Exam 4 Flashcards
content analysis
-the systematic, objective, quantitative analysis of message characteristics
-Helps us learn about pop cultures & mass media
-goal is to develop inferences from text
Geographic information system (GIS)
software tool that made crime mapping available to police & researchers
Inter-University Consortium for Political and Social Research (ICPSR)
-1 of the largest networks for secondary data
-pro: researcher doest need money or time to collect data
-Con: researcher has no say in what info is available in the dataset. Stuck with what you get!
Bivariate analysis
describes 2 variables and their association (hence “bi”)
Descriptive statistics
used to summarize and describe data in manageable forms
Equation for the mean
x bar = the symbol for the sample mean
X= the value for every case in the sample
Sigma= summation symbol (literally just means “add this up)
N= the total # of cases in the sample
Frequency distributions & how to calculate percentages
Frequency distribution: a description of the # of times the attributes of a variable are observed in the sample
Inferential statistics
-help researchers form conclusions about their observations; involves forming conclusions about a population from the study sample drawn from it
Mean & how to calculate it
-The arithmetic average in a dataset
-The most common measure of central tendency
-The sum of all values in a group divided by the # of observations in that group
-Highly influenced by outliers
- Add up all the #’s then divide by the total # of cases
Measures of central tendency
mean, median, mode
Median & how to calculate it
-The midpoint in the ranked distribution of attributes
-Represent the middle value. So, half of the values are above it, half of the values are bellow it
-Values must be arranged in rank order to correctly identify the median
-To calculate the position of the median:
(N +1) / 2
“N” is the total numbers of cases
If the dataset contains an even number of cases, the median is the average between the 2 middles case values
Mode & how to calculate it
-Most frequently occurring attribute of category in a set of scores
-No formula
Multivariate analysis
describes the relationship between 3 or more variables (hence “multi”)
N =
the total number of cases in the sample
Outlier
a source that is extremely low or high compared to the rest
Range
Distance between highest and lowest scores in a set of data.
Sample mean symbol
x-bar (x̄ )
Sigma symbol
∑
Univariate analysis
describes a single variable (hence “uni)
X =
the value for every case in the sample
Bimodal distribution
a frequency distribution having two different values that are heavily populated with cases (two peaks)
equation for standard deviation
the square root of the variance
Equation for variance
SD^2= sigmaE(x-m)^2/N
Kurtosis
how flat or peaked a normal distribution is
Measures of dispersion AKA measures of variability
- Range
- Variance
- Standard Deviation
Multimodal distribution
Two or more peaks in a distribution curve
Negative kurtosis
Many values are far away from the mean/median/mode (flatter)
Mastered (4)
You’ve been getting these terms right!
Select these 4
Comparative methods research
-Comparing data from different geographical entities
-Studies the structure, nature, & scope of nations’ criminal justice systems
Crime mapping
geographical mapping strategies used to visualize things like location, distance, & patterns of crimes
Freedom of Information Act (FOIA)
federal law that stipulates all persons have a right to access any federal agency records (unless those records are exempt)
Historical events research
-when documents from one time in the past (such as letters, newspapers, or trial transcripts) are analyzed
-Used when you want to develop theoretical explanations of historical events & processes, not just detailed descriptions of events
Not studied (29)
You haven’t studied these terms yet!
Select these 29
Negatively skewed distribution
the median is larger than the mean
Nominal variables
variables measured in monetary units
Positive kurtosis
indicates a relatively peaked distribution
Positively skewed distribution
A distribution where the scores pile up on the left side and taper off to the right.
Standard deviation
the square root of the variance
Symmetrical distribution
A distribution where the left-hand side is a mirror image of the right-hand side.
Symmetry vs. skewness
A symmetric distribution is one in which the 2 “halves” of the histogram appear as mirror-images of one another. A skewed (non-symmetric) distribution is a distribution in which there is no such mirror-imaging.
Unimodal distribution
A distribution with one peak
Variance
standard deviation squared
Bar chart
-> Contains solid bars separated by spaces
-> Displays the frequency (y-axis) for different attributes of a variable (x-axis)
-> Use within nominal or ordinal level data
-> More appropriate than pie charts when variables have several categories (6+)
-> Can display the rank-ordered attributes of ordinal level variables, for example:
Education
Likert scales
Frequency distributions with interval groups
-Categories should be mutually exclusive and exhaustive
- 1st Interval -> must have the lowest value
- Last interval -> must have the highest value
- The “width” of intervals should be the same in each category
Histograms
-> A histogram is simply 1 way to represent a frequency distribution
-> Similar to a bar chart, but there are NO spaces between the bars
-> Appropriate for interval/ratio level (continuous) variables, such as age or years in prison
-> Y axis: left side (frequency)
-> X Axis: (bottom) attributes for continuous variables
Line graph
-> Line graphs plot values of a variable over time
-> line graphs are useful for describing trends in data
Longitudinal data -> measurements repeated overtime
Pie chart
-> Useful for presenting nominal level data like:
Race/ethnicity
Marital status
Crime type
Geographical location
-> Best when there are fewer than 5 attributes or categories
-> Presents the data based on percentages
-> The entire “pie” represents 100% and each of the “slices” represents each attribute’s contribution to the total
Grouped Bar Charts
->Grouped bar charts are useful for showing information about different subgroups
Cells in a crosstab
-Simple way of representing a bivariate distribution; similar to a frequency distribution table, but with 2 variables instead of 1
-Displays the distribution of 1 variable for each category of another variable. We are interested in the overlap of both variables
-Usually used for nominal and ordinal level data
-Essentially, it’s a special table with several cells & percentage calculated
-Cells = the “box at the intersection of rows & columns
-Referred to as “R X C tables” where R is the # of rows and C is the # of column → “ # of Rows by # of Columns Contingency table”
Column marginals
Crosstab AKA contingency table
-Crosstab AKA cross-tabulation AKA contingency table
Called a contingency table b/c they values of the DV are contingent on the values of the IV
How to calculate percentages in a crosstab
1). Divide each cell value by its own column total
(example) If we want to know # females with As, then divide 8 by 60 = 0.1333
2). Multiply that by 100 (or move two decimal places to the left)
(example) 0.1333 x 100 = 13.33%
Combined frequency display
a table that presents together the distributions for a set of conceptually similar variables with the same response categories
Compressed frequency display
a table that presents data efficiently by eliminating unnecessary percentages
First step to writing effectively
Principles of writing effectively:
1) start with an outline!
2) you will rewrite & reorganize; your 1 st draft will not be polished
3) leave enough time for dead ends, restarts, revisions, & accept the fact that you will throw out some of what you initially wrote
4) write quickly; leave the polishing for later
5) ask people you trust for reactions
6) write as you go along; so you will have pieces of notes & reports drafted already
Participatory action research (PAR)
the researcher involves some organizational members as participants during the research process of studying an organization; the goal is to make relevant changes
Peer review process
a process in which a journal editor sends a submitted article to 2 or 3 experts who judge the paper; the experts provide comments & explain their decisions
Plagiarism
presenting the ideas or words of another person as if they are your own without proper acknowledgement
Research report goals
1) Advance scientific knowledge
2) Shape social policy
3) Organize social action
Reverse outlining
outlining the sections in an already written draft to improve its organization for the next draft
Standard sections of a journal article
Thesis committee
-one chairperson and two members
-Need to make 3 professors happy with differing perspectives & comments (can be tough!)
- Committee members should have complementary areas of expertise: maybe 1 methodologist, 1 specialist in a primary substantive area, & 1 specialist in a secondary area
