Psych Stats Test 1

how to format the title of your reference page

The paper's title should be centered, bold, and written in the title case. It should be three or four lines below the top margin of the page. In this sample paper, we've put three blank lines above the title.

Briefly describe why secondary sources (books, wikis, popular press articles) are not as reliable as primary sources (empirical journal articles)

They can misrepresent the original research. They can omit information on methodologies. They can ignore mitigating results. They can misinform.

Reverse coding a variable

Reversing the scoring of a variable (e.g. 5 becomes 1, 4 becomes 2, 3 stays 3 . . . etc).

In a univariate analysis, how many variables do we analyze at a time?

1

Code-in valid data that is unnecessarily missing

Ensuring that valid answers are not coded as missing, simply because the question was automatically skipped due to a previous answer.

Variable

A particular characteristic of the unit of observation.

Primary Source (Empirical Article)

An article that reports original research findings.

True/False: The title of your paper should be left-justified and in non-bold text.

False

In the default R settings, indicate where you would find each of the following R windows.

File window → Lower Right R script editor → Upper Left Global Environment → Upper Right Console → (Sometimes Lower) Left

Code out Missing Data

Getting rid of data that is genuinely non-valid (e.g. "don't know")

Exploratory data analysis (sometimes called descriptive analysis) is important because:

Summarized data are easier to interpret than raw data. It helps us to look for patterns in the data.

Binning a quantitive variable

Taking a quantitative variable and breaking it down into categorical "bins" for group comparisons (e.g. younger vs older adults).

Making a categorical variable into a quantitiave one

Taking a variable that has been unnecessarily "binned" and turning it back into quantitate values based on the description of the bins.

Response

The outcome/result The dependent variable

Data management

is the process of making decisions about your data (and cleaning up your variables).

Quantitative

numerical values or measurements. E.g. Height, weight, score on a test, amount of money, etc.

research plan outline

running head, author note, an abstract

If you want to cite two papers to support a single point, you can include both citations in a set of parentheses. What symbol do you use to separate the two citations?

semicolon

Three "steps in the research process" were described in the video. Briefly describe each one in one sentence each.

1. Producing data: choosing a sample and collecting data from it. 2. Summarizing the collected data: Exactly as it sounds! Summarize the data. It allows us to explore new ways to think about theta, refine questions, and reveal new questions. 3. Inference: Making conclusions about a population based on the data collected from a sample.

Sometimes, you can recode a variable from categorial into quantitative, to give you a more meaningful response. Which of the following would be an appropriate quantitative variable for the following statement. I smoke 2-3 cigarettes a day. ***NOTE: For our class, I would prefer that you NOT do this. Instead, find several categorical variables that you can add together (creating a secondary variable). ****

17.5 cigarettes a week (2.5 * 7)

Creating secondary variables

Creating a new value by performing an arithmetic calculations with two original variables.

Libraries or packages are

collections of R functions that others have written to add on to the basic functionality of R.

Sometimes, a variable is coded in the wrong direction. For example, in the add health wave IV dataset, the following question is coded the following way: "In general, how happy are you in your relationship with your partner? very happy fairly happy not too happy For any variable, the largest value should represent the greatest amount, strongest agreement (e.g. strongly agree), greatest quantity, etc. Therefore, in this case, which number in the scale should represent "very happy", the largest amount of happiness?

3. it's the greatest amount of happiness and therefore deserves the biggest number!

Data Set

A collection of information about individuals observations across variables. Rows represent units of observations. Columns represent variables.

Unit of Observation

A particular person, object, or case in your data set.

What is a secondary variable?

A variable that is derived from two ore more variables.

Secondary Source Article

An article that summarizes the work of others.

What is a literature review?

An examination of the body of work that has been written about a topic.

If a source has 3 or more authors, how should you cite them?

By listing only the first author's name followed by "et al."

Why is it important for you to conduct a literature review?

It will help you understand the theories of other researchers who have worked on your topic. It will help you understand the methodologies used by other researchers on your topic. It will tell you the current state of the knowledge on your topic. It will help you to refine your topic.

One thing we need to do with our data is "code for missing values." This means that we need to remove from a variable any values that we are not interested in and would like removed from the dataset. In R, what value do you give a data point if you want it to be treated as "missing?"

NA

Data

Pieces of information about a unit of observation (individual).

Explanatory

The independent variable The variable the experimenter manipulates The variable that is making the impact (the one we think might be doing the causing).

distribution

a representation of what values the variable takes and how often the variable takes those values.

We are interested in the average income of people living in the United States. Of the following, which sample is most representative of the population? Select one: a. Choosing individuals based on social security number. b. Placing a public questionnaire on Facebook. c. Polling college students. d. Placing an ad for a study on Craigslist and collecting data from people who respond to the ad.

a. Choosing individuals based on social security number.

Let's say you are doing a study to examine the political views of people living in Manhattan. You randomly call people in Manhattan from the phone book and ask them about which political party they plan to support in the upcoming election. Which of the following best represents your population and your sample? Select one: a. Population: All the people of Manhattan, Sample: The people you call. b. Population: The people you call, Sample: All of the people in Manhattan. c. Population: The people in the US, Sample: The people you call. d. Population: The people who live in Manhattan, Sample: The people who live in Manhattan.

a. Population: All the people of Manhattan, Sample: The people you call.

Which of the following are true about R? a. R is a programming language. b. R does NOT allow you to analyze data. c. R is a data analysis software d. R is an environment for statistical analysis.

a. R is a programming language. c. R is a data analysis software d. R is an environment for statistical analysis.

Which of the following provides the best definition of a population? Select one: a. The entire group that is the target of interest. b. A subgroup of your target of interest. c. The unique individuals that actually participate in your study. d. All of the people, objects, and organisms in the entire world.

a. The entire group that is the target of interest.

Which of the following are correct ways to cite a single author in your text? (select all that apply). a. Statistics is one of the leading fields of the decade. (Corrow, 2021) b. Corrow reported that statistics is one of the leading fields of the decade (2021). c. Corrow (2021) reported that statistics is one of the leading fields of the decade. d. Statistics is one of the leading fields of the decade (Corrow). e. Statistics is one of the leading fields of the decade (Corrow, 2021).

c. Corrow (2021) reported that statistics is one of the leading fields of the decade. e. Statistics is one of the leading fields of the decade (Corrow, 2021).

Categorical

categories or labels. Categorical variables places individuals into groups. Eg. race, gender, smoking status. Often coded as numbers (called dummy coding because the number have no arithmetic meaning). For example, 0 might represent non-smokers and 1 would represent smokers.

Sometimes, there are data points currently set to missing, because the question was part of a skip pattern in the survey to save participants time, that actually represent interesting data. In these cases, we need to assign them a new value to represent their actual response (rather than just "skipped"). In order to add values to a variable, we need to convert the format into:

character format