Scribd
Upload
54 views23 pages

RMPA Chapter 6

The document discusses statistical concepts such as descriptive statistics, inferential statistics, sampling, populations, measures of central tendency, variability, correlation, and statistical tests. It explains why statistics are needed to objectively interpret observations, defines important terms, and discusses how to select samples and generalize results to populations. Examples are provided to illustrate concepts such as normal distributions, skewness, kurtosis, and how computers are used in statistical analysis.

Uploaded by

Tiaan de Jager
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
54 views23 pages

RMPA Chapter 6

The document discusses statistical concepts such as descriptive statistics, inferential statistics, sampling, populations, measures of central tendency, variability, correlation, and statistical tests. It explains why statistics are needed to objectively interpret observations, defines important terms, and discusses how to select samples and generalize results to populations. Examples are provided to illustrate concepts such as normal distributions, skewness, kurtosis, and how computers are used in statistical analysis.

Uploaded by

Tiaan de Jager
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

Chapter 6: Becoming Acquainted

With Statistical Concepts


Thomas, J.R., Nelson. J.K. and Silverman, S.J. (Eds.). Research
Methods in Physical Activity (6th Ed.). (2011). Champaign, IL: Human
Kinetics. Chapter 6
Why We Need Statistics

 Statisticsis an objective way of interpreting a


collection of observations.
 Types of statistics
 Descriptive techniques
 Example: Mean
 Correlational techniques
 Pearson product moment coefficient of correlation – Pearson r
 Differences among groups
 Example: t- tests
Terms

 Inference
 Generalization of results to a larger group
 Inferential Statistics
 Sample
 A group selected from a larger population
 Population
 The larger group from which a sample is drawn
Inference

 What allows us to generalize our results to a population?


 Method for selecting your sample
 Procedures
 Context
 Inference is not affected by the statistic.
Ways to Select a Sample
 Random sampling: allows inference
 Allows us to infer the findings apply to the larger population
 Taking a sample from LCU student population.
 Assign each student a numerical number from 0001 – 1500
 Use online random number generator to select 100 participants for our study
 Stratified random sampling
 Population is stratified (divided) before random sampling occurs
 Examples: Age, class
 Take a ratio of students from each class (25 freshmen, 25 soph., etc)
 Systematic Sampling
 Population is sampled via a systematic selection
 Example: every 15th person listed is chosen.
Ways to Select a Sample
 Random assignment
 Groups within a sample
 Randomization
 Allows for assumption that groups are equivalent at the beginning of
experiment
 Justifying post hoc explanations
 Not all samples are random, so run post hoc tests to help account for this
 Allows the assumption that the sample does not differ from the
population of the characteristics measured.
 Is random sampling possible in all instances?
 NO!
 How good does the sample have to be?
 Good enough for our purposes!
Measures of Central Tendency

 Central tendency scores


 Measure of central tendency: a single score
that best represents a group of scores
Mean: average
Median: midpoint
Mode: most frequent
Variability

 The degree of difference between each individual score and the


central tendency score
 Variability scores
 Standard deviation
 Estimates the variability in a group of scores around the mean
A large standard deviation may indicate the mean is not the best
representation of the group of scores
 Range of scores
 Highest – lowest
 Reported when the median is used
Variance Formula

 Total (observed) variance = true variance ÷ error variance


 Allstatistical estimates are one of two arrangements of
the variance formula:
 Significance tests (t, F, and X2) = true variance ÷ error variance
 Correlation (r2, R2, % variance accounted for) = true variance ÷ total variance
Correlation
How Computers Are Used in Statistics

 Frequently used in offices, labs, and homes for statistical


analysis
 Hardware and software
 Types of software for statistics
 Statistical Analysis System (SAS)
 Statistical Package for the Social Sciences (SPSS)
 JASP
Unit of Analysis
 The concept, related to sampling and statistical analysis,
that refers to what is considered the most basic unit from
which data can be produced
 Often, it’s the individual participant
 Significantly affects the sample size
 2 treatments: experimental and control
 Unit of Analysis:

Students are randomly Classes are randomly Schools are randomly


assigned to each treatment assigned to each treatment assigned to each treatment
4,800 observations 192 observations 16 observations
(n = 300; N = 4800) (n = 12; N = 192) (n = 8; N = 16)
Variability

 Confidence Intervals
 Provides a range within which the estimate of the population
mean is likely to fall
 Are appropriate because all statistics have sampling error
 The error relates how well the statistic represents the population
 Standard Error
 Variability of the sampling distribution
 Standard deviation of all sample means
Frequency

 Frequency Distribution
 A distribution of scores including the frequency with which they occur
 Shown with a Histogram
 Frequency Interval
 Small ranges of scores within a frequency distribution into which
scores are grouped
 Stem-and-leaf display
 A method of organizing raw scores where score intervals are shown on
the left side and individual scores shown on the right side
Histogram, Stem-and-Leaf Display
Categories of Statistical Tests

• Parametric (must meet 3 assumptions)


1. Normal distribution
 The population from which you drew the sample is distributed
normally on the variable of interest
2. Equal variances
 The samples taken from the population have the same variances on
the variable of interest
3. Independent observations
• Nonparametric (distribution free)
 Distribution is not normal
Normal Curve (Figure 6.3)
Mean, Median and Mode are
represented by A (at the same point)
Normal Curve (Figure 6.3)

68% of your scores fall within 1s of the


center of the distribution
Figure 6.4 Skewness

Positive (+) Negative (-)


Figure 6.5 Kurtosis
Statistics

 What statistical techniques tell us (Page 113)


 Statistical Significance and Reliability
 Are your results statistically significant?
 If the research is repeated, will the effect still be present?
 Strength of the relationship (meaningfulness)
 What is the magnitude, or size of the effect or relationship?
Statistics

 Types of statistical techniques


 Relationships among variables
 Regression or correlation
 Differences among groups
 t-tests or analysis of variance (ANOVA)
 Cause and effect: “Correlation is no proof of causation.”
Example

 Obtain height and weight for all students in ESS 3341


 Calculate measures of central tendency.
 Calculate the standard deviation
 How does the standard deviation change if our group is
selected with greater specificity?
 Assuming a normal distribution, how many students fall
within 1, 2 and 3 standard deviations of the mean.
 What population do our results describe?
 To what population can our results be inferred?

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy