Академический Документы
Профессиональный Документы
Культура Документы
Our strategy for solving problems about violations of assumptions and outliers will include the following steps:
1. 2. Run type of regression specified in problem statement on variables using full data set. Test the dependent variable for normality. If it does not satisfy the criteria for normality unless transformed, substitute the transformed variable in the remaining tests that call for the use of the dependent variable. Test for normality, linearity, homoscedasticity using scripts. Decide which transformations should be used. Substitute transformations and run regression entering all independent variables, saving studentized residuals and Mahalanobis distance scores. Compute probabilities for D. Remove the outliers (studentized residual greater than 3 or Mahalanobis D with p <= 0.001), and run regression with the method and variables specified in the problem. Compare R for analysis using transformed variables and omitting outliers (step 5) to R obtained for model using all data and original variables (step 1).
3. 4. 5. 6.
If dependent variable is not normally distributed: Try log, square root, and inverse transformation. Use first transformed variable that satisfies normality criteria. If no transformation satisfies normality criteria, use untransformed variable and add caution for violation of assumption. If a transformation satisfies normality, use the transformed variable in the tests of the independent variables.
If independent variable is normally distributed and linearly related to dependent variable, use as is. If independent variable is normally distributed but not linearly related to dependent variable: Try log, square root, square, and inverse transformation. Use first transformed variable that satisfies linearity criteria and does not violate normality criteria If no transformation satisfies linearity criteria and does not violate normality criteria, use untransformed variable and add caution for violation of assumption
We evaluate the regression assumptions and detect outliers with a view toward strengthening the relationship. This may not happen. The regression may be the same, it may be weaker, and it may be stronger. We cannot be certain of the impact until we run the regression again. In the end, we may opt not to exclude outliers and not to employ transformations; the analysis informs us of the consequences of doing either.
Notes
Whenever you start a new problem, make sure you have removed variables created for previous analysis and have included all cases back into the data set. I have added the square transformation to the checkboxes for transformations in the normality script. Since this is an option for linearity, we need to be able to evaluate its impact on normality.
If you change the options for output in pivot tables from labels to names, you will get an error message when you use the linearity script. To solve the problem, change the option for output in pivot tables back to labels.
Problem 1
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.01 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to identify the best subset of predictors of "total family income" [income98] from the list: "sex" [sex], "how many in family earned money" [earnrs], and "income" [rincom98]. After substituting transformed variables to satisfy regression assumptions and removing outliers, the total proportion of variance explained by the regression analysis increased by 10.8%.
1. 2. 3. 4.
Dissecting problem 1 - 1
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.01 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to identify the best subset of predictors The problem may give us different of "total family income" [income98] from the list: "sex" [sex], "how many levels of significance for the analysis. in family earned money" [earnrs], and "income" [rincom98]. After satisfy regression assumptions and removing outliers, the total proportion of variance explained by the regression analysis increased by 10.8%.
In this problem, we are told to use 0.01 as alpha for the regression analysis as well as for testing to substituting transformed variables assumptions.
1. 2. 3. 4.
Dissecting problem 1 - 2
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.01 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to identify the best subset of predictors of "total family income" [income98] from the list: "sex" [sex], "how many in family earned money" [earnrs], and "income" [rincom98]. After substituting transformed variables to satisfy regression assumptions The method for selecting variables is and removing outliers, the total proportion of variance explained by the derived from the research question. regression analysis increased by 10.8%.
1. 2. 3. 4.
In this problem we are asked to idnetify the best subset of predicotrs, so we do a stepwise multiple regression.
Dissecting problem 1 - 3
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application ofofatesting statistic? Assume and that there is no problem with The purpose for assumptions outliers is to stronger The mainof question bethe regression missing data. identify Use a alevel of model. significance 0.01 to for in this problem is whether or not the use analysis. Use answered a level of significance of 0.01 for evaluating assumptions. transformed variables to satisfy assumptions and the The of predictors of "total family income" [income98] from the list: "sex" [sex], "how many in family earned money" [earnrs], and "income" [rincom98]. After substituting transformed variables to satisfy regression assumptions and removing outliers, the total proportion of variance explained by the regression analysis increased by 10.8%.
removal of outliers improves the overall relationship between the independent variables and the dependent research variable, question requires us to identify the best subset as measured by R.
1. 2. 3. 4.
True Specifically, the question asks whether or True with caution not the R for a regression analysis after substituting transformed variables and False eliminating outliers is 10.8% higher than a regression analysis using the original format Inappropriate application of a statistic
for all variables and including all cases.
To start out, we run a stepwise multiple regression analysis with income98 as the dependent variable and sex, earnrs, and rincom98 as the independent variables.
Prior to any transformations of variables to satisfy the assumptions of multiple regression or removal of outliers, the proportion of variance in the dependent variable explained by the independent variables (R) was 51.1%. This is the benchmark that we will use to evaluate the utility of transformations and the elimination of outliers.
For this particular question, we are not interested in the statistical significance of the overall relationship prior to transformations and removing outliers. In fact, it is possible that the relationship is not statistically significant due to variables that are not normal, relationships that are not linear, and the inclusion of outliers.
In evaluating assumptions, the first step is to examine the normality of the dependent variable. If it is not normally distributed, or cannot be normalized with a transformation, it can affect the relationships with all other variables. To test the normality of the dependent variable, run the script: NormalityAssumptionAndTransformations.SBS
First, move the dependent variable INCOME98 to the list box of variables to test.
.161 .320
The dependent variable "total family income" [income98] satisfies the criteria for a normal distribution. The skewness (-0.628) and kurtosis (-0.248) were both between -1.0 and +1.0. No transformation is necessary.
To evaluate the linearity of the relationship between number of earners and total family income, run the script for the assumption of linearity: LinearityAssumptionAndTransformations.SBS Second, move the independent variable, EARNRS, to the list box for independent variables.
TOTAL FAMILY INCOME Pearson Correlation Sig. (2-tailed) N HOW MANY IN FAMILY Pearson Correlation EARNED MONEY Sig. (2-tailed) N Logarithm of EARNRS Pearson Correlation [LG10( 1+EARNRS)] Sig. (2-tailed) N Square of EARNRS [(EARNRS)**2] Square Root of EARNRS [SQRT( 1+EARNRS)] Inverse of EARNRS [-1/( 1+EARNRS)] Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N
HOW MANY Logarithm of Square of Square Root TOTAL IN FAMILY EARNRS EARNRS of EARNRS Inverse of FAMILY EARNED [LG10( [(EARNR [SQRT( EARNRS [-1/( INCOME MONEY The 1+EARNRS)] S)**2] 1+EARNRS)] independent variable "how many in 1+EARNRS)] 1 .505** .536** .376** .527** .526* family earned money" [earnrs] satisfies . .000 the criteria .000 .000 .000 for the assumption of .000 linearity with the dependent variable 229 228 228 228 228 228 "total family income" [income98], but .505** 1 .959** .908** .989** .871* the .000 assumption of .000 . does not satisfy .000 .000 .000 normality. The evidence of linearity in 228 269 269 269 269 269 the relationship between the .536** .959** 1 .759** .990** .973* independent variable "how many in .000 .000 . .000 .000 .000 228 .376** .000 228 .527** .000 228 .526** .000 228
family earned money" [earnrs] and the variable "total 269 dependent269 269 family income" 269 [income98] was the statistical .908** .759** 1 .839** significance of the correlation coefficient .000 (r = 0.505). .000 . .000 The probability for the 269 correlation269 269 coefficient was <0.001,269 less than or equal to the .839** level of significance .989** .990** 1 of 0.01. We reject the null hypothesis .000 .000 .000 . that r = 0 and conclude that there is 269 269 269 269 a linear relationship between the .871** .973** .606** .932** variables.
.000 269 .000 269 .000 269 .000 269
269
After evaluating the dependent variable, we examine the normality of each metric variable and linearity of its relationship with the dependent variable. To test the normality of number of earners in family, run the script: NormalityAssumptionAndTransformations.SB S
First, move the independent variable EARNRS to the list box of variables to test.
.149 .296
The independent variable "how many in family earned money" [earnrs] satisfies the criteria for the assumption of linearity with the dependent variable "total family income" [income98], but does not satisfy the assumption of normality.
In evaluating normality, the skewness (0.742) was between -1.0 and +1.0, but the kurtosis (1.324) was outside the range from -1.0 to +1.0.
The square root transformation also has values of skewness and kurtosis in the acceptable range. However, by our order of preference for which transformation to use, the logarithm is preferred.
The logarithmic transformation improves the normality of "how many in family earned money" [earnrs] without a reduction in the strength of the relationship to "total family income" [income98]. In evaluating normality, the skewness (-0.483) and kurtosis (-0.309) were both within the range of acceptable values from -1.0 to +1.0. The correlation coefficient for the transformed variable is 0.536.
The independent variable, how many in family earned money, had a linear relationship to the dependent variable, total family income. The logarithmic transformation improves the normality of "how many in family earned money" [earnrs] without a reduction in the strength of the relationship to "total family income" [income98]. We will substitute the logarithmic transformation of how many in family earned money in the regression analysis.
After evaluating the dependent variable, we examine the normality of each metric variable and linearity of its relationship with the dependent variable. To test the normality of respondents in family, run the script: NormalityAssumptionAndTransformations.SB S
First, move the independent variable RINCOM89 to the list box of variables to test.
.187 .373
The independent variable "income" [rincom98] satisfies the criteria for both the assumption of normality and the assumption of linearity with the dependent variable "total family income" [income98]. In evaluating normality, the skewness (-0.686) and kurtosis (-0.253) were both within the range of acceptable values from -1.0 to +1.0.
To evaluate the linearity of the relationship between respondents income and total family income, run the script for the assumption of linearity: LinearityAssumptionAndTransformations.SBS Second, move the independent variable, RINCOM89, to the list box for independent variables.
Pearson Correlation Sig. (2-tailed) N RESPONDENTS INCOME Pearson Correlation Sig. (2-tailed) N Logarithm of RINCOM98 Pearson Correlation [LG10( 24-RINCOM98)] Sig. (2-tailed) N Square of RINCOM98 [(RINCOM98)**2] Pearson Correlation Sig. (2-tailed) N Square Root of Pearson Correlation RINCOM98 [SQRT( Sig. (2-tailed) 24-RINCOM98)] N Inverse of RINCOM98 [-1/( Pearson Correlation 24-RINCOM98)] Sig. (2-tailed) N
correlation coefficient was <0.001, less than or equal 168 168to the level 168of significance 168 of 0.01. We reject the null hypothesis .967** that r = 0-.976** and conclude 1 that there -.993** is a .000 .000 . .000 linear relationship between the 168 168 168 variables. 168
.974** .000 168 .848** .000 168 -.993** .000 168 -.718** .000 168 1 . 168 .714** .000 168
Homoscedasticity: sex
First, move the dependent variable INCOME98 to the text box for the dependent variable.
To evaluate the homoscedasticity of the relationship between sex and total family income, run the script for the assumption of homogeneity of variance: HomoscedasticityAssumptionAnd Transformations.SBS
Second, move the independent variable, SEX, to the list box for independent variables.
Homoscedasticity: sex
Based on the Levene Test, the variance in "total family income" [income98] is homogeneous for the categories of "sex" [sex]. The probability associated with the Levene Statistic (0.031) is greater than the level of significance, so we fail to reject the null hypothesis and conclude that the homoscedasticity assumption is satisfied.
Even though we do not need a transformation for any of the variables in this analysis, we will demonstrate how to use a script, such as the normality script, to add a transformed variable to the data set, e.g. a logarithmic transformation for highest year of school.
First, move the variable that we want to transform to the list box of variables to test.
Second, mark the checkbox for the transformation we want to add to the data set, and clear the other checkboxes.
Third, clear the checkbox for Delete transformed variables from the data. This will save the transformed variable.
Whenever we add transformed variables to the data set, we should be sure to delete them before starting another analysis.
We use the regression procedure to identify both univariate and multivariate outliers. We start with the same dialog we used for the last analysis, in which income98 as the dependent variable and sex, earnrs, and rincom98 were the independent variables.
First, we substitute the logarithmic transformation of earnrs, logearn, into the list of independent variables.
Second, we change the method of entry from Stepwise to Enter so that all variables will be included in the detection of outliers.
Third, we want to save the calculated values of the outlier statistics to the data set. Click on the Save button to specify what we want to save.
Second, mark the checkbox for Mahalanobis in the Distances panel. This will compute Mahalanobis distances for the set of independent variables.
Second, to complete the specifications for the CDF.CHISQ function, type the name of the variable containing the D scores, mah_1, followed by a comma, followed by the number of variables used in the calculations, 3. Since the CDF function (cumulative density function) computes the cumulative probability from the left end of the distribution up through a given value, we subtract it from 1 to obtain the probability in the upper tail of the distribution.
Third, click on the OK button to signal completion of the computer variable dialog.
Multivariate outliers
Using the probabilities computed in p_mah_1 to identify outliers, scroll down through the list of case to see if we can find cases with a probability less than 0.001. There are no outliers for the set of independent variables.
Univariate outliers
Similarly, we can scroll down the values of sre_1, the studentized residual to see the one outlier with a value larger than 3.0.
Based on these criteria, there are 4 outliers.There are 4 cases that have a score on the dependent variable that is sufficiently unusual to be considered outliers (case 20000357: studentized residual=3.08; case 20000416: studentized residual=3.57; case 20001379: studentized residual=3.27; case 20002702: studentized residual=-3.23).
To omit the outliers from the analysis, we select in the cases that are not outliers.
First, select the Select Cases command from the Transform menu.
First, mark the If condition is satisfied option button to indicate that we will enter a specific condition for including cases.
Second, click on the If button to specify the criteria for inclusion in the analysis.
To eliminate the outliers, we request the cases that are not outliers. The formula specifies that we should include cases if the studentized residual (regardless of sign) if less than 3 and the probability for Mahalanobis D is higher than the level of significance, 0.001. After typing in the formula, click on the Continue button to close the dialog box,
SPSS identifies the excluded cases by drawing a slash mark through the case number. Most of the slashes are for cases with missing data, but we also see that the case with the low probability for Mahalanobis distance is included in those that will be omitted.
We run the regression again, excluding the outliers. Select the Regression | Linear command from the Analyze menu.
We specify the dependent and independent variables, substituting any transformed variables required by assumptions.
When we used regression to detect outliers, we entered all variables. Now we are testing the relationship specified in the problem, so we change the method to Stepwise.
On our last run, we instructed SPSS to save studentized residuals and Mahalanobis distance. To prevent these values from being calculated again, click on the Save button.
Once we have removed outliers, we need to check the sample size requirement for regression. Since we will need the descriptive statistics for this, click on the Statistics button.
Having specified the output needed for the analysis, we click on the OK button to obtain the regression output.
The minimum ratio of valid cases to independent variables for stepwise multiple regression is 5 to 1. After removing 4 outliers, there are 159 valid cases and 3 independent variables. The ratio of cases to independent variables for this analysis is 53.0 to 1, which satisfies the minimum requirement. In addition, the ratio of 53.0 to 1 satisfies the preferred ratio of 50 to 1.
Descriptiv e Statistics TOTAL FAMILY INCOME RESPONDENTS SEX RESPONDENTS INCOME Logarithm of EARNRS [LG10( 1+EARNRS)] Mean 17.09 1.55 13.76 .424896 Std. Deviation 4.073 .499 5.133 .1156559 N 159 159 159 159
116.957
.000 b
84.107
.000 c
The probability of the F statistic (84.107) for the regression 1+EARNRS)] relationship which includes these variables is <0.001, less c. Predictors: (Constant), RESPONDENTS INCOME, Logarithm of EARNRS [LG10( than or equal to the level of significance of 0.01. We reject 1+EARNRS)], RESPONDENTS SEX the null hypothesis that there is no relationship between d. Dependent Variable: TOTAL FAMILY INCOME the best subset of independent variables and the dependent variable (R = 0). We support the research hypothesis that there is a statistically significant relationship between the best subset of independent variables and the dependent variable.
a. Predictors: (Constant), RESPONDENTS INCOME b. Predictors: (Constant), RESPONDENTS INCOME, Logarithm of EARNRS [LG10( 1+EARNRS)]
Prior to any transformations of variables to satisfy c. Predictors: (Constant), RESPONDENTS INCOME, the assumptions of multiple regression or removal Logarithm of EARNRS [LG10( 1+EARNRS)], of outliers, the proportion of variance in the RESPONDENTS SEX dependent variable explained by the independent
variables (R) was 51.1%. After transformed variables were substituted to satisfy assumptions and outliers were removed from the sample, the proportion of variance explained by the regression analysis was 61.9%, a difference of 10.8%.
The answer to the question is true with caution. A caution is added because of the inclusion of ordinal level variables.
Problem 2
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.05 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to examine the relationship of "age" [age], "highest year of school completed" [educ], and "sex" [sex] to the dependent variable "occupational prestige score" [prestg80]. After substituting transformed variables to satisfy regression assumptions and removing outliers, the proportion of variance explained by the regression analysis increased by 3.6%. 1. 2. 3. 4. True True with caution False Inappropriate application of a statistic
Dissecting problem 2 - 1
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.05 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to examine the relationship of "age" The problem may give us different [age], "highest year of school completed" [educ], and "sex" [sex] to the levels of significance for the analysis. dependent variable "occupational prestige score" [prestg80].
In this problem, we are told to use 0.05 as alpha for the regression and the more conservative After substitutinganalysis transformed variables to satisfy regression 0.01 as the alpha in testing assumptions and removing outliers, the proportion of variance assumptions.
1. 2. 3. 4.
Dissecting problem 2 - 2
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem with missing data. Use a level of significance of 0.05 for the regression analysis. Use a level of significance of 0.01 for evaluating assumptions. The research question requires us to examine the relationship of "age" [age], "highest year of school completed" [educ], and "sex" [sex] to the dependent variable "occupational prestige score" [prestg80]. After substituting transformed variables to satisfy regression The method for selecting variables is assumptions andderived removing outliers, proportion of variance from the research the question. explained by the regression analysis increased by 3.6%.
1. 2. 3. 4.
If we are asked to examine a relationship without any statement about control variables or the best subset of variables, we do a standard multiple regression.
Dissecting problem 2 - 3
In the dataset GSS2000.sav, is the following statement true, false, or an incorrect application of a statistic? Assume that there is no problem The purpose of testing for assumptions and outliers is to with missing data. Use a level of significance of 0.05 for the regression identify a stronger model. The main question to be analysis. Use answered a level of significance of 0.01 forthe evaluating assumptions. in this problem is whether or not use The of "age" [age], "highest year of school completed" [educ], and "sex" [sex] to the dependent variable "occupational prestige score" [prestg80]. After substituting transformed variables to satisfy regression assumptions and removing outliers, the proportion of variance explained by the regression analysis increased by 3.6%.
transformed variables to satisfy assumptions and the removal of outliers improves the overall relationship the requires independent variables and the dependent research between question us to examine the relationship variable, as measured by R.
1. 2. 3. 4.
True True with caution Specifically, the question asks whether or not the R for a regression analysis after False substituting transformed variables and eliminating outliers is 3.6% higher than a Inappropriate application a statistic regression of analysis using the original format
for all variables and including all cases.
Prior to any transformations of variables to satisfy the assumptions of multiple regression or removal of outliers, the proportion of variance in the dependent variable explained by the independent variables (R) was 27.1%. This is the benchmark that we will use to evaluate the utility of transformations and the elimination of outliers.
For this particular question, we are not interested in the statistical significance the overall relationship prior to transformations and removing outliers. In fact, it is possible that the relationship is not statistically significant due to variables that are not normal, relationships that are not linear, and the inclusion of outliers.
In evaluating assumptions, the first step is to examine the normality of the dependent variable. If it is not normally distributed, or cannot be normalized with a transformation, it can affect the relationships with all other variables. To test the normality of the dependent variable, run the script: NormalityAssumptionAndTransformations.SBS
First, move the dependent variable PRESTG80 to the list box of variables to test.
The dependent variable "occupational prestige score" [prestg80] satisfies the criteria for a normal distribution. The skewness (0.401) and kurtosis (-0.630) were both between -1.0 and +1.0. No transformation is necessary.
After evaluating the dependent variable, we examine the normality of each metric variable and linearity of its relationship with the dependent variable. To test the normality of age, run the script: NormalityAssumptionAndTransformations.SB S
First, move the independent variable AGE to the list box of variables to test.
.148 .295
The independent variable "age" [age] satisfies the criteria for the assumption of normality, but does not satisfy the assumption of linearity with the dependent variable "occupational prestige score" [prestg80]. In evaluating normality, the skewness (0.595) and kurtosis (-0.351) were both within the range of acceptable values from -1.0 to +1.0.
To evaluate the linearity of the relationship between age and occupational prestige, run the script for the assumption of linearity: LinearityAssumptionAndTransformations.SBS Second, move the independent variable, AGE, to the list box for independent variables.
Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N
AGE OF Logarithm of Square of Square Root Inverse of The evidence of nonlinearity in the RESPON AGE AGE of AGE AGE relationship between the independent DENT [LG10(AGE)] [(AGE)**2] [SQRT(AGE)] [-1/(AGE)] variable "age" [age] and the dependent .024 variable .059 -.004 .041 .096 "occupational prestige score" .706 [prestg80] .348 .956 .128 was the lack of statistical.518 coefficient 255 significance 255of the correlation 255 255 255 (r = 0.024). The probability for the 1 .979** .983** .995** .916** correlation coefficient was 0.706, greater . .000 .000 .000 .000 than the level of significance of 0.01. We 270 cannot reject 270 the null 270 270 270 hypothesis that r = 0, .979** and cannot 1 .994** .978** conclude .926** that there is a linear the variables. .000 .000 relationship .between .000 .000 270 Since none 270 270 of the transformations to270 improve linearity were successful, it is an .983** .926** 1 .960** indication that the problem may be a weak .000 relationship, .000 rather than .a curvilinear .000 270 relationship 270correctable 270 by using a 270 transformation. A weak relationship is not .995** .994** .960** 1 a violation of the assumption of linearity, .000 .000 .000 .and does not require a caution. 270 270 270 270 .916** .978** .832** .951** .000 .000 .000 .000 270 270 270 270 270 .832** .000 270 .951** .000 270 1 . 270
Square of AGE [(AGE)**2] Pearson Correlation Sig. (2-tailed) N Square Root of AGE Pearson Correlation [SQRT(AGE)] Sig. (2-tailed) N Inverse of AGE [-1/(AGE)] Pearson Correlation Sig. (2-tailed) N
No transformation will be used - it would not help linearity and is not needed for normality.
To evaluate the linearity of the relationship between highest year of school and occupational prestige, run the script for the assumption of linearity: LinearityAssumptionAndTransformations.SBS Second, move the independent variable, EDUC, to the list box for independent variables.
RS OCCUPATIONAL PRESTIGE SCORE (1980) HIGHEST YEAR OF SCHOOL COMPLETED Logarithm of EDUC [LG10( 21-EDUC)]
Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N Pearson Correlation Sig. (2-tailed) N
RS OCCUPA TIONAL HIGHEST Square Root PRESTIG YEAR OF The Logarithm of Square of "highest of EDUC Inverse of independent variable year E SCORE SCHOOL of EDUC [LG10( EDUC [SQRT( EDUC [-1/( school completed" [educ] satisfies (1980) COMPLETEDthe 21-EDUC)] [(EDUC)**2] 21-EDUC)] 21-EDUC)] criteria for the assumption of 1 .495** -.512** .528** variable -.518** -.423 linearity with the dependent . .000 "occupational .000 prestige score" .000 .000 .000 255 254 [prestg80], 254 254 254 but does not satisfy the 254 assumption of normality. The evidence .495** 1 -.920** .980** -.982** -.699 of linearity in the relationship between .000 . .000 .000 .000 .000 the independent variable "highest year 254 269 269 269 269 269 of school completed" [educ] and the -.512** -.920** 1 -.969** .977** .915 dependent variable "occupational .000 .000 . .000 .000 .000 254 .528** .000 254 -.518** .000 254 -.423** .000 254
Square of EDUC [(EDUC)**2] Square Root of EDUC [SQRT( 21-EDUC)] Inverse of EDUC [-1/( 21-EDUC)]
prestige score" [prestg80] was the of the correlation 269 statistical significance 269 269 269 coefficient (r = 0.495). The probability .980** -.969** 1 for the correlation coefficient was -.997** .000 <0.001, less .000than or equal . to the level .000 269 of significance 269 of 0.01. We 269 reject the 269 -.982** .977** that r = -.997** 1 null hypothesis 0 and conclude is a linear relationship .000 that there.000 .000 . between the variables. 269 269 269 269
-.699** .000 269 .915** .000 269 -.789** .000 269 .812** .000 269
269
To test the normality of EDUC, Highest year of school completed, run the script: NormalityAssumptionAndTransformations.SB S
First, move the dependent variable EDUC to the list box of variables to test.
.149 .296
In evaluating normality, the skewness (-0.137) was between -1.0 and +1.0, but the kurtosis (1.246) was outside the range from -1.0 to +1.0. None of the transformations for normalizing the distribution of "highest year of school completed" [educ] were effective.
The independent variable, highest year of school, had a linear relationship to the dependent variable, occupational prestige. The independent variable, highest year of school, did not satisfy the criteria for normality. None of the transformations for normalizing the distribution of "highest year of school completed" [educ] were effective. No transformation will be used - it would not help normality and is not needed for linearity. A caution should be added to any findings.
Homoscedasticity: sex
First, move the dependent variable PRESTG80 to the text box for the dependent variable.
To evaluate the homoscedasticity of the relationship between sex and occupational prestige, run the script for the assumption of homogeneity of variance: HomoscedasticityAssumptionAnd Transformations.SBS
Second, move the independent variable, SEX, to the list box for independent variables.
Homoscedasticity: sex
Based on the Levene Test, the variance in "occupational prestige score" [prestg80] is homogeneous for the categories of "sex" [sex]. The probability associated with the Levene Statistic (0.808) is greater than the level of significance, so we fail to reject the null hypothesis and conclude that the homoscedasticity assumption is satisfied. Even if we violate the assumption, we would not do a transformation since it could impact the relationships of the other independent variables with the dependent variable.
Even though we do not need a transformation for any of the variables in this analysis, we will demonstrate how to use a script, such as the normality script, to add a transformed variable to the data set, e.g. a logarithmic transformation for highest year of school.
First, move the variable that we want to transform to the list box of variables to test.
Second, mark the checkbox for the transformation we want to add to the data set, and clear the other checkboxes.
Third, clear the checkbox for Delete transformed variables from the data. This will save the transformed variable.
Whenever we add transformed variables to the data set, we should be sure to delete them before starting another analysis.
We can use the regression procedure to identify both univariate and multivariate outliers. We start with the same dialog we used for the last analysis, in which prestg90 as the dependent variable and age, educ, and sex were the independent variables. If we need to use any transformed variables, we would substitute them now.
We will save the calculated values of the outlier statistics to the data set.
Second, mark the checkbox for Mahalanobis in the Distances panel. This will compute Mahalanobis distances for the set of independent variables.
Second, to complete the specifications for the CDF.CHISQ function, type the name of the variable containing the D scores, mah_1, followed by a comma, followed by the number of variables used in the calculations, 3. Since the CDF function (cumulative density function) computes the cumulative probability from the left end of the distribution up through a given value, we subtract it from 1 to obtain the probability in the upper tail of the distribution.
Third, click on the OK button to signal completion of the computer variable dialog.
Using the probabilities computed in p_mah_1 to identify outliers, scroll down through the list of case to see the one case with a probability less than 0.001. There is 1 case that has a combination of scores on the independent variables that is sufficiently unusual to be considered an outlier (case 20001984: Mahalanobis D=16.97, p=0.0007).
Similarly, we can scroll down the values of sre_1, the studentized residual to see the one outlier with a value larger than 3.0.
There is 1 case that has a score on the dependent variable that is sufficiently unusual to be considered an outlier (case 20000391: studentized residual=4.14).
To omit the outliers from the analysis, we select in the cases that are not outliers.
First, select the Select Cases command from the Transform menu.
First, mark the If condition is satisfied option button to indicate that we will enter a specific condition for including cases.
Second, click on the If button to specify the criteria for inclusion in the analysis.
To eliminate the outliers, we request the cases that are not outliers. The formula specifies that we should include cases if the studentized residual (regardless of sign) if less than 3 and the probability for Mahalanobis D is higher than the level of significance, 0.001. After typing in the formula, click on the Continue button to close the dialog box,
SPSS identifies the excluded cases by drawing a slash mark through the case number. Most of the slashes are for cases with missing data, but we also see that the case with the low probability for Mahalanobis distance is included in those that will be omitted.
We run the regression again, excluding the outliers. Select the Regression | Linear command from the Analyze menu.
On our last run, we instructed SPSS to save studentized residuals and Mahalanobis distance. To prevent these values from being calculated again, click on the Save button.
Once we have removed outliers, we need to check the sample size requirement for regression. Since we will need the descriptive statistics for this, click on the Statistics button.
Having specified the output needed for the analysis, we click on the OK button to obtain the regression output.
The minimum ratio of valid cases to independent variables for multiple regression is 5 to 1. After removing 2 outliers, there are 252 valid cases and 3 independent variables. The ratio of cases to independent variables for this analysis is 84.0 to 1, which satisfies the minimum requirement. In addition, the ratio of 84.0 to 1 satisfies the preferred ratio of 15 to 1.
The probability of the F statistic (36.639) for the overall regression relationship is <0.001, less than or equal to the level of significance of 0.05. We reject the null hypothesis that there is no relationship between the set of independent variables and the dependent variable (R = 0). We support the research hypothesis that there is a statistically significant relationship between the set of independent variables and the dependent variable.
Prior to any transformations of variables to satisfy the assumptions of multiple regression or removal of outliers, the proportion of variance in the dependent variable explained by the independent variables (R) was 27.1%. No transformed variables were substituted to satisfy assumptions, but outliers were removed from the sample. The proportion of variance explained by the regression analysis after removing outliers was 30.7%, a difference of 3.6%.
The answer to the question is true with caution. A caution is added because of a violation of regression assumptions.
The following is a guide to the decision process for answering problems about the impact of assumptions and outliers on analysis:
Dependent variable metric? Independent variables metric or dichotomous?
No
Yes
No
Yes
Run baseline regression and record R for future reference, using method for including variables identified in the research question.
No
Try: 1. Logarithmic transformation 2. Square root transformation 3. Inverse transformation If unsuccessful, add caution
Yes
Try: 1. Logarithmic transformation 2. Square root transformation (3. Square transformation) 4. Inverse transformation If unsuccessful, add caution
No
Yes
No
Add caution
Yes
Yes
Remove outliers from data
No
No
Yes
Run regression again using transformed variables and eliminating outliers
Yes
No
False
Yes
Increase in R correct?
No
False
Yes
No
Yes
Yes
No
True