POLI 380 - UBC

Observation

The information collected from a particular entity or individual in the study.

Variable

A variable contains the values of a changing characteristic for the various individuals or entities in the study.

Unit of Observation

The unit of observation of the dataset defines the individuals or the entities that each observation in the dataframe represents.

What are the two main types of variables based on content?

Character variables and numeric variables.

What do character variables contain?

Text.

What do numeric variables contain?

Numbers.

What are binary variables?

Numeric variables that can take only two values, typically represented as 1s and 0s.

What do binary variables represent?

The presence (1) or absence (0) of a trait.

What are non-binary variables?

Numeric variables that can take more than two values.

Give an example of a binary variable.

voted = {1, 0, 0, 1, 1, 1, 0}, where 1 indicates an individual voted and 0 indicates they did not.

How is the average or mean of a variable computed?

By summing the values across all observations and dividing by the total number of observations.

What does X (X-bar) represent in the context of means?

The average of the variable X.

What is the unit of measurement when interpreting the mean of a non-binary variable?

The same unit of measurement as the values in the variable.

How should the mean of a binary variable be interpreted?

As a proportion, expressed in percentage after multiplying the result by 100.

What does a mean of 0.5 for a binary variable indicate?

That 50% of the observations have the characteristic identified by the variable.

What is an example of a variable in the leaders dataset?

country, year, leadername, polityafter, civilwarafter, outcome, died.

What does the variable 'polityafter' represent in the leaders dataset?

The average polity score of the country in the three-year period after the assassination attempt, on a 21-point scale from -10 to +10.

What does the variable 'civilwarafter' indicate?

Whether the country had a civil war within 3 years of the assassination attempt, coded as 1 for 'yes' and 0 for 'no'.

What does the variable 'died' signify in the leaders dataset?

Whether the leader died as a result of the assassination attempt, with 1 indicating 'died' and 0 indicating 'did not die'.

What is the significance of the leaders dataset in this course?

It serves as a practical example for applying data visualization and analysis techniques.

What is a characteristic of categorical variables?

They often take on a limited number of values and can be represented as text.

What is the difference between binary numeric variables and character variables?

Binary numeric variables are numeric encodings of variables with two categories, while character variables are text-based.

What are the four main variable types in R?

character, factor, numeric (or double), integer

What is the purpose of data visualization?

To identify patterns and potential issues in data.

What type of plot is used to visualize the distribution of categorical variables?

Barplots

How do you interpret the mean of a binary numeric variable?

As a percentage of occurrences.

What does the command leaders %>% summarize(dies_mean = mean(dies, na.rm=T)) compute?

The average of the dies variable in the leaders dataset.

What is the average polityafter score in the leaders data?

The average polity score is -1.65 points on a 21-point scale.

What is the significance of using ggplot() for visualizing data?

It allows for a structured approach to mapping data to visual elements.

What is the purpose of the 'na.rm' argument in mean calculations?

To remove NA values from the calculation.

What does the command leaders %>% summarize(dies_mean_percent = 100 * mean(dies, na.rm=T)) calculate?

The percentage of assassination attempts that ended in death.

What is the difference between a histogram and a barplot?

Histograms visualize numeric variable distributions, while barplots visualize categorical variable distributions.

What does the 'geom' parameter in ggplot() represent?

The geometric object to be plotted, such as points, lines, or bars.

What are the three main reasons for analyzing data in political science?

To measure population characteristics, to predict outcomes, and to explain causal effects.

What is a treatment variable?

A variable whose change may produce a change in the outcome variable.

What is an outcome variable?

A variable that may change as a result of a change in the treatment variable.

In the voting dataset, what is the treatment variable?

The message indicating whether a registered voter received a message inducing social pressure.

In the voting dataset, what is the outcome variable?

Whether the registered voter voted (1 for voted, 0 for didn't vote).

What does the notation X → Y represent?

The causal relationship where changes in the treatment variable X affect the outcome variable Y.

What is the fundamental problem of causal inference?

We can never observe the counterfactual outcome for the same individual at the same time.

What is the average causal effect?

The average change in the outcome variable caused by a change in the treatment variable across a group.

What is a randomized experiment?

A study design where treatment assignment is randomized, ensuring comparability between treatment and control groups.

What is the difference-in-means estimator?

A method to estimate the average treatment effect by calculating the difference in average outcomes between treatment and control groups.

What is the purpose of using a control group in experiments?

To provide a baseline for comparison against the treatment group.

How do researchers ensure that treatment and control groups are comparable?

By randomizing treatment assignment, which balances observed and unobserved pre-treatment characteristics.

What does the notation ΔYi represent?

The change in the outcome variable for individual i, calculated as Yi(Xi=1) − Yi(Xi=0).

What is the significance of the message sent to voters in the experiment?

It was designed to induce social pressure to vote by informing neighbors about voting behavior.

What type of variable is 'voted' in the voting dataset?

Binary variable (1 if voted, 0 if didn't vote).

What is the goal of estimating causal effects in political research?

To understand the impact of various factors, such as social pressure, on voter turnout.

What is the role of randomization in experiments?

To eliminate bias and ensure that the treatment and control groups are statistically equivalent.

What is the expected outcome if Δvotedi is positive?

The probability of voting increased when the individual received the social pressure message.

What does it mean if Δvotedi is zero?

The probability of voting did not change when the individual received the social pressure message.

What is the implication if Δvotedi is negative?

The probability of voting decreased when the individual received the social pressure message.

What is the purpose of conducting a randomized experiment?

To obtain valid estimates of causal effects by ensuring comparability between treatment and control groups.

What is the significance of the average treatment effect?

It provides insights into the overall impact of a treatment across a population.

What does the term 'pre-treatment characteristics' refer to?

Characteristics of individuals before the treatment was administered.

What is the expected outcome of a well-designed randomized experiment?

To produce reliable estimates of the causal effect of the treatment on the outcome.

What are the two conditions in a randomized experiment?

Treatment condition (with treatment) and control condition (without treatment).

What is the importance of the voting dataset in the context of the experiment?

It allows researchers to analyze the effect of social pressure on voter turnout.

What is the main research question addressed in the voting experiment?

Does social pressure increase the probability of turning out to vote?

What is the difference between a sample and a population?

A sample is a subset of individuals chosen for study, while a population is the entire group of individuals we want to understand.

Why do researchers use samples instead of populations?

Collecting data from each individual in a population is often prohibitively expensive or infeasible.

What is a representative sample?

A representative sample accurately reflects the characteristics of the population it is drawn from.

What is random sampling?

Random sampling is the procedure of selecting individuals at random from the population to ensure the sample is representative.

What is the purpose of analyzing data in survey research?

To measure population characteristics, predict outcomes, and explain causal effects.

What is quota sampling?

Quota sampling ensures specific segments of a population are represented in a sample by setting quotas based on predefined characteristics.

What is the significance of a frequency table?

A frequency table shows the values a variable takes and the number of times each value appears.

How do you calculate proportions in survey data?

Proportions are calculated by dividing the count of observations for each value by the total number of observations.

What is a histogram?

A histogram is a visual representation of the distribution of a variable, showing the frequency of values within specified intervals.

What are descriptive statistics?

Descriptive statistics summarize and describe the main features of a dataset, including mean, median, standard deviation, and variance.

What is the purpose of using random treatment assignment?

Random treatment assignment ensures that treatment and control groups are comparable, allowing valid estimates of the average treatment effect.

What is the role of descriptive statistics in data analysis?

Descriptive statistics help summarize the data, making it easier to understand and interpret.

What does it mean if a sample is not representative?

If a sample is not representative, the inferences about the population characteristics based on that sample will be invalid.

What is the purpose of creating a table of proportions?

To show the proportion of observations that take each value in a variable.

What is the expected outcome when using random sampling?

Random sampling ensures that the sample is representative of the target population, allowing valid inferences.

What are the key components of descriptive statistics?

Mean, median, standard deviation, and variance.

What does the term 'sample selection bias' refer to?

Sample selection bias occurs when certain individuals are systematically excluded from the sample, leading to invalid conclusions.

What does the term 'mean' refer to in descriptive statistics?

The mean is the average value of a dataset, calculated by summing all values and dividing by the number of observations.

What does the term 'standard deviation' indicate?

Standard deviation measures the amount of variation or dispersion in a set of values.

What is the significance of using Dplyr functions in R for data analysis?

Dplyr functions, such as group_by() and summarize(), facilitate data manipulation and summarization in R.

What is the purpose of the 'head()' function in R?

The 'head()' function displays the first six observations of a dataset.

What characterizes left-skewed data?

The tail on the left side of the distribution is longer than the tail on the right side.

What characterizes right-skewed data?

The tail on the right side of the distribution is longer than the tail on the left side.

What is the purpose of barplots in data visualization?

Barplots are used to visualize the distribution of categorical variables.

How can you create a barplot for a binary variable in R?

Use the ggplot function with geom_bar() to visualize counts of categories.

How do you calculate proportions for a binary variable in R?

Group by the variable, summarize counts, and mutate to calculate proportions.

What is the mean of a variable?

The mean is the sum of all values divided by the total number of observations.

How is the median of a variable defined?

The median is the value at the midpoint of the distribution that divides the data into two equal-size groups.

What is the standard deviation?

The standard deviation measures the spread of a variable's distribution, indicating the average distance of observations from the mean.

What does a larger standard deviation indicate?

A larger standard deviation indicates a flatter distribution with more variability in the data.

What is variance in statistics?

Variance is the square of the standard deviation, representing the spread of a distribution.

What is the significance of the 95% rule in normal distributions?

In normal distributions, about 95% of observations fall within two standard deviations from the mean.

What is the interpretation of the mean of a binary variable?

The mean of a binary variable is interpreted as a proportion or percentage.

How do you summarize the mean and median age of prospective voters in R?

Use the summarize function to calculate mean and median age from the dataset.

What is the purpose of a frequency table?

A frequency table shows how many observations belong to each category in a variable.

What is the significance of outliers in data analysis?

Outliers can skew the mean, making the median a preferred measure of central tendency in such cases.

What is the R function to calculate variance?

The R function to calculate variance is var().

How do you interpret the output of the summarize function in R?

The output provides summary statistics such as mean, median, standard deviation, and variance for specified variables.

What are the two types of variables discussed in the lecture?

Binary and nonbinary variables.

What is the difference between treatment variables and outcome variables?

Treatment variables are manipulated in an experiment, while outcome variables are measured to assess the effect of the treatment.