STAT 200 Exam 1 Study Guide: Data, Univariate Data, Bivariate Data, Multivariate Data, Exams of Statistics

A study guide for exam 1 of stat 200, focusing on data, univariate data, bivariate data, and multivariate data. It covers various topics such as types of variables, missing values, measures of center and variation, quantiles, boxplots, histograms, bivariate data analysis, and simple linear regression. Students are encouraged to review their lecture notes and homework for each chapter. The use of a calculator is allowed during the exam.

Typology: Exams

Pre 2010

Uploaded on 03/10/2009

koofers-user-5qt
koofers-user-5qt 🇺🇸

9 documents

1 / 3

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Exam 1 Study Guide
STAT 200
For each of the topics below, look over the relevant problems in your lecture notes and
homework. Exams will be done entirely with “pen and paper,” and the use of a calculator is
allowed and encouraged.
Chapter 1 – Data
Types of variables: numeric (discrete, continuous); categorical (ordinal, unordered); logical
Missing values
R things to know:
R as a calculator, sqrt(), sin(), cos(), exp(), log()
=, <-, ->
c(), seq(), :, rep(), rev()
length(),sum(), min(), max(), range(), sort()
help(), ?, help.search()
() versus []
==, >=, <=, >, <, !=
&, |, !, %in%
which(), with()
Using logical operators and which() inside of []
NA, is.na()
library(), attach(), detach(), dim(), names(), $
read.table(), read.csv()
Chapter 2 – Univariate Data
Using a table to display frequency and/or proportion of a categorical variable.
Be able to creating and read a barplot (bar graph)
Be able to creating and read a stem-and-leaf plot.
Measures of center: mean, trimmed mean, median, mode
- Be able to calculate
- How do mean, trimmed mean, median behave with presence of extreme values
Measures of variation: variance, standard deviation, range, IQR
- Be able to calculate
- Which variation measure goes with which center measure
Explain how the mean and SD change when various changes are made to a distribution:
o A constant is added/subtracted to every number in the list
o All numbers are multiplied/divided by the same value
Quantiles/Percentiles – the pth quantile is the theoretical value with proportion p of the data
less than it
- Be able to calculate
- Five number summary
Boxplots (box-and-whisker plots)
- Be able to read and interpret
- Be able to draw
Histograms
- Be able to read and interpret
pf3

Partial preview of the text

Download STAT 200 Exam 1 Study Guide: Data, Univariate Data, Bivariate Data, Multivariate Data and more Exams Statistics in PDF only on Docsity!

Exam 1 Study Guide

STAT 200

For each of the topics below, look over the relevant problems in your lecture notes and

homework. Exams will be done entirely with “pen and paper,” and the use of a calculator is

allowed and encouraged.

Chapter 1 – Data

• Types of variables: numeric (discrete, continuous); categorical (ordinal, unordered); logical

• Missing values

• R things to know:

R as a calculator, sqrt(), sin(), cos(), exp(), log() =, <-, -> c(), seq(), :, rep(), rev() length(),sum(), min(), max(), range(), sort() help(), ?, help.search() () versus [] ==, >=, <=, >, <, != &, |, !, %in% which(), with() Using logical operators and which() inside of [] NA, is.na() library(), attach(), detach(), dim(), names(), $ read.table(), read.csv()

Chapter 2 – Univariate Data

• Using a table to display frequency and/or proportion of a categorical variable.

• Be able to creating and read a barplot (bar graph)

• Be able to creating and read a stem-and-leaf plot.

• Measures of center: mean, trimmed mean, median, mode

- Be able to calculate

- How do mean, trimmed mean, median behave with presence of extreme values

• Measures of variation: variance, standard deviation, range, IQR

- Be able to calculate

- Which variation measure goes with which center measure

• Explain how the mean and SD change when various changes are made to a distribution:

o A constant is added/subtracted to every number in the list

o All numbers are multiplied/divided by the same value

• Quantiles/Percentiles – the p th quantile is the theoretical value with proportion p of the data

less than it

- Be able to calculate

- Five number summary

• Boxplots (box-and-whisker plots)

- Be able to read and interpret

- Be able to draw

• Histograms

- Be able to read and interpret

  • Be able to draw
  • Be able to tell how the data are distributed from the shape

o Symmetric: mean ≈ median

o Long left tail: mean < median

o Long right tail: mean > median

  • Height vs. Area (i.e. density vs. percentage)
  • Roughly locate the mean (the “balancing” point) on a histogram.
  • Locate the median and percentiles using area
  • R things to know: table(), barplot(), pie() stem(), boxplot(), hist() mean(), median(), var(), sd(), IQR(), apply() quantile(), summary(), fivenum()

Chapter 3 – Bivariate Data

  • Using a two-way contingency table to display frequency and/or proportion of two categorical

variables.

  • Be able to define and calculate marginal and conditional distributions of categorical data.
  • Creating and reading a barplot (bar graph) for bivariate data.
    • Segmented
    • Side-by-side
  • Be able to compare two independent numeric samples given their:
    • Side-by-side stem-and-leaf plots
    • Overlapping densityplots
    • Side-by-side boxplots
    • Quantile-quantile plot
  • Be able to create and interpret a scatterplot
  • Be able to calculate and interpret correlation coefficient
    • A unitless measure of linear association always between -1 and 1
    • Does not measure causation
    • Influence of outliers
    • Match scatter plots with correlation coefficients.
  • Explain how the correlation coefficient changes when:

o A constant is added/subtracted to every number in one of the lists

o A constant is multiplied/divided by every number in one of the lists

  • Simple Linear Regression
    • Be able to calculate and interpret the estimated slope and intercept coefficients
    • Be able to predict values
    • Be able to interpret the scatterplot and residual plot as they apply to a linear model
    • Be able to calculate and interpret the role of residuals and residual standard error
  • R things to know: table(), margin.table(), addmargins(), prop.table() density(), boxplot(), horizontal=, qqplot() plot(), lines(), abline(), main=, lty=, xlab=, ylab=, Table 3.7 (p86) Formula expressions (e.g. y~x) cor(), lm(), $residuals, $fitted.values, predict()