basically dependable or with consistency

If it did what it was meant to do.

Basically accurate or correct.

The one you're manipulating, or altering

Ex: Pen color

What you measure (from independent variable).

Of the Independen variable that is being changed

Ex: Pen color variation

Both participant & environmental variables.

Control & manipulation

Gender, age, intelligence, race, etc.

Correlational research would be used for this since you cannot manipulate it, & experiments require manipulation

The end result you are trying to get out of the experiment.

Ex: Amy measures academic success with sleep and parental support; the operational definition would be the graduation rate of the students being studied

(Involves names)

Names DO NOT relate to any quantity

(Involves names)

Names relate to a quantity and CAN be ordered

(Involves numbers)

Involves equal-sized categories with an arbitrary zero value; zero DOESN'T mean zero)

Ex: On a scale from 1 to 10

(Involves numbers)

Involves equal size categories were zero DOES mean zero

Ex: 0 lbs.

Two or more subjects in comparison

Subject(s) compared to themselves

No.

Yes.

The first variable

(The variable being examined in general)

If there is more than one; the second variable being examined

The population

The sample

Summation/the "sum of"

X= variables/subjects

F= frequency of "x," or the variables/subjects

Table with an "x" column & "f" column used to organize data

Table with an "x" column & "f" column used to organize data, BUT the variables in "x" are grouped (ex: 9-11) since there are so many/there is great gaps in between numbers

10

It should be easy to deal with; as 2, 5, 10

The numbers of "x," or the variables, grouped

Ex: 6-8

Ex: Let's say there are 5 intervals and we are counting from 50 to 54:

We count "50, 51, 52, 53, 54"

45-49

50-54

55-59

(No over lap)

-(& bottom score of each interval should be a multiple of the width, say your interval # is 5, then the bottom scores should be like 15, 20, 25)

Grouped Frequency Distribution Tables

Not by how many subjects you have, BUT the value amounts between the subjects determine which you use

By:

+Subtracting the largest number, by the smallest number

+Then, dividing the result of that by 10

(10 bc remember that is the number of approximate best interval rows)

+Then, determining which the answer from these above steps is closest to (1, 2, 5, or 10)

After, with this, we figure out our ideal interval size for the data

Histogram & Polygon

A Polygon is more technical (As 5.5 on data), & a Histogram is more whole numbers. Polygon is continuous data & helps predict other values, whereas Histogram is discrete data

The diagonal line represents the trend; & the dots are the information the researchers gathered from their variables

Goes from left down, to up center, & back down towards right

(Pg. 17)

Starts high-ish from left, & goes down, down, down towards right

(Pg. 17)

Starts high-ish from right & goes down, down, down towards left

(Pg. 17)

The ending lower part of the graph

Ex: right side of a positively skewed distribution graph, & left side of a negatively skewed distribution graph

When the scores cannot go any higher due to some constraint

When the scores cannot go any lower due to some constraint

The Floor Effect

The Ceiling Effect

the Positively Skewed Distributions

Negatively Skewed Distributions

Nominal variables

Data with 2 subjects of the variables collected (& a lot of #s of info)

Ex: Height & Weight (scatter plot) vs. Exam scores (bar graph)

Histograms are connected & nothing but numbers.

Bar Graphs are not connected, bc each nominal subject is an individual, & since is nominal, is names on bottom & numbers to match on side

Add up all numbers of data, & divide by how many numbers data there are

(ORGANIZE #s by numerical order)

It is the middle number.

If two middle numbers, add the two middle numbers & divide by 2 (bc there are two numbers)

The number that appears the most

Population

Sample

The Mean is affected more

The Mean is affected more

Always, yes.

It sometimes changes. Although, if you have the same number as a Mean, it wouldn't change

You list one of the major Mode and the other has the minor Mode

Extreme scores that are either way lower or a way higher than the other scores in the sample

(Most of the time, an error in data. Someone fell asleep, meets un-usual circumstances, etc.)

Ex: 15, 17, 13, 11, 19, 13, 17, 45

Outlier= 45

It would get lower

(for the Mean)

Mean

(Use as the default calculation)

When the outlier is unavoidable

For Nominal data

A numerical way of describing the spread to a distribution

(How spread out your data is)

Range, Variance, & Standard Deviation

By subtracting the top score, from the bottom score

+Write down the "x" variable column on the Frequency Distribution Table

+Then, subtract the "x" variables by the Mean of the "x" data itself

(X-M)

+Then, square the answers

(of the data subtracted from the Mean of itself)

(X-M)^2

+Lastly, take the Mean of the remaining answers of data

(of the data subtracted from the Mean of itself, & squared)

(X-M)^2 <--M

+And that's the variance. That is how you measure the spread of variability with variance

+Find variance

[+Write down the "x" variable column on the Frequency Distribution Table

+Then, subtract the "x" variables by the Mean of the "x" data itself

(X-M)

+Then, square the answers (of the data subtracted from the Mean of itself)

(X-M)^2

+Lastly, take the Mean of the remaining answers of data(of the data subtracted from the Mean of itself, & squared)

(X-M)^2 <--M]

+Lastly, just Square Root the answer to the variance. And, that is how you find the spread of variability with standard deviation.