Quiz
COMM 304 Week 12.1 Descriptive Statistics
This quiz has question types that open in the usual player.
Questions in this quiz (32)
1[blank_start]Statistics[blank_end] (singular)—A branch of applied mathematics that specializes in procedures for describing and reasoning from measures. (Williams & Monge, 2001). A set of tools to analyze and interpret [blank_start]numerical[blank_end] data, thereby allowing researchers to answer questions and [blank_start]test[blank_end] hypotheses from these data. (Weiss & Leets, 1998)
Benefits
[blank_start]Describe[blank_end]—Allows us to summarize large amounts of data.
[blank_start]Organize[blank_end]—Enables us to organize information in a meaningful way to make predictions.
[blank_start]Interpret[blank_end]—Helps us in understanding and explaining (assigning meaning) to the world around us.- AStatistics
- Bnumerical
- Ctest
- DDescribe
- EOrganize
- FInterpret
2Types of ‘Statistics’
[blank_start]Descriptive[blank_end] Statistics—Statistical tests used to [blank_start]describe[blank_end] the shape of a dataset; to organize and summarize information or data. (Wrench et al., 2019)
These are the types of statistics most individuals are used to thinking about, e.g., means, percentages, frequencies.
[blank_start]Data[blank_end]—Any records or observations; the reports of observations of variables.
Note. Data is plural; datum is the [blank_start]singular[blank_end]
[blank_start]Inferential[blank_end] Statistics—Tests that allow researchers to make inferences (i.e., [blank_start]predictions)[blank_end] about some unknown aspect of a population from a sample.- ADescriptive
- BData
- Csingular
- DInferential
- Edescribe
- Fpredictions)
3[blank_start]Population[blank_end]: The collection of all people or things you are interested in studying.
[blank_start]Sample[blank_end]: A small subset of the larger population of interest from or about which you decide to collect data.- APopulation
- BSample
4Types of ‘Statistics’
A [blank_start]Parameter[blank_end]: A value of a population.
Note. In APA, these are symbolized
using Greek letters (e.g., μ, σ, β)
A [blank_start]Statistic[blank_end]: A value of a sample.
Note. In APA, these are symbolized using Latin letters (e.g., M, s, b)- AParameter
- BStatistic
5Parameter: A value of a population.
Note. In APA, these are symbolized using Greek letters (e.g., [blank_start]μ,[blank_end] [blank_start]σ[blank_end], [blank_start]β[blank_end])
A Statistic: A value of a sample.
Note. In APA, these are symbolized using Latin letters (e.g., [blank_start]M[blank_end], [blank_start]s[blank_end], [blank_start]b[blank_end])- Aμ,
- Bσ
- Cβ
- DM
- Es
- Fb
6Statistics Greek Symbols:
μ= [blank_start]mean[blank_end]
σ= [blank_start]sigma[blank_end], sample [blank_start]standard deviation[blank_end]
β= [blank_start]beta[blank_end]
Statistic Latin symbols:
[blank_start]M[blank_end]= mean
[blank_start]s[blank_end]= sample standard deviation
[blank_start]b[blank_end]= beta- Amean
- Bsigma
- Cstandard deviation
- Dbeta
- EM
- Fs
- Gb
7Descriptive Statistics
Distribution: Data ordered by [blank_start]numerical[blank_end] value- Anumerical
8[blank_start]Frequency[blank_end] Distribution: A distribution with a corresponding frequency of occurrence for each data point.
- AFrequency
9Graphing Distributions
[blank_start]Scatter[blank_end] Plot: Good for comparing values on variable X with scores on variable Y. You plot one [blank_start]dot[blank_end] for each combination of x and y.- AScatter
- Bdot
10Graphing Distributions
[blank_start]Line[blank_end] Graph—A scatterplot, where we connect the lines.
Rarely useful when using raw data.
Frequency [blank_start]Polygon[blank_end]—What we call a line graph when what we’re graphing is a frequency distribution (rather than two distinct variables)- ALine
- BPolygon
11[blank_start]Bar[blank_end] Graph—Good for categorical or ordinal data. Shows the frequency with which each unique value of X occurs in the data set.
Note: In order to get it to look like this using Excel / PowerPoint, I had to add in each possible value in the desired range, with f = 0.- ABar
12[blank_start]Histogram[blank_end]—Good for interval or ratio level data. Places raw data in ‘buckets’ of a standard (researcher or computer program specified) interval (in this case, an interval of 5).
- AHistogram
13Shapes of Distributions
The [blank_start]Normal[blank_end] Distribution (aka, Gaussian distribution) If the scores are distributed “normally,” the curve forms a [blank_start]bell[blank_end] shape, giving rise to the nickname “[blank_start]bell-curve[blank_end].”
Normality (or a derivation thereof) is a condition for MOST statistical analyses associated with [blank_start]hypothesis[blank_end] testing (especially parametric tests).- ANormal
- Bbell
- Cbell-curve
- Dhypothesis
14Other Common Types of (non-normal) Distributions
• Negatively or [blank_start]Left[blank_end] Skewed—When the longest tail is on the negative (or left) end of the distribution (i.e., when Skew < −1)
• Positively or [blank_start]Right[blank_end] Skewed—When the longest tail is on the positive (or right) end of the graph (i.e., when Skew > 1)
Skewness: [blank_start]Asymmetry[blank_end] in a distribution.- ALeft
- BRight
- CAsymmetry
15Other Common Types of (non-normal) Distributions
• [blank_start]Lepto[blank_end]kurtic—High [blank_start]homo[blank_end]geneity (i.e., when Kurtosis > 2)
• [blank_start]Platy[blank_end]kurtic—High [blank_start]hetero[blank_end]geneity (i.e., when Kurtosis < −2)
[blank_start]Kurtosis[blank_end]—Excess homogeneity or heterogeneity in a distribution.- ALepto
- Bhomo
- CPlaty
- Dhetero
- EKurtosis
16Other Common Types of (non-normal) Distributions
• [blank_start]Bi[blank_end]modal—Two modes, or ‘peaks’
• [blank_start]Multi[blank_end]modal—More than one mode (usually used to describe distributions with more than two modes)- ABi
- BMulti
17Measures of Central Tendency
Measures of the “[blank_start]center[blank_end]” of “middle” score in a distribution.
[blank_start]Mean[blank_end]—Identifies the arithmetic [blank_start]average[blank_end] score in a distribution. Only used with [blank_start]interval[blank_end] or [blank_start]ratio[blank_end] data. It cannot be used with nominal or ordinal data.
[blank_start]Median[blank_end]: Identifies the middle score in a [blank_start]distribution[blank_end]. Most often used with [blank_start]ordinal[blank_end] data, or with [blank_start]interval[blank_end] or [blank_start]ratio[blank_end] data in a skewed distribution.
[blank_start]Mode[blank_end]: Identifies the most [blank_start]frequently[blank_end] occurring score in a distribution. Most often used with [blank_start]nominal[blank_end] data, or with data in a bi or multimodal distribution.- Acenter
- BMean
- CMedian
- DMode
- Eaverage
- Fdistribution
- Ginterval
- Hratio
- Iordinal
- Jinterval
- Kratio
- Lfrequently
- Mnominal
18Mean: Same formula for [blank_start]population[blank_end] or [blank_start]sample[blank_end]
Parameter: μ
μ = ∑ 𝑥 divided by 𝑁
Statistic:
M or 𝑋
𝑀 = 𝑋 = ∑ 𝑥 divided by 𝑁- Apopulation
- Bsample
19Median
Statistic:
Mdn
The median and mode are considered non-[blank_start]parametric[blank_end]. We use the median when the population is [blank_start]skewed[blank_end] (e.g., income); mode when the population is [blank_start]multimodal[blank_end].- Aparametric
- Bskewed
- Cmultimodal
20Median: How to Calculate
If odd number of cases: Median = [blank_start]Middle[blank_end] number
If even number of cases: Median = [blank_start]average[blank_end] of two middle points
𝑀dn = 85 + 85 divided by 2 = 85- AMiddle
- Baverage
21Measures of Dispersion
Descriptive statistics that measure how far apart scores are from one another, or how [blank_start]spread out[blank_end] the data is in a distribution.
[blank_start]Range[blank_end]—Difference between the highest and lowest score in a distribution.
[blank_start]Standard[blank_end] Deviation—Average variability of scores about the mean of a distribution.
In other words, measures how far away, on [blank_start]average[blank_end], scores in a distribution are from
the [blank_start]mean[blank_end] of the distribution.
[blank_start]Variance[blank_end]—Average [blank_start]variability[blank_end] of scores about the mean of a distribution, in [blank_start]squared[blank_end] units. Variance is literally the [blank_start]square[blank_end] of the standard deviation.- Aspread out
- BRange
- CStandard
- Daverage
- Emean
- FVariance
- Gvariability
- Hsquared
- Isquare
22A class of 20 students take a midterm exam that is graded on a scale from 0 to 100 (interval level). The class period after the exam, the professor informs them that students obtained the following scores:
69, 78, 78, 79, 79, 81, 81, 81, 85, 85, 85, 85, 86, 86, 87, 87, 91, 91, 98
Range: Non-[blank_start]parametric[blank_end]; [blank_start]Highest[blank_end] value [blank_start]minus[blank_end] [blank_start]lowest[blank_end] value
Range = [𝑋] − [𝑋] = 98 − 69 = 29- Aparametric
- Bminus
- CHighest
- Dlowest
23A class of 20 students take a midterm exam that is graded on a scale from 0 to 100 (interval level). The class period after the exam, the professor informs them that students obtained the following scores:
69, 78, 78, 79, 79, 81, 81, 81, 85, 85, 85, 85, 86, 86, 87, 87, 91, 91, 98
Standard Deviation
Parameter: σ
Statistic: SD or s
σ (standard deviation)= [blank_start]square root[blank_end] of 𝑆 divided by 𝑁- Asquare root
24Sum of [blank_start]Squares[blank_end]—The sum of squared distances (from the [blank_start]mean[blank_end])
𝑆𝑆 = E (x-𝑋 ) squared- ASquares
- Bmean
25[blank_start]Variance[blank_end]
Parameter: σ2
σ2 = 𝑆𝑆 divided by 𝑁 = S2
Statistic: S2 or 𝑠 squared
𝑠 squared = 𝑆𝑆 divided by 𝑁 − 1
𝑠 squared is the unbiased estimator of σ 2- AVariance
26A class of 20 students take a midterm exam that is graded on a scale from 0 to 100 (interval level). The class period after the exam, the professor informs them that students obtained the following scores:
69, 78, 78, 79, 79, 81, 81, 81, 85, 85, 85, 85, 86, 86, 87, 87, 91, 91, 98
Variance: Average [blank_start]Squared[blank_end] Distance
Parameter: σ2
σ2 = 𝑆𝑆 divided by 𝑁 = 701.8 divided by 20= [blank_start]35.09[blank_end]= s squared
Statistic: S2 or 𝑠𝑠 2
s squared = 𝑆𝑆 divided by 𝑁 − 1 = 701.8 divided by 20 − 1 = [blank_start]36.94[blank_end]- ASquared
- B35.09
- C36.94
27A class of 20 students take a midterm exam that is graded on a scale
from 0 to 100 (interval level). The class period after the exam, the
professor informs them that students obtained the following scores:
69, 78, 78, 79, 79, 81, 81, 81, 85, 85, 85, 85, 86, 86, 87, 87, 91, 91, 98
[blank_start]Standard Deviation[blank_end]: Average Distance
Parameter: σ
σ = take 𝑆quare root of (SS divided by 𝑁) = SD
Statistic: SD or s
𝑠 = take square root of (𝑆𝑆 divided by 𝑁 − 1 )- AStandard Deviation
28A class of 20 students take a midterm exam that is graded on a scale
from 0 to 100 (interval level). The class period after the exam, the
professor informs them that students obtained the following scores:
69, 78, 78, 79, 79, 81, 81, 81, 85, 85, 85, 85, 86, 86, 87, 87, 91, 91, 98
Standard Deviation—Average Distance
Parameter: σ
σ = σ2 = square root of 35.09 = [blank_start]5.92[blank_end]
Statistic: SD or s
𝑠 = square root of 𝑠 squared = square root of 36.94 = [blank_start]6.08[blank_end]- A5.92
- B6.08
29z-Scores
Because of the [blank_start]constant[blank_end] relationship between the normal curve and the standard deviation, it is often useful to consider data in terms of standard deviation [blank_start]units[blank_end], i.e., z-Scores
𝑧 = (θ𝑖 − θ top bar) divided by σθ = individual score in distribution − mean of distribution standard deviation of distribution- Aconstant
- Bunits
30Four Important Types of Normal Distribution
[blank_start]Sample[blank_end] Distribution—Represents individual scores from a sample.
[blank_start]Population[blank_end] Distribution—Represents individual scores from a population.
[blank_start]Sampling[blank_end] Distribution—Represents sample means computed from an infinite number of random samples drawn from the same population.*
Distribution of [blank_start]Differences[blank_end]—Represents differences between pairs of sample means that are computed from an infinite number of random samples drawn from the same population.*- ASample
- BPopulation
- CSampling
- DDifferences
31[blank_start]Sample[blank_end] Distribution
𝑧 = 𝑥 − 𝑋 (top bar) divided by SD
[blank_start]Population[blank_end] Distribution
𝑧 = 𝑥 − μ divided by σ
[blank_start]Sampling[blank_end] Distribution
𝑧 = 𝑋 (top bar) − μ 𝑋 divided by σ 𝑋 = 𝑋 − μ divided by σ 𝑋
Distribution of [blank_start]Differences[blank_end]
𝑧 = (𝑋1 − 𝑋2 )− μ 𝑋1 − 𝑋2 divided by σ 𝑋1 − 𝑋2 = (𝑋1 − 𝑋2) − μdiff divided by σdiff = (𝑋1 − 𝑋2) − 0 divided by σdiff- ASample
- BPopulation
- CSampling
- DDifferences
32z-[blank_start]Score[blank_end]—How many SDs away a given score in a distribution is from the mean of the distribution
- AScore
Information
- Description
- Undergrad COMM 304 Unit 2 Exam Quiz on COMM 304 Week 12.1 Descriptive Statistics, created by Sarah Kassaye on 14/11/2023.
- Author
- Sarah Kassaye
- Language
- English
- Views
- 2
- Tags
- Rating
- No ratings yet Rate this quiz