Typical Steps in Statistical Study

Identifying the question

 What is the question?  (What are my hypotheses?)

 Is it possible to answer the question with statistics?
 Is the data obtainable? (birth weight, socio economic, drugs, alcohol)
 Is it ethical to obtain such data?
 If not, is there a reasonable substitute?

Introduction:
The purpose of the introduction is to explain where your hypothesis comes from.
• Start with general theory, briefly introducing the topic.
• Narrow down to specific and relevant theory and research. One or two studies is sufficient.
• Leading logically into your aims and hypotheses.
• Do be concise and selective, it’s very tempting to put anything in case it is relevant.
• Don’t turn this introduction into an essay.
• Don’t spell out all the details of a piece of research unless it is one you are replicating.
• Do include any relevant critical comment on research, but take care that your aims remain consistent with the literature review. If
your hypothesis is unlikely, why are you testing it?
• Don’t include material more appropriate to the discussion or you won’t have anything left for that section.
• Write a paragraph explaining what you plan to investigate and why. Use previously cited research to explain your expectations.
• Include a justification of the direction of your hypotheses. This means explaining why it is one-tailed (e.g. ‘previous research
suggests that people remember more in the morning, therefore the hypothesis is one-tailed’) or two-tailed (‘previous research is
not clear which group will do better, therefore the hypothesis will be two-tailed’).
• Do understand that aims are not the same as the hypotheses.

Hypothesis: State the alternate hypothesis and whether it is one- or two-tailed. Make sure that this is unambiguous and
understandable to someone who has not yet read the rest of your report. You can write several sentences, such as ‘Participants in
condition 1 perform better than those in condition 2. Condition 1 involves words which are hierarchically organized and condition 2
consists of randomly organized word lists'.

 State the null hypothesis. This is a statement of ‘no difference’ or that any difference is due to chance factors alone. It is not
the opposite of the experimental hypothesis Are the assumptions reasonable?

Designing a Study

 Identify the population of interest

 Survey
o Obtain a representative sample of that population
 Simple Random Sampling
 Stratified Sampling (M-F, Age groups)
 Systematic Sampling (class roster, census list)
 Multi-Stage Sampling

o Sources of Bias
 Voluntary Response
 Non-response bias (day phone)
 Response bias (people lie)
 Under-coverage
  Observational Studies
o Used when a designed experiment is not ethical
o Subjects studied over a period of time in natural setting
o Case/Control – Control must match
o Record Variables of interest
o Confounding is a major issue
 Designing an Experiment
o Researcher has control over the subjects or units in the study
o An intervention takes place that otherwise would not occur
o Randomization used to assign treatments
o Strongest case for causality
 EDA – Exploratory Data Analysis (trends, relationships, differences)
 Pilot Study

Participants
 Identify the target population (refer to a geographic location) and type of sample. Say how you obtained your sample (e.g.
opportunity sample) and why you chose this sample. Give relevant details, e.g. how many, age range, background etc. If
appropriate, details of how participants were assigned to each IV group.

Materials
 Describe the materials used, e.g. pictures, word lists, instructions, debrief, record sheets etc. Give plenty of detail and explain
why you chose these things. Tell the reader they are in the appendix.

Procedure

 Describe the precise procedure you followed when carrying out your research i.e. exactly what you did. Anyone should be
able to copy what you did from this. Include the brief, standardize instructions and debrief – all word for word. Start with a
sentence like “Participants were approached in the college library and asked if….”

Collecting Data

 Identify variables
 Identify types of variables
o Qualitative
o Quantitative
 Identify Limits of measurement or observation

There are four main methods of data collection.

Census. A census is a study that obtains data from every member of a population. In most studies, a census is not practical, because of
the cost and/or time required.

Sample survey. A sample survey is a study that obtains data from a subset of a population, in order to estimate population attributes.

Experiment. An experiment is a controlled study in which the researcher attempts to understand cause-and-effect relationships. The
study is "controlled" in the sense that the researcher controls (1) How subjects are assigned to groups (2) Which treatments each
group receives.
Observational study. Like experiments, observational studies attempt to understand cause-and-effect relationships. However, unlike
experiments, the researcher is not able to control (1) how subjects are assigned to groups and/or (2) which treatments each group
receives.

Analyze the data

 Use proper procedures and techniques.

 Check the assumptions behind the procedures and techniques.

Goal of an analysis:

 To explain cause-and-effect phenomena

 To relate research with real-world event
 To predict/forecast the real-world phenomena based on research
 Finding answers to a particular problem
 Making conclusions about real-world event based on the problem
 Learning a lesson from the problem

Data can’t “talk”. Thus, analysis must contain scientific reasoning/argument:

Define Explain
Interpret Clarify
Evaluate Compare
Illustrate Contrast
Discuss

When analyzing:
Be objective True
Accurate Separate facts and opinion

Displaying Data:

Descriptions of the various graphs students will learn to make as they progress from the primary to the middle grades are listed below,
with examples:

 Bar Graph: Used when comparing various items or ideas.

 Histogram: Used to show frequency and compare items or ideas; each bar represents an interval of values.

 Line Graph: Used to show change over time.

 Pictograph: Used to show frequency and compare items or ideas.

 Circle Graph (or Pie Graph): Used to show parts or percentages of a whole.

 Box-and-Whisker Plot: Used to show the range of values as well as the median, quartiles, and outliers; five-number summary
is another name for this representation.

 Line Plot: Used to easily organize one group of data.

 Scatterplot : Used to determine if a correlation exists between two data sets, and how strong it is, also used to calculate line or
curve of best fit.

 Stem-and-Leaf Plot: Used to show frequency; data is grouped according to place value, using the digit in the greatest place.
  It is valuable for students to explore various ways to represent the same data. Students can determine which graph makes the
most sense to use and which graph can help them answer their questions most easily. For example, a favorite book survey can
be shown as a table, a bar graph, a circle graph and a picture graph. Students can discuss which representation most clearly
shows which book got the most votes or the difference in votes. Students can remove the least favorite book and vote again to
explore the change in data.

It is also valuable for students to understand that the same data is not always best represented in different ways. For example, line
plots, bar graphs, scatterplots, and stem-and-leaf plots are best used to represent numerical data. However, longitudinal data are
best represented by line graphs. Categorical data are not displayed in a specific order and most often are represented by line plots,
bar graphs, and circle graphs.

V.  Make Conclusions and Discuss Limitations

 What are the answers to the original hypotheses?

 What are the limitations of the study?
 What conclusions does the study not make?
 What new questions arise from this study?

Strategies for an effective Conclusion:

One or more of the following strategies may help you write an effective conclusion.

 Play the “So What” Game. If you’re stuck and feel like your conclusion isn’t saying anything new or interesting, ask a
friend to read it with you. Whenever you make a statement from your conclusion, ask the friend to say, “So what?” or
“Why should anybody care?” Then ponder that question and answer it. Here’s how it might go:

You: Basically, I’m just saying that education was important to Douglass.

Friend: So what?
You: Well, it was important because it was a key to him feeling like a free and equal citizen.
Friend: Why should anybody care?
You: That’s important because plantation owners tried to keep slaves from being educated so that they could maintain
control. When Douglass obtained an education, he undermined that control personally.

 Return to the theme or themes in the introduction. This strategy brings the reader full circle. For example, if you
begin by describing a scenario, you can end with the same scenario as proof that your essay is helpful in creating a new
understanding. You may also refer to the introductory paragraph by using key words or parallel concepts and images that
you also used in the introduction.
 Synthesize, don’t summarize: Include a brief summary of the paper’s main points, but don’t simply repeat things that
were in your paper. Instead, show your reader how the points you made and the support and examples you used fit
together. Pull it all together.
 Include a provocative insight or quotation from the research or reading you did for your paper.
 Propose a course of action, a solution to an issue, or questions for further study. This can redirect your reader’s
thought process and help her to apply your info and ideas to her own life or to see the broader implications.