Data Screening - Revision history

Admin at 22:29, 19 November 2019

2019-11-19T22:29:02Z

Kuslis001: /* Detection of Multivariate Outliers: Scatterplot Matrices */

2019-11-17T14:59:35Z

‎Detection of Multivariate Outliers: Scatterplot Matrices

Kuslis001: /* Detection of Multivariate Outliers */

2019-11-17T14:52:14Z

‎Detection of Multivariate Outliers

Kuslis001: /* Causes of Outliers */

2019-11-17T14:50:56Z

‎Causes of Outliers

Kuslis001: /* Data Cleaning */

2019-11-17T14:41:50Z

‎Data Cleaning

Kuslis002: /* Data Screening */

2019-11-17T02:27:52Z

‎Data Screening

Kuslis002: /* Value Cleaning */

2019-11-17T02:26:10Z

‎Value Cleaning

Kuslis002: /* Detection of Multivariate Outliers: Mahalanobis Distance */

2019-11-17T02:25:47Z

‎Detection of Multivariate Outliers: Mahalanobis Distance

Kuslis002: /* Detection of Multivariate Outliers: Mahalanobis Distance */

2019-11-17T02:25:27Z

‎Detection of Multivariate Outliers: Mahalanobis Distance

Kuslis002: /* Outliers */

2019-11-17T02:25:11Z

‎Outliers

@@ Line 8: / Line 8: @@
-''Contribution by: Britany Kuslis, WCSU Cohort 8''
+''contributed by Britany Kuslis, WCSU Cohort 8''
@@ Line 21: / Line 21: @@
 This process of representing original data. In its initial phases, involves the researcher looking for incomplete data that may skew futher data screening. For example if there is a 5 question subscale where all the scores are added and a mean derived, if a respondent does not answer a question, that would skew the subscale, and that set of answers should be removed.
-Contribution by: Mykal Kuslis, WCSU Cohort 8
+''contributed by Mykal Kuslis, WCSU Cohort 8''
@@ Line 31: / Line 31: @@
 '''Value cleaning''' is ensuring the values are "within the limits of reasonable expectation" within the "to the extent that it is possible...within the bounds of feasibility"(Meyers, Gamst, & Guarino, 2017, p. 32). For example, you want to ensure the age of a presumed adult is not 9 years old or that a response to an item rated on a likert scale of 1-5 is not a 6 or an otherwise value that is not within the bounds of the study.
-''Contribution by: Britany Kuslis, WCSU Cohort 8''
+''contributed by Britany Kuslis, WCSU Cohort 8''
 Reference:
@@ Line 51: / Line 51: @@
-''Contribution by: Britany Kuslis, WCSU Cohort 8''
+''contributed by Britany Kuslis, WCSU Cohort 8''
@@ Line 68: / Line 68: @@
 -Multivariate outliers- a pattern of combination of valuable on several variables.
-Contribution by: Mykal Kuslis, WCSU Cohort 8
+''contributed by Mykal Kuslis, WCSU Cohort 8''
 Reference:
@@ Line 88: / Line 88: @@
 See page 52 on reference for example matrices.
-Contribution by: Mykal Kuslis, WCSU Cohort 8
+''contributed by Mykal Kuslis, WCSU Cohort 8''
 Reference:
@@ Line 104: / Line 104: @@
-''Contribution by: Britany Kuslis, WCSU Cohort 8''
+''contributed by Britany Kuslis, WCSU Cohort 8''

← Older revision		Revision as of 14:59, 17 November 2019
Line 76:		Line 76:
	== Detection of Multivariate Outliers: Scatterplot Matrices ==		== Detection of Multivariate Outliers: Scatterplot Matrices ==

		+	Multivariate outliers uniqueness occurs in their pattern of combination of values on several variables. For example, a particular combination of age, sex, and number of arrests may be quite different from other combinations (young males in certain populations will have proportionally more arrests than other combinations of sex and age).
		+
		+	Running bivariate scatterplots for combinations of key variables.
		+
		+	Run a Scatterplot Matrices.
		+
		+	Each case is represented as a point on the X and Y axes.
		+
		+	Most cases will fall within the elliptical swarm or pattern mass, outliers are those cases that tend to lie outside the oval.
		+
		+	See page 52 on reference for example matrices.
		+
		+	Contribution by: Mykal Kuslis, WCSU Cohort 8
		+
		+	Reference:
		+
		+	Meyers, S., Gamst, G., & Guarino, A.J. (2017). Applied multivariate research: Design and interpretation. Thousand Oaks, CA: Sage Publications. (p.49-53)

	== Detection of Multivariate Outliers: Mahalanobis Distance ==		== Detection of Multivariate Outliers: Mahalanobis Distance ==

← Older revision		Revision as of 14:52, 17 November 2019
Line 73:		Line 73:

	Meyers, S., Gamst, G., & Guarino, A.J. (2017). Applied multivariate research: Design and interpretation. Thousand Oaks, CA: Sage Publications. (p.48-49)		Meyers, S., Gamst, G., & Guarino, A.J. (2017). Applied multivariate research: Design and interpretation. Thousand Oaks, CA: Sage Publications. (p.48-49)
−
−	~~== Detection of Multivariate Outliers ==~~
−

	== Detection of Multivariate Outliers: Scatterplot Matrices ==		== Detection of Multivariate Outliers: Scatterplot Matrices ==

← Older revision		Revision as of 14:50, 17 November 2019
Line 59:		Line 59:

	== Causes of Outliers ==		== Causes of Outliers ==
		+
		+	- Data entry errors or improper attribute coding (normally caught in data cleaning)
		+
		+	- A function of extraordinary events or unusual circumstances (for example a traumatic event causing someone to forget what they learned or a person remembering all 80 facts)
		+
		+	- Some have no explanation, these are good cause for deletion.
		+
		+	-Multivariate outliers- a pattern of combination of valuable on several variables.
		+
		+	Contribution by: Mykal Kuslis, WCSU Cohort 8
		+
		+	Reference:
		+
		+	Meyers, S., Gamst, G., & Guarino, A.J. (2017). Applied multivariate research: Design and interpretation. Thousand Oaks, CA: Sage Publications. (p.48-49)

	== Detection of Multivariate Outliers ==		== Detection of Multivariate Outliers ==

← Older revision		Revision as of 14:41, 17 November 2019
Line 18:		Line 18:

	== Data Cleaning ==		== Data Cleaning ==
		+
		+	This process of representing original data. In its initial phases, involves the researcher looking for incomplete data that may skew futher data screening. For example if there is a 5 question subscale where all the scores are added and a mean derived, if a respondent does not answer a question, that would skew the subscale, and that set of answers should be removed.
		+
		+	Contribution by: Mykal Kuslis, WCSU Cohort 8
		+
		+
		+	Reference:
		+
		+	Meyers, S., Gamst, G., & Guarino, A.J. (2017). Applied multivariate research: Design and interpretation. Thousand Oaks, CA: Sage Publications. (p. 31-33)

	== Value Cleaning ==		== Value Cleaning ==

← Older revision		Revision as of 02:27, 17 November 2019
Line 8:		Line 8:


−	Contribution by: Britany Kuslis, WCSU Cohort 8	+	''Contribution by: Britany Kuslis, WCSU Cohort 8''
		+

	Reference:		Reference:

@@ Line 19: / Line 19: @@
 == Value Cleaning ==
-Value cleaning is ensuring the values are "within the limits of reasonable expectation" within the "to the extent that it is possible...within the bounds of feasibility"(Meyers, Gamst, & Guarino, 2017, p. 32). For example, you want to ensure the age of a presumed adult is not 9 years old or that a response to an item rated on a likert scale of 1-5 is not a 6 or an otherwise value that is not within the bounds of the study.
+'''Value cleaning''' is ensuring the values are "within the limits of reasonable expectation" within the "to the extent that it is possible...within the bounds of feasibility"(Meyers, Gamst, & Guarino, 2017, p. 32). For example, you want to ensure the age of a presumed adult is not 9 years old or that a response to an item rated on a likert scale of 1-5 is not a 6 or an otherwise value that is not within the bounds of the study.
 ''Contribution by: Britany Kuslis, WCSU Cohort 8''

@@ Line 59: / Line 59: @@
 The '''Mahalanobis Distance''' statistic measures "the multivariate 'distance' between each case and the group multivariate mean (known as centroid) taking into account the correlations between the variables" (Meyers, Gamst, & Guarino, 2017, p. 52). This method is used to determine if there are scores that vary from the mean of a set of DV's. The Mahalanobis distances details how far a case is from the group center mass of the predictor or IV's.  The greater the distance the higher the possibility of a multivariate outlier.  According to Lawrence S. Meyers, Glenn Gamst and A.J. Guarino, "Each case is evaluated using the chi square distribution with a stringent alpha level of .001.  Cases that reach this significance threshold can be considered multivariate outliers and possible candidates for elimination. This approach is also not without its critics (e.g., Wilcox, 2012) for alternative approaches to multivariate outlier detection" (Meyers, Gamst, & Guarino, 2017, p.53).
 Identifying Multivariate Outliers with Mahalanobis Distance-->[https://www.youtube.com/watch?v=AXLAX6r5JgE]
 Mahalanobis Distance -->[https://www.youtube.com/watch?v=spNpfmWZBmg]
 ''Contribution by: Britany Kuslis, WCSU Cohort 8''

@@ Line 58: / Line 58: @@
 == Detection of Multivariate Outliers: Mahalanobis Distance ==
-The Mahalanobis Distance statistic measures "the multivariate 'distance' between each case and the group multivariate mean (known as centroid) taking into account the correlations between the variables" (Meyers, Gamst, & Guarino, 2017, p. 52). This method is used to determine if there are scores that vary from the mean of a set of DV's. The Mahalanobis distances details how far a case is from the group center mass of the predictor or IV's.  The greater the distance the higher the possibility of a multivariate outlier.  According to Lawrence S. Meyers, Glenn Gamst and A.J. Guarino, "Each case is evaluated using the chi square distribution with a stringent alpha level of .001.  Cases that reach this significance threshold can be considered multivariate outliers and possible candidates for elimination. This approach is also not without its critics (e.g., Wilcox, 2012) for alternative approaches to multivariate outlier detection" (Meyers, Gamst, & Guarino, 2017, p.53).
+The '''Mahalanobis Distance''' statistic measures "the multivariate 'distance' between each case and the group multivariate mean (known as centroid) taking into account the correlations between the variables" (Meyers, Gamst, & Guarino, 2017, p. 52). This method is used to determine if there are scores that vary from the mean of a set of DV's. The Mahalanobis distances details how far a case is from the group center mass of the predictor or IV's.  The greater the distance the higher the possibility of a multivariate outlier.  According to Lawrence S. Meyers, Glenn Gamst and A.J. Guarino, "Each case is evaluated using the chi square distribution with a stringent alpha level of .001.  Cases that reach this significance threshold can be considered multivariate outliers and possible candidates for elimination. This approach is also not without its critics (e.g., Wilcox, 2012) for alternative approaches to multivariate outlier detection" (Meyers, Gamst, & Guarino, 2017, p.53).
 Identifying Multivariate Outliers with Mahalanobis Distance-->[https://www.youtube.com/watch?v=AXLAX6r5JgE]

← Older revision		Revision as of 02:25, 17 November 2019
Line 28:		Line 28:
	== Outliers ==		== Outliers ==

−	Outliers are values that are "extreme or unusual values on a single variable (univariate) or on a combination of variables (multivariate)" (Meyers, Gamst, & Guarino, 2017, p. 48).	+	'''Outliers''' are values that are "extreme or unusual values on a single variable (univariate) or on a combination of variables (multivariate)" (Meyers, Gamst, & Guarino, 2017, p. 48).