Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
43 Cards in this Set
- Front
- Back
There are four main components of statistics; what does the first component, or the Design component, refer to? |
A plan on how to OBTAIN DATA needed to answer the question. |
|
What is the Description Component refer to? |
Using tables, graphs, etc to summarize and analyze the data. |
|
What is the third component (probability) refer to? |
Determine how sample differs from the population. |
|
What is the fourth and final component refer to (also called the inference)? |
Make decisions and predictions. |
|
What is the difference between Descriptive Statistics and Inferential Statistics? |
Descriptive Statistics uses graphs and numerical summaries; used with samples or populations. Inferential we use data from SAMPLES to make predictions about populations |
|
When is Inferential Statistics not necessary? |
When we already have information about a population and there is no need to make a prediction (i.e. mean age of a population). |
|
A survey of all graduating students was taken and numerical summaries are taken of average starting salary and the percentage of students earning more than $30k/year. 1.) Are these Descriptive or Inferential? 2.) And, are the numerical summaries statistics or parameters? |
1.) Descriptive - they summarize data from a population 2.) Parameter - they refer to a population |
|
What is a Response Variable? |
The variable we are interested in measuring (dependent variable; y-axis). |
|
What is a Component? |
What you are actually simulating through the use of a random device. |
|
True or False? In a particular study, you could use descriptive statistics or inferential statistics, but you would rarely use both. |
False. We often want to describe the sample and make inferences (predictions) about the population. |
|
Inferential Statistics are often used to draw a conclusion. What are some methods for drawing measuring the reliability and conclusions about a population? |
Things like confidence intervals and hypotheses. |
|
What is a categorical variable? |
A qualitative, non-numerical variable with different categories. Ex: types of pets. |
|
What is a Quantitative variable? |
numerical, measurable variable. Ex: GPA |
|
Which of Qualitative and Quantitative variables are further categorized into discrete and continuous? |
Quantitative. |
|
What is a discrete, quantitative variable? |
values that for a set of separate numbers. Ex: shoe size, rolling a die, or something that can be counted. Often whole numbers. Something we count. |
|
What is a continuous, quantitative variable? |
values form a continuum of values over a real number line. Ex: height, weight, time, age. Something we can measure. |
|
What kind of charts are used for Categorical data? |
Pie, Bar, Pareto (specialized bar; ordered in relative frequency) |
|
When would a data set have the same median and mode? |
A symmetric distribution. |
|
If the mean is greater than the median the data are likely skewed which way? |
Right. Mean>Median = right-skewed |
|
If the median is larger than the mean the data are likely skewed... |
Left. Median>Mean = left-skewed |
|
What percent of a data set is said to be one standard deviation from the mean (in a normal distribution)? Two standard deviations? Three? |
68% 95% Nearly all for three standard deviations. |
|
A graph of the 5 number summary is just a...? |
Boxplot - min, Q1, median, Q3, max |
|
Why is the standard deviation (s) preferred over the range? |
the range is more affected by an outlier and the standard deviation uses all of the data. |
|
Why is the IQR sometimes preferred to (s)? |
IQR is not affected by the outlier |
|
What is the advantage of (s) over the IQR? |
the standard deviation takes into account all observations. |
|
How do you describe data distributions? |
SOCS - shape, outliers, central tendency, and spread. |
|
What does shape refer to in SOCS? |
Modality (# of peak) - uni, bi, multimodal. Skewness & Symmetry - left (negative), right (positive), symmetric (bell-shaped or normal) |
|
What does Outliers refer to in SOCS? |
Unusual values. A data value with a z-score greater than zero. |
|
What does the Central Tendency of SOCS refer to? |
Mean for symmetric distributions. Median for skewed distributions |
|
The spread of SOCS refers to? |
Standard deviation (mean) IQR and Range (median) |
|
What is an explanatory variable? |
The varibale being manipulated (x-axis; independent variable). Explanatory explains the response variable. |
|
What is a lurking variable? |
unobserved variable that influences the association between explanatory and response variables. |
|
True or False? An observational study can establish causation. |
False. An observational study can reveal association or correlation. |
|
How is Margin of Error calculated? |
= 1/[sqrt(n)] x 100% |
|
What is the significance of the Margin of Error? Why is it used? |
Used to give a range of plausible values for the population parameter. |
|
How do you find the range of plausible values for a given parameter? |
= sample statistic (+/-) margin of error ex: 78%(+/-)2.9% = (75.1%, 80.9%) |
|
What is sampling bias? |
Sampling method that tends to obtain non-representative samples. |
|
What is under-coverage? |
Sampling frame does not represent all parts of the population; portion is not sampled or has smaller representation in sample than it does the population. |
|
What is over-coverage? |
Members that are not in the population of interest are included in the sample. |
|
What is non-response bias? |
Sampled subjects cannot be reached or refuse to participate. Or some may not respond to some questions further resulting in missing data. |
|
Name three poor ways to sample. |
Convenience sample (individuals who are easy to sample, which may not rep pop) Volunteer sample (common type of convenient sample) Large, non-representative sample |
|
What is Cluster Random Sampling? |
Heterogenous "clusters" that resemble the population; a census is taken of each cluster. |
|
What is Stratified Random Sampling? |
Homogenous groups (to reduce variability); then use simple random sampling to choose members from each strata. Each stratum will be different from the others. |