Types of Research

1
Types of Research

• Types of Questions
• Time in Research
• Unit of Analysis

2
Types of questions/research

• Descriptive
• Relational
• Causal

3
Descriptive

• When a study is designed primarily to describe
  what is going on or what exists
• Public opinion polls that seek only to describe
  the proportion of people who hold various
  opinions are primarily descriptive in nature
• For instance, if we want to know what percent of
  the population would vote for a Democratic or a
  Republican in the next presidential election, we
  are simply interested in describing something

4
Food preferences
5
Descriptive
Sources Rape (excluding sexual assault),
robbery, and assault data are from the National
Crime Victimization Survey (NCVS)
6
Relational research

• When a study is designed to look at the
  relationships between two or more variables
• A public opinion poll that compares what
  proportion of males and females say they would
  vote for a Democratic or a Republican candidate
  in the next presidential election
• As such, this research is studying the
  relationship between gender and voting preference

7
Food preferences (relational research)

• Males

• Females

8
Relational research
9
Source Census Bureau, http//www.census.gov/popul
ation/www/socdemo/hh-fam.html
10
(No Transcript)
11
Note The solid area (in blue) represents the
trend for the entire United States while the
lines (in red) are the trends for each region
12
Dangerous Times and Places for Homicide and
Aggravate Assault

• Homicide
• Evening hours (6pm-6a.m) (70)
• Weekends (39)
• Home/residence (35)
• Street/alley (39)
• Vehicle (10)
• Commercial places (6)

• Aggravated Assault
• Evening hours (6p.m. midnight) (49)
• Within 1 mile of residence (54)
• Streets/parking lots (34)
• In or near victims home (28)
• Schools (5)
• Home of friend/relative/neighbor (9)

13
Victim profile in homicide and aggravated assault

• Homicide victims
• Male (76)
• White (50) African american(48)
• 13-24 years old (32)
• Same race of victim and offender (89)
• Single and never married (54)
• Urban resident (54)
• Employed (56)
• High risk occupations
• 1. Taxicab driver and Chauffeurs
• 2. Police/Law enforcement officials
• 3. Hotel clerks
• 4. Garage service station employee
• 5. Stock handlers and baggers

Aggravated assault victims Male (68) White
(77) African american(19) 16-24 years (17 per
100,000) Never married (13 per 100,000) Divorced/S
eparated (13 per 100,000) Family income lt7,500
(20 per 1,000) Urban resident (11 per
1,000) One-Victim incident (90) Victim tried to
protect self (74) Victim physically injured (25)
14
Causal research

• When a study is designed to determine whether one
  or more variables (e.g., a program or treatment
  variable) causes or affects one or more outcome
  variables
• If we did a public opinion poll to try to
  determine whether a recent political advertising
  campaign changed voter preferences, we would
  essentially be studying whether the campaign
  (cause) changed the proportion of voters who
  would vote Democratic or Republican (effect)

15
Domestic violence

• Unfortunately, domestic violence against women is
  common
• It happens to teenage girls and women of all
  backgrounds
• As many as 4 million women suffer abuse from
  their husbands, ex-husbands, boyfriends or
  intimate partners in the United States each year.

16
Breaking the cycle of violence is difficult

• The abuser strikes using words or actions.
• The abuser may beg for forgiveness, offer gifts
  or promise to change.
• The abuser becomes tense, angry or depressed.
• The abuser repeats the abusive behavior.

17
Police responses

• The most common police responses were to mediate
  the dispute, recommend a referral for counseling,
  or separate the parties.
• Arrest was a relatively uncommon action.

18
The Minneapolis Domestic Violence Experiment
(1983)

• Goal was to find the most
• effective strategy
• Three groups two with different treatments and
  one was a control group
• Police officers volunteering to take whatever
  action was dictated by a random system
  instruction in an envelope

19
The Minneapolis Domestic Violence Experiment
(1983)

• Three different instructions (1) arrest the
  suspect (2) separate or remove the suspect from
  the scene for 8 hours (3) advise and mediate

20
Minneapolis Domestic Violence Experiment
Experimental group I Arrest O1 X1 O2 19
Experimental group II Separate O1 X2 O2 33
Control group Mediate O1 O2 37

• Victims have been interviewed every two weeks for
  the next 6 months, police records have been
  monitored as well
• Most influential policy experiment
• Arrest works more effectively in deterring
  domestic violence

21
Time in Research

• Cross-sectional studies
• Longitudinal studies

22
What is a cross-sectional design?

• A research design where subjects are assessed at
  a single time in their lives
• In effect, we are taking a 'slice' or
  cross-section of whatever it is we're observing
  or measuring

23
What is a cross sectional design?

• Also, you don't have to worry about subjects
  dropping out during the course of the study
• This study is efficient at identifying
  association, but may have trouble deciding cause
  and effect
• With data at only one time point, you don't know
  whether the chicken or the egg came first

24
What is a longitudinal design?

• A research design where subjects are assessed at
  several different times in their lives
• Usually, you use this design when you are
  interested in how subjects change over time
• These studies are often expensive, difficult to
  conduct, and have lots of trouble without drop
  outs
• They also will require more complex statistical
  analyses.

25
Types of longitudinal designs

• Trend studies
• Cohort studies
• Panel data

26
Trend studies

• A trend study samples different groups of people
  at different points in time from the same
  population
• Suppose that 2 months before a year-long gun
  control campaign, a sample of adults is drawn
  64 report that they're in favor of a strict gun
  control regulation and 34 report that they are
  not
• A year later, a different sample drawn from the
  same population shows a change 75 report that
  they're in favor of gun control and 25 report
  that they are not. 

27
Cohort Studies

• A cohort is any group of individuals who are
  linked in some way or who have experienced the
  same significant life event within a given period
• There are many kinds of cohorts, including birth
  (for example, all those who were born in 1985),
  education/graduation, employment, family
  formation, etc.
• Any study in which there are measures of some
  characteristic of one or more cohorts at two or
  more points in time is cohort analysis

28
Cohort Studies

• Cohort analysis attempts to identify cohorts
  effects Are changes in the dependent variable
  (health problems in this example) due to aging,
  or are they present because the sample members
  belongs to the same cohort
• In other words, cohort studies are about the life
  histories of sections of populations and the
  individuals who comprise them

29
Graphical illustration of cohort study
30
Panel studies

• Panel studies measure the same sample of
  respondents at different points in time
• Depending on the purpose of the study,
  researchers can use either a continuous panel,
  consisting of members who report specific
  attitudes or behavior patterns on a regular
  basis, or an interval panel, whose members agree
  to complete a certain number of measurement
  instruments only when the information is needed
• In general, panel studies provide data suitable
  for sophisticated statistical analysis and might
  enable researcher to predict cause-effect
  relationships.

31
Panel studies

• Panel data are particularly useful in predicting
  long-term or cumulative effects which are
  normally hard to analyze in a one-shot case study
  (or cross-sectional study)

32
Example

• In the early 80s', the National Broadcasting
  Company supported a panel study in order to
  investigate the causal influence of violent TV
  viewing on aggression among young people
• The methodology in the study involved collecting
  data on aggression, TV viewing, and a host of
  sociological variables from children in several
  metropolitan cities in the US
• About 1,200 boys participated in the study and
  the variables were measured six times for 3 year
  study period
• The investigators concluded that there was no
  consistent statistically significant relationship
  between watching violent TV programs and later
  acts of aggression

33
Example

• The National Longitudinal Survey of Children and
  Youth (NLSCY) is a long-term study of Canadian
  children that follows their development and
  well-being from birth to early adulthood
• The study is designed to collect information
  about factors influencing a child's social,
  emotional and behavioural development and to
  monitor the impact of these factors on the
  child's development over time

34
Unit of Analysis

• One of the most important ideas in a research
  project is the unit of analysis. The unit of
  analysis is the major entity that you are
  analyzing in your study. For instance, any of the
  following could be a unit of analysis in a study
  
• individuals
• groups
• artifacts (books, photos, newspapers)
• geographical units (town, census tract, state)
• social interactions (dyadic relations, divorces,
  arrests)

35
Unit of analysis

• For instance, if you are comparing the children
  in two classrooms on achievement test scores, the
  unit is the individual child because you have a
  score for each child
• On the other hand, if you are comparing the two
  classes on classroom climate, your unit of
  analysis is the group, in this case the
  classroom, because you only have a classroom
  climate score for the class as a whole and not
  for each individual student.