What statistical analysis should I use?

Chip Oglesby bio photo By Chip Oglesby

One sample t-test

A one sample t-test allows us to test whether a sample mean (of a normally distributed interval variable) significantly differs from a hypothesized value. For example, using the hsb2 data file, say we wish to test whether the average writing score (write) differs significantly from 50. We can do this as shown below.

t.test(write, mu = 50)
##
## 	One Sample t-test
##
## data:  write
## t = 4.1403, df = 199, p-value = 5.121e-05
## alternative hypothesis: true mean is not equal to 50
## 95 percent confidence interval:
##  51.45332 54.09668
## sample estimates:
## mean of x
##    52.775

The mean of the variable write for this particular sample of students is 52.775, which is statistically significantly different from the test value of 50. We would conclude that this group of students has a significantly higher mean on the writing test than 50.

One sample median test

A one sample median test allows us to test whether a sample median differs significantly from a hypothesized value. We will use the same variable, write, as we did in the one sample t-test example above, but we do not need to assume that it is interval and normally distributed (we only need to assume that write is an ordinal variable and that its distribution is symmetric). We will test whether the median writing score (write) differs significantly from 50.

wilcox.test(write, mu = 50)
##
## 	Wilcoxon signed rank test with continuity correction
##
## data:  write
## V = 13177, p-value = 3.702e-05
## alternative hypothesis: true location is not equal to 50

The results indicate that the median of the variable write for this group is statistically significantly different from 50.

Binomial test

A one sample binomial test allows us to test whether the proportion of successes on a two-level categorical dependent variable significantly differs from a hypothesized value. For example, using the hsb2 data file, say we wish to test whether the proportion of females (female) differs significantly from 50%, i.e., from .5. We can do this as shown below.

prop.test(sum(female), length(female), p = 0.5)
##
## 	1-sample proportions test with continuity correction
##
## data:  sum(female) out of length(female), null probability 0.5
## X-squared = 1.445, df = 1, p-value = 0.2293
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
##  0.4733037 0.6149394
## sample estimates:
##     p
## 0.545

The results indicate that there is no statistically significant difference (p = .2292). In other words, the proportion of females does not significantly differ from the hypothesized value of 50%.

Chi-square goodness of fit

A chi-square goodness of fit test allows us to test whether the observed proportions for a categorical variable differ from hypothesized proportions. For example, let’s suppose that we believe that the general population consists of 10% Hispanic, 10% Asian, 10% African American and 70% White folks. We want to test whether the observed proportions from our sample differ significantly from these hypothesized proportions. To conduct the chi-square goodness of fit test, you need to first download the csgof program that performs this test.

chisq.test(table(race), p = c(10, 10, 10, 70)/100)
##
## 	Chi-squared test for given probabilities
##
## data:  table(race)
## X-squared = 5.0286, df = 3, p-value = 0.1697

These results show that racial composition in our sample does not differ significantly from the hypothesized values that we supplied (chi-square with three degrees of freedom = 5.03, p = .1697).

Two independent samples t-test

An independent samples t-test is used when you want to compare the means of a normally distributed interval dependent variable for two independent groups. For example, using the hsb2 data file, say we wish to test whether the mean for write is the same for males and females.

t.test(write ~ female)
##
## 	Welch Two Sample t-test
##
## data:  write by female
## t = -3.6564, df = 169.71, p-value = 0.0003409
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -7.499159 -2.240734
## sample estimates:
## mean in group 0 mean in group 1
##        50.12088        54.99083

The results indicate that there is a statistically significant difference between the mean writing score for males and females (t = -3.7341, p = .0002). In other words, females have a statistically significantly higher mean score on writing (54.99) than males (50.12).

Wilcoxon-Mann Whitney test

The Wilcoxon-Mann-Whitney test is a non-parametric analog to the independent samples t-test and can be used when you do not assume that the dependent variable is a normally distributed interval variable (you only assume that the variable is at least ordinal). You will notice that the Stata syntax for the Wilcoxon-Mann-Whitney test is almost identical to that of the independent samples t-test. We will use the same data file (the hsb2 data file) and the same variables in this example as we did in the independent t-test example above and will not assume that write, our dependent variable, is normally distributed.

wilcox.test(write ~ female)
##
## 	Wilcoxon rank sum test with continuity correction
##
## data:  write by female
## W = 3606, p-value = 0.0008749
## alternative hypothesis: true location shift is not equal to 0

The results suggest that there is a statistically significant difference between the underlying distributions of the write scores of males and the write scores of females (z = -3.329, p = 0.0009). You can determine which group has the higher rank by looking at the how the actual rank sums compare to the expected rank sums under the null hypothesis. The sum of the female ranks was higher while the sum of the male ranks was lower. Thus the female group had higher rank.

Chi-square test

A chi-square test is used when you want to see if there is a relationship between two categorical variables. In Stata, the chi2 option is used with the tabulate command to obtain the test statistic and its associated p-value. Using the hsb2 data file, let’s see if there is a relationship between the type of school attended (schtyp) and students’ gender (female). Remember that the chi-square test assumes the expected value of each cell is five or higher. This assumption is easily met in the examples below. However, if this assumption is not met in your data, please see the section on Fisher’s exact test below.

chisq.test(table(female, schtyp))
##
## 	Pearson's Chi-squared test with Yates' continuity correction
##
## data:  table(female, schtyp)
## X-squared = 0.00054009, df = 1, p-value = 0.9815

These results indicate that there is no statistically significant relationship between the type of school attended and gender (chi-square with one degree of freedom = 0.0470, p = 0.828).

Fisher’s exact test

The Fisher’s exact test is used when you want to conduct a chi-square test, but one or more of your cells has an expected frequency of five or less. Remember that the chi-square test assumes that each cell has an expected frequency of five or more, but the Fisher’s exact test has no such assumption and can be used regardless of how small the expected frequency is. In the example below, we have cells with observed frequencies of two and one, which may indicate expected frequencies that could be below five, so we will use Fisher’s exact test with the exact option on the tabulate command.

fisher.test(table(race, schtyp))
##
## 	Fisher's Exact Test for Count Data
##
## data:  table(race, schtyp)
## p-value = 0.5975
## alternative hypothesis: two.sided

These results suggest that there is not a statistically significant relationship between race and type of school (p = 0.597). Note that the Fisher’s exact test does not have a “test statistic”, but computes the p-value directly.

One-way ANOVA

A one-way analysis of variance (ANOVA) is used when you have a categorical independent variable (with two or more categories) and a normally distributed interval dependent variable and you wish to test for differences in the means of the dependent variable broken down by the levels of the independent variable. For example, using the hsb2 data file, say we wish to test whether the mean of write differs between the three program types (prog). The command for this test would be:

summary(aov(write ~ prog))
##              Df Sum Sq Mean Sq F value   Pr(>F)    
## prog          2   3176  1587.8   21.27 4.31e-09 ***
## Residuals   197  14703    74.6                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

The mean of the dependent variable differs significantly among the levels of program type. However, we do not know if the difference is between only two of the levels or all three of the levels. (The F test for the Model is the same as the F test for prog because prog was the only variable entered into the model. If other variables had also been entered, the F test for the Model would have been different from prog.) To see the mean of write for each level of program type, you can use the tabulate command with the summarize option, as illustrated below.

Kruskal Wallis test

The Kruskal Wallis test is used when you have one independent variable with two or more levels and an ordinal dependent variable. In other words, it is the non-parametric version of ANOVA and a generalized form of the Mann-Whitney test method since it permits 2 or more groups. We will use the same data file as the one way ANOVA example above (the hsb2 data file) and the same variables as in the example above, but we will not assume that write is a normally distributed interval variable.

kruskal.test(write, prog)
##
## 	Kruskal-Wallis rank sum test
##
## data:  write and prog
## Kruskal-Wallis chi-squared = 34.045, df = 2, p-value = 4.047e-08

If some of the scores receive tied ranks, then a correction factor is used, yielding a slightly different value of chi-squared. With or without ties, the results indicate that there is a statistically significant difference among the three type of programs.

Paired t-test

A paired (samples) t-test is used when you have two related observations (i.e. two observations per subject) and you want to see if the means on these two normally distributed interval variables differ from one another. For example, using the hsb2 data file we will test whether the mean of read is equal to the mean of write.

t.test(write, read, paired = TRUE)
##
## 	Paired t-test
##
## data:  write and read
## t = 0.86731, df = 199, p-value = 0.3868
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.6941424  1.7841424
## sample estimates:
## mean of the differences
##                   0.545

These results indicate that the mean of read is not statistically significantly different from the mean of write (t = -0.8673, p = 0.3868).

Wilcoxon signed rank sum test

The Wilcoxon signed rank sum test is the non-parametric version of a paired samples t-test. You use the Wilcoxon signed rank sum test when you do not wish to assume that the difference between the two variables is interval and normally distributed (but you do assume the difference is ordinal). We will use the same example as above, but we will not assume that the difference between read and write is interval and normally distributed.

wilcox.test(write, read, paired = TRUE)
##
## 	Wilcoxon signed rank test with continuity correction
##
## data:  write and read
## V = 9261, p-value = 0.3666
## alternative hypothesis: true location shift is not equal to 0

The results suggest that there is not a statistically significant difference between read and write.

McNemar test

You would perform McNemar’s test if you were interested in the marginal frequencies of two binary outcomes. These binary outcomes may be the same outcome variable on matched pairs (like a case-control study) or two outcome variables from a single group. For example, let us consider two questions, Q1 and Q2, from a test taken by 200 students. Suppose 172 students answered both questions correctly, 15 students answered both questions incorrectly, 7 answered Q1 correctly and Q2 incorrectly, and 6 answered Q2 correctly and Q1 incorrectly. These counts can be considered in a two-way contingency table. The null hypothesis is that the two questions are answered correctly or incorrectly at the same rate (or that the contingency table is symmetric). We can enter these counts into Stata using mcci, a command from Stata’s epidemiology tables. The outcome is labeled according to case-control study conventions.

X <- matrix(c(172, 7, 6, 15), 2, 2)
mcnemar.test(X)
##
## 	McNemar's Chi-squared test with continuity correction
##
## data:  X
## McNemar's chi-squared = 0, df = 1, p-value = 1

McNemar’s chi-square statistic suggests that there is not a statistically significant difference in the proportions of correct/incorrect answers to these two questions.

One-way repeated measures ANOVA

You would perform a one-way repeated measures analysis of variance if you had one categorical independent variable and a normally distributed interval dependent variable that was repeated at least twice for each subject. This is the equivalent of the paired samples t-test, but allows for two or more levels of the categorical variable. This tests whether the mean of the dependent variable differs by the categorical variable. We have an example data set called rb4, which is used in Kirk’s book Experimental Design. In this data set, y is the dependent variable, a is the repeated measure and s is the variable that indicates the subject number.

kirk <- within(read.dta("http://www.ats.ucla.edu/stat/stata/examples/kirk/rb4.dta"),
               {
                 s <- as.factor(s)
                 a <- as.factor(a)
               })
model <- lm(y ~ a + s, data = kirk)
analysis <- Anova(model, idata = kirk, idesign = ~s)
print(analysis)
## Anova Table (Type II tests)
##
## Response: y
##           Sum Sq Df F value    Pr(>F)    
## a           49.0  3 11.6271 0.0001056 ***
## s           31.5  7  3.2034 0.0180188 *  
## Residuals   29.5 21                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

You will notice that this output gives four different p-values. The “regular” (0.0001) is the p-value that you would get if you assumed compound symmetry in the variance-covariance matrix. Because that assumption is often not valid, the three other p-values offer various corrections (the Huynh-Feldt, H-F, Greenhouse-Geisser, G-G and Box’s conservative, Box). No matter which p-value you use, our results indicate that we have a statistically significant effect of a at the .05 level.

Repeated measures logistic regression

If you have a binary outcome measured repeatedly for each subject and you wish to run a logistic regression that accounts for the effect of these multiple measures from each subjects, you can perform a repeated measures logistic regression. In Stata, this can be done using the xtgee command and indicating binomial as the probability distribution and logit as the link function to be used in the model. The exercise data file contains 3 pulse measurements of 30 people assigned to 2 different diet regiments and 3 different exercise regiments. If we define a “high” pulse as being over 100, we can then predict the probability of a high pulse using diet regiment.

exercise <- within(read.dta("http://www.ats.ucla.edu/stat/stata/whatstat/exercise.dta"),
                   {
                     id <- as.factor(id)
                     diet <- as.factor(diet)
                   })
glmer(highpulse ~ diet + (1 | id), data = exercise, family = binomial)
## Generalized linear mixed model fit by maximum likelihood (Laplace
##   Approximation) [glmerMod]
##  Family: binomial  ( logit )
## Formula: highpulse ~ diet + (1 | id)
##    Data: exercise
##      AIC      BIC   logLik deviance df.resid
## 105.4679 112.9674 -49.7340  99.4679       87
## Random effects:
##  Groups Name        Std.Dev.
##  id     (Intercept) 1.821   
## Number of obs: 90, groups:  id, 30
## Fixed Effects:
## (Intercept)        diet2  
##      -2.004        1.145

These results indicate that diet is not statistically significant (Z = 1.24, p = 0.216).

Factorial ANOVA

A factorial ANOVA has two or more categorical independent variables (either with or without the interactions) and a single normally distributed interval dependent variable. For example, using the hsb2 data file we will look at writing scores (write) as the dependent variable and gender (female) and socio-economic status (ses) as independent variables, and we will include an interaction of female by ses. Note that in Stata, you do not need to have the interaction term(s) in your data set. Rather, you can have Stata create it/them temporarily by placing an asterisk between the variables that will make up the interaction term(s).

anova(lm(write ~ female * ses, data = hsb2))
## Analysis of Variance Table
##
## Response: write
##             Df  Sum Sq Mean Sq F value    Pr(>F)    
## female       1  1176.2 1176.21 14.7212 0.0001680 ***
## ses          1  1042.3 1042.32 13.0454 0.0003862 ***
## female:ses   1     0.0    0.04  0.0005 0.9827570    
## Residuals  196 15660.3   79.90                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

These results indicate that the overall model is statistically significant (F = 5.67, p = 0.001). The variables female and ses are also statistically significant (F = 16.59, p = 0.0001 and F = 6.61, p = 0.0017, respectively). However, that interaction between female and ses is not statistically significant (F = 0.13, p = 0.8753).

Friedman test

You perform a Friedman test when you have one within-subjects independent variable with two or more levels and a dependent variable that is not interval and normally distributed (but at least ordinal). We will use this test to determine if there is a difference in the reading, writing and math scores. The null hypothesis in this test is that the distribution of the ranks of each type of score (i.e., reading, writing and math) are the same. Your data will need to be transposed such that subjects are the columns and the variables are the rows. We will use the xpose command to arrange our data this way.

friedman.test(cbind(read, write, math))
##
## 	Friedman rank sum test
##
## data:  cbind(read, write, math)
## Friedman chi-squared = 0.64491, df = 2, p-value = 0.7244

Friedman’s chi-square has a value of 0.6175 and a p-value of 0.7344 and is not statistically significant. Hence, there is no evidence that the distributions of the three types of scores are different.

Factorial logistic regression

A factorial logistic regression is used when you have two or more categorical independent variables but a dichotomous dependent variable. For example, using the hsb2 data file we will use female as our dependent variable, because it is the only dichotomous (0/1) variable in our data set; certainly not because it common practice to use gender as an outcome variable.We will use type of program (prog) and school type (schtyp) as our predictor variables. Because prog is a categorical variable (it has three levels), we need to create dummy codes for it. The use of i.prog does this. You can use the logit command if you want to see the regression coefficients or the logistic command if you want to see the odds ratios.

summary(glm(female ~ prog * schtyp, data = hsb2, family = binomial))
##
## Call:
## glm(formula = female ~ prog * schtyp, family = binomial, data = hsb2)
##
## Deviance Residuals:
##    Min      1Q  Median      3Q     Max  
## -1.893  -1.249   1.064   1.107   1.199  
##
## Coefficients:
##               Estimate Std. Error z value Pr(>|z|)
## (Intercept)   -0.05129    0.32036  -0.160    0.873
## prog2          0.32459    0.39108   0.830    0.407
## prog3          0.21835    0.43191   0.506    0.613
## schtyp2        1.66073    1.14131   1.455    0.146
## prog2:schtyp2 -1.93402    1.23271  -1.569    0.117
## prog3:schtyp2 -1.82779    1.84025  -0.993    0.321
##
## (Dispersion parameter for binomial family taken to be 1)
##
##     Null deviance: 275.64  on 199  degrees of freedom
## Residual deviance: 272.49  on 194  degrees of freedom
## AIC: 284.49
##
## Number of Fisher Scoring iterations: 3

The results indicate that the overall model is not statistically significant (LR chi2 = 3.15, p = 0.6774). Furthermore, none of the coefficients are statistically significant either. We can use the test command to get the test of the overall effect of prog as shown below. This shows that the overall effect of prog is not statistically significant.

Correlation

A correlation is useful when you want to see the linear relationship between two (or more) normally distributed interval variables. For example, using the hsb2 data file we can run a correlation between two continuous variables, read and write.

cor(read, write)
## [1] 0.5967765
cor.test(read, write)
##
## 	Pearson's product-moment correlation
##
## data:  read and write
## t = 10.465, df = 198, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.4993831 0.6792753
## sample estimates:
##       cor
## 0.5967765

In the first example above, we see that the correlation between read and write is 0.5968. By squaring the correlation and then multiplying by 100, you can determine what percentage of the variability is shared. Let’s round 0.5968 to be 0.6, which when squared would be .36, multiplied by 100 would be 36%. Hence read shares about 36% of its variability with write. In the output for the second example, we can see the correlation between write and female is 0.2565. Squaring this number yields .06579225, meaning that female shares approximately 6.5% of its variability with write.

Simple linear regression

Simple linear regression allows us to look at the linear relationship between one normally distributed interval predictor and one normally distributed interval outcome variable. For example, using the hsb2 data file, say we wish to look at the relationship between writing scores (write) and reading scores (read); in other words, predicting write from read.

lm(write ~ read)
##
## Call:
## lm(formula = write ~ read)
##
## Coefficients:
## (Intercept)         read  
##     23.9594       0.5517

We see that the relationship between write and read is positive (.5517051) and based on the t-value (10.47) and p-value (0.000), we would conclude this relationship is statistically significant. Hence, we would say there is a statistically significant positive linear relationship between reading and writing.

Non-parametric correlation

A Spearman correlation is used when one or both of the variables are not assumed to be normally distributed and interval (but are assumed to be ordinal). The values of the variables are converted in ranks and then correlated. In our example, we will look for a relationship between read and write. We will not assume that both of these variables are normal and interval .

cor.test(write, read, method = "spearman")
## Warning in cor.test.default(write, read, method = "spearman"): Cannot
## compute exact p-value with ties
##
## 	Spearman's rank correlation rho
##
## data:  write and read
## S = 510990, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho
## 0.6167455

The results suggest that the relationship between read and write (rho = 0.6167, p = 0.000) is statistically significant.

Simple logistic regression

Logistic regression assumes that the outcome variable is binary (i.e., coded as 0 and 1). We have only one variable in the hsb2 data file that is coded 0 and 1, and that is female. We understand that female is a silly outcome variable (it would make more sense to use it as a predictor variable), but we can use female as the outcome variable to illustrate how the code for this command is structured and how to interpret the output. The first variable listed after the logistic (or logit) command is the outcome (or dependent) variable, and all of the rest of the variables are predictor (or independent) variables. You can use the logit command if you want to see the regression coefficients or the logistic command if you want to see the odds ratios. In our example, female will be the outcome variable, and read will be the predictor variable. As with OLS regression, the predictor variables must be either dichotomous or continuous; they cannot be categorical.

glm(female ~ read, family = binomial)
##
## Call:  glm(formula = female ~ read, family = binomial)
##
## Coefficients:
## (Intercept)         read  
##     0.72609     -0.01044  
##
## Degrees of Freedom: 199 Total (i.e. Null);  198 Residual
## Null Deviance:	    275.6
## Residual Deviance: 275.1 	AIC: 279.1

The results indicate that reading score (read) is not a statistically significant predictor of gender (i.e., being female), z = -0.75, p = 0.453. Likewise, the test of the overall model is not statistically significant, LR chi-squared 0.56, p = 0.4527.

Multiple regression

Multiple regression is very similar to simple regression, except that in multiple regression you have more than one predictor variable in the equation. For example, using the hsb2 data file we will predict writing score from gender (female), reading, math, science and social studies (socst) scores.

lm(write ~ female + read + math + science + socst)
##
## Call:
## lm(formula = write ~ female + read + math + science + socst)
##
## Coefficients:
## (Intercept)       female         read         math      science  
##      6.1388       5.4925       0.1254       0.2381       0.2419  
##       socst  
##      0.2293

The results indicate that the overall model is statistically significant (F = 58.60, p = 0.0000). Furthermore, all of the predictor variables are statistically significant except for read.

Analysis of covariance

Analysis of covariance is like ANOVA, except in addition to the categorical predictors you also have continuous predictors as well. For example, the one way ANOVA example used write as the dependent variable and prog as the independent variable. Let’s add read as a continuous variable to this model, as shown below.

summary(aov(write ~ prog + read))
##              Df Sum Sq Mean Sq F value   Pr(>F)    
## prog          2   3176    1588   28.65 1.21e-11 ***
## read          1   3842    3842   69.33 1.41e-14 ***
## Residuals   196  10861      55                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

The results indicate that even after adjusting for reading score (read), writing scores still significantly differ by program type (prog) F = 5.87, p = 0.0034.

Multiple logistic regression

Multiple logistic regression is like simple logistic regression, except that there are two or more predictors. The predictors can be interval variables or dummy variables, but cannot be categorical variables. If you have categorical predictors, they should be coded into one or more dummy variables. We have only one variable in our data set that is coded 0 and 1, and that is female. We understand that female is a silly outcome variable (it would make more sense to use it as a predictor variable), but we can use female as the outcome variable to illustrate how the code for this command is structured and how to interpret the output. The first variable listed after the logistic (or logit) command is the outcome (or dependent) variable, and all of the rest of the variables are predictor (or independent) variables. You can use the logit command if you want to see the regression coefficients or the logistic command if you want to see the odds ratios. In our example, female will be the outcome variable, and read and write will be the predictor variables.

glm(female ~ read + write, family = binomial)
##
## Call:  glm(formula = female ~ read + write, family = binomial)
##
## Coefficients:
## (Intercept)         read        write  
##    -1.70614     -0.07101      0.10637  
##
## Degrees of Freedom: 199 Total (i.e. Null);  197 Residual
## Null Deviance:	    275.6
## Residual Deviance: 247.8 	AIC: 253.8

These results show that both read and write are significant predictors of female.

One-way MANOVA

MANOVA (multivariate analysis of variance) is like ANOVA, except that there are two or more dependent variables. In a one-way MANOVA, there is one categorical independent variable and two or more dependent variables. For example, using the hsb2 data file, say we wish to examine the differences in read, write and math broken down by program type (prog). For this analysis, you can use the manova command and then perform the analysis like this.

summary(manova(cbind(read, write, math) ~ prog))
##            Df  Pillai approx F num Df den Df    Pr(>F)    
## prog        2 0.26721   10.075      6    392 2.304e-10 ***
## Residuals 197                                             
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

This command produces three different test statistics that are used to evaluate the statistical significance of the relationship between the independent variable and the outcome variables. According to all three criteria, the students in the different programs differ in their joint distribution of read, write and math.

Multivariate multiple regression

Multivariate multiple regression is used when you have two or more dependent variables that are to be predicted from two or more predictor variables. In our example, we will predict write and read from female, math, science and social studies (socst) scores.

M1 <- lm(cbind(write, read) ~ female + math + science + socst, data = hsb2)

Many researchers familiar with traditional multivariate analysis may not recognize the tests above. They do not see Wilks’ Lambda, Pillai’s Trace or the Hotelling-Lawley Trace statistics, the statistics with which they are familiar. It is possible to obtain these statistics using the mvtest command written by David E. Moore of the University of Cincinnati. UCLA updated this command to work with Stata 6 and above. You can download mvtest from within Stata by typing findit mvtest (see How can I used the findit command to search for programs and get additional help? for more information about using findit).

summary(Anova(M1))
##
## Type II MANOVA Tests:
##
## Sum of squares and products for error:
##          write     read
## write 7258.783 1091.057
## read  1091.057 8699.762
##
## ------------------------------------------
##  
## Term: female
##
## Sum of squares and products for the hypothesis:
##           write       read
## write 1413.5284 -133.48461
## read  -133.4846   12.60544
##
## Multivariate Tests: female
##                  Df test stat approx F num Df den Df     Pr(>F)    
## Pillai            1 0.1698853 19.85132      2    194 1.4335e-08 ***
## Wilks             1 0.8301147 19.85132      2    194 1.4335e-08 ***
## Hotelling-Lawley  1 0.2046528 19.85132      2    194 1.4335e-08 ***
## Roy               1 0.2046528 19.85132      2    194 1.4335e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## ------------------------------------------
##  
## Term: math
##
## Sum of squares and products for the hypothesis:
##          write      read
## write 714.8665  856.2825
## read  856.2825 1025.6735
##
## Multivariate Tests: math
##                  Df test stat approx F num Df den Df     Pr(>F)    
## Pillai            1 0.1599321 18.46685      2    194 4.5551e-08 ***
## Wilks             1 0.8400679 18.46685      2    194 4.5551e-08 ***
## Hotelling-Lawley  1 0.1903800 18.46685      2    194 4.5551e-08 ***
## Roy               1 0.1903800 18.46685      2    194 4.5551e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## ------------------------------------------
##  
## Term: science
##
## Sum of squares and products for the hypothesis:
##          write     read
## write 857.8824 901.3191
## read  901.3191 946.9551
##
## Multivariate Tests: science
##                  Df test stat approx F num Df den Df     Pr(>F)    
## Pillai            1 0.1664254 19.36631      2    194 2.1459e-08 ***
## Wilks             1 0.8335746 19.36631      2    194 2.1459e-08 ***
## Hotelling-Lawley  1 0.1996526 19.36631      2    194 2.1459e-08 ***
## Roy               1 0.1996526 19.36631      2    194 2.1459e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## ------------------------------------------
##  
## Term: socst
##
## Sum of squares and products for the hypothesis:
##          write     read
## write 1105.653 1277.393
## read  1277.393 1475.810
##
## Multivariate Tests: socst
##                  Df test stat approx F num Df den Df     Pr(>F)    
## Pillai            1 0.2206710 27.46604      2    194 3.1399e-11 ***
## Wilks             1 0.7793290 27.46604      2    194 3.1399e-11 ***
## Hotelling-Lawley  1 0.2831551 27.46604      2    194 3.1399e-11 ***
## Roy               1 0.2831551 27.46604      2    194 3.1399e-11 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

These results show that female has a significant relationship with the joint distribution of write and read. The mvtest command could then be repeated for each of the other predictor variables.

Canonical correlation

Canonical correlation is a multivariate technique used to examine the relationship between two groups of variables. For each set of variables, it creates latent variables and looks at the relationships among the latent variables. It assumes that all variables in the model are interval and normally distributed. Stata requires that each of the two groups of variables be enclosed in parentheses. There need not be an equal number of variables in the two groups.

cc(cbind(read, write), cbind(math, science))
## $cor
## [1] 0.7728409 0.0234784
##
## $names
## $names$Xnames
## [1] "read"  "write"
##
## $names$Ynames
## [1] "math"    "science"
##
## $names$ind.names
## NULL
##
##
## $xcoef
##              [,1]       [,2]
## read  -0.06326131 -0.1037908
## write -0.04924918  0.1219084
##
## $ycoef
##                [,1]       [,2]
## math    -0.06698268  0.1201425
## science -0.04824063 -0.1208860
##
## $scores
## $scores$xscores
##               [,1]         [,2]
##   [1,] -0.26358835 -0.589561062
##   [2,] -1.30420707 -0.877901269
##   [3,]  1.49454321 -1.556539586
##   [4,] -0.24916276 -2.187572699
##   [5,]  0.36902478  0.448346869
##   [6,]  0.55880872  0.759719249
##   [7,] -0.16550344  0.990333008
##   [8,]  1.48691695  1.066177022
##   [9,] -0.88940214 -0.602764022
##  [10,] -0.41133590 -0.223835983
##  [11,] -0.15787718 -1.632383600
##  [12,] -0.90382773  0.995247615
##  [13,] -1.66976282 -1.274946875
##  [14,] -0.61554542  1.062803275
##  [15,]  0.24930149  1.265470254
##  [16,]  0.83307890  0.601575756
##  [17,]  0.36902478  0.448346869
##  [18,] -0.50983426  0.019980737
##  [19,] -1.59970217 -0.146451110
##  [20,]  0.50317366 -1.966788153
##  [21,] -0.49540867 -1.578030900
##  [22,] -1.18489724  0.128686136
##  [23,]  0.77023105 -1.325925827
##  [24,] -0.45337228 -0.900933442
##  [25,]  1.39563138  0.510987923
##  [26,]  1.93015961 -0.030998216
##  [27,] -1.40991823  0.164921269
##  [28,]  0.12277887  1.057888668
##  [29,]  1.24829729 -0.946997788
##  [30,]  0.44671169 -1.045873974
##  [31,]  1.71956420 -1.592774720
##  [32,] -1.46555329 -2.561586132
##  [33,] -1.50841660  0.408737989
##  [34,]  1.22707237 -0.373691122
##  [35,] -0.29202606  0.782751422
##  [36,] -1.09361167  0.683875235
##  [37,] -1.05796116 -1.487443067
##  [38,] -1.26217068 -0.200803810
##  [39,]  1.40325764 -2.111728685
##  [40,]  1.90934814 -1.281402340
##  [41,]  0.61527070 -0.161194929
##  [42,] -0.48181000  0.471379042
##  [43,] -0.04578015  0.173209623
##  [44,]  1.22707237 -0.373691122
##  [45,] -1.40991823  0.164921269
##  [46,] -0.48181000  0.471379042
##  [47,]  0.77023105 -1.325925827
##  [48,] -1.11442313 -0.566528889
##  [49,]  0.02428050  1.301705388
##  [50,] -0.36208671 -0.345744343
##  [51,] -0.45378574  0.922777348
##  [52,]  1.81084977 -1.037585621
##  [53,]  0.95280219 -0.215547629
##  [54,] -0.98790051 -0.358947303
##  [55,] -1.76826119 -1.031130155
##  [56,]  1.51535467 -0.306135462
##  [57,]  1.74037567 -0.342370595
##  [58,]  1.32557073 -0.617507842
##  [59,] -0.88940214 -0.602764022
##  [60,]  0.45351102 -0.021169003
##  [61,]  0.47473595 -0.594475669
##  [62,] -0.12346705  1.667430467
##  [63,]  0.95280219 -0.215547629
##  [64,]  2.12715634 -0.518631655
##  [65,]  0.67173268 -1.082109108
##  [66,]  1.10054974 -0.581272708
##  [67,] -0.55187065 -0.657116722
##  [68,]  1.00926417 -1.136461807
##  [69,] -0.19991357 -2.309481059
##  [70,]  1.11497533 -2.179284345
##  [71,]  0.95280219 -0.215547629
##  [72,] -0.55187065 -0.657116722
##  [73,] -2.01450711 -0.421588356
##  [74,] -1.30420707 -0.877901269
##  [75,]  0.20767856 -1.235337994
##  [76,]  0.96001499 -1.014553448
##  [77,] -0.58030837  0.715195762
##  [78,] -1.30420707 -0.877901269
##  [79,]  2.16919273  0.158465804
##  [80,]  0.91076580 -0.892645088
##  [81,] -0.98790051 -0.358947303
##  [82,]  1.21264678  1.224320515
##  [83,] -1.30420707 -0.877901269
##  [84,] -1.28339561  0.372502856
##  [85,]  0.40467530 -1.722971433
##  [86,] -0.62955755  0.837104122
##  [87,]  0.59445924 -1.411599054
##  [88,]  1.33916940  1.431902101
##  [89,]  1.21347370 -2.423101065
##  [90,]  0.01068183 -0.747704555
##  [91,] -0.43977362  1.148476501
##  [92,] -0.49540867 -1.578030900
##  [93,] -1.45195462 -0.512176189
##  [94,]  1.26910876  0.303406337
##  [95,]  0.95280219 -0.215547629
##  [96,] -0.31325099  1.356058087
##  [97,] -1.78948611 -0.457823489
##  [98,] -1.28339561  0.372502856
##  [99,]  1.58541532  0.822360302
## [100,] -1.18489724  0.128686136
## [101,] -1.35345626 -0.755992909
## [102,]  0.02428050  1.301705388
## [103,]  0.66451988 -0.283103289
## [104,] -0.64315622 -1.212305821
## [105,] -0.29202606  0.782751422
## [106,] -0.23556409 -0.138162756
## [107,] -0.94586412  0.318150156
## [108,]  1.96539666 -0.378605729
## [109,]  0.27052642  0.692163589
## [110,] -1.78948611 -0.457823489
## [111,] -0.26358835 -0.589561062
## [112,]  0.65730709  0.515902529
## [113,] -1.11442313 -0.566528889
## [114,] -1.59970217 -0.146451110
## [115,] -1.71901201 -1.153038515
## [116,]  1.45889269  0.614778716
## [117,]  0.52357167  1.107326761
## [118,] -2.01450711 -0.421588356
## [119,] -0.19352770  0.538934702
## [120,]  0.99483858  0.461549830
## [121,] -0.55187065 -0.657116722
## [122,]  0.17924085  0.136974490
## [123,]  0.17924085  0.136974490
## [124,]  0.66451988 -0.283103289
## [125,] -0.12346705  1.667430467
## [126,] -0.38331164  0.227562323
## [127,]  0.72098186 -1.204017467
## [128,]  0.82586610  1.400581574
## [129,]  0.32698840 -0.228750589
## [130,]  2.02865797 -0.274814935
## [131,] -0.60833263  0.263797456
## [132,] -0.90382773  0.995247615
## [133,] -1.45195462 -0.512176189
## [134,]  0.58683298  1.211117555
## [135,] -0.86137788 -0.151365716
## [136,] -2.00729431 -1.220594175
## [137,]  0.02428050  1.301705388
## [138,]  0.43228610  0.552137663
## [139,]  1.41685631 -0.062318743
## [140,]  0.20046577 -0.436332176
## [141,]  1.86648483  1.688921781
## [142,]  0.58683298  1.211117555
## [143,]  0.86151662 -0.770736728
## [144,]  0.12277887  1.057888668
## [145,] -0.29202606  0.782751422
## [146,]  0.36902478  0.448346869
## [147,] -0.31325099  1.356058087
## [148,]  0.55880872  0.759719249
## [149,]  0.91076580 -0.892645088
## [150,]  0.34779986  1.021653535
## [151,]  1.10776254 -1.380278527
## [152,] -0.86817722 -1.176070688
## [153,]  0.37582412  1.473051841
## [154,]  0.27052642  0.692163589
## [155,] -0.75608018  0.629522535
## [156,] -1.30420707 -0.877901269
## [157,] -0.09502933  0.295117983
## [158,]  0.43908543  1.576842634
## [159,]  1.32557073 -0.617507842
## [160,] -1.57167791  0.304947196
## [161,] -0.12346705  1.667430467
## [162,] -0.16508998 -0.833377782
## [163,] -0.07421787  1.545522107
## [164,] -0.75608018  0.629522535
## [165,] -0.29202606  0.782751422
## [166,]  0.95280219 -0.215547629
## [167,] -0.16550344  0.990333008
## [168,]  0.77661692  1.522489934
## [169,] -0.75608018  0.629522535
## [170,] -0.65758181  0.385705816
## [171,]  0.43908543  1.576842634
## [172,]  0.66451988 -0.283103289
## [173,]  1.47331828 -0.983232921
## [174,] -0.79811657 -0.047574923
## [175,]  0.70655627  0.393994170
## [176,] -1.03714969 -0.237038943
## [177,] -1.50841660  0.408737989
## [178,]  0.77661692  1.522489934
## [179,]  0.17924085  0.136974490
## [180,] -0.58752117  1.514201580
## [181,] -0.94586412  0.318150156
## [182,]  0.70655627  0.393994170
## [183,] -0.68601953  1.758018300
## [184,] -0.77730510  1.202829201
## [185,] -0.55949691  1.965599886
## [186,] -1.40991823  0.164921269
## [187,] -0.04578015  0.173209623
## [188,]  0.76301825 -0.526920009
## [189,] -1.13564806  0.006777776
## [190,]  0.47473595 -0.594475669
## [191,]  0.58683298  1.211117555
## [192,]  0.81865331  2.199587393
## [193,]  0.17924085  0.136974490
## [194,]  0.40384838  1.924450147
## [195,] -0.27121460  2.033155546
## [196,] -0.48181000  0.471379042
## [197,]  0.98082645  0.235850677
## [198,]  0.27815267 -1.930553019
## [199,] -0.62955755  0.837104122
## [200,] -1.28339561  0.372502856
##
## $scores$yscores
##                [,1]        [,2]
##   [1,]  1.013980334 -0.81276184
##   [2,] -0.561661891 -1.30522812
##   [3,] -0.387441410 -0.58065576
##   [4,]  0.322640484 -0.81722302
##   [5,] -0.347186284  0.38420150
##   [6,] -0.427696537 -1.54551302
##   [7,]  0.657553868 -1.41793527
##   [8,]  1.131974678  0.63489582
##   [9,] -0.387441410 -0.58065576
##  [10,]  0.132448995  0.14614718
##  [11,]  0.054709777 -0.33665321
##  [12,] -0.427696537 -1.54551302
##  [13,] -1.670868810  1.09910797
##  [14,] -0.443667546  0.14242953
##  [15,]  1.182986345  2.20269592
##  [16,]  0.735293086 -0.93513488
##  [17,]  0.199431671  0.02600473
##  [18,] -0.789337471  0.14019895
##  [19,] -0.778580931  0.74314179
##  [20,] -0.347186284  0.38420150
##  [21,]  0.499304397 -3.83045019
##  [22,] -2.469446463  0.24993198
##  [23,]  0.360124575 -1.29927988
##  [24,] -0.733111335 -0.58288635
##  [25,]  1.131974678  0.63489582
##  [26,]  1.064992001  0.75503827
##  [27,] -1.335955426  0.49839571
##  [28,] -0.588389441 -0.22022841
##  [29,]  0.864043971  1.11546562
##  [30,]  0.092193868 -0.81871008
##  [31,] -0.057742495  1.10951738
##  [32,] -1.346711967 -0.10454714
##  [33,] -1.376210553 -0.46646155
##  [34,] -1.263758281 -1.91263214
##  [35,] -0.264232597 -1.42388351
##  [36,] -0.800094012 -0.46274390
##  [37,] -2.180002675  0.97524787
##  [38,] -1.711123937  0.13425071
##  [39,]  1.343679249  0.87741131
##  [40,]  1.466888062  0.03418356
##  [41,]  1.255183491 -0.20833193
##  [42,] -0.923302825  0.38048385
##  [43,] -0.443667546  0.14242953
##  [44,]  0.735293086 -0.93513488
##  [45,] -0.226748507 -1.90594038
##  [46,] -1.520932447 -0.82911949
##  [47,]  1.051464425 -1.29481870
##  [48,] -1.700367396  0.73719355
##  [49,] -0.749082344  1.10505620
##  [50,] -0.191707849  1.34980229
##  [51,] -0.808079517  0.38122738
##  [52,]  1.214928364 -1.17318919
##  [53,] -0.470395097  1.22742925
##  [54,]  0.092193868 -0.81871008
##  [55,] -2.190759215  0.37230502
##  [56,]  1.826085563  2.08627112
##  [57,]  1.622366497  0.99978435
##  [58,]  0.713780005 -2.14102057
##  [59,] -0.454424087 -0.46051331
##  [60,]  0.421892783  0.87146307
##  [61,]  0.215402681 -1.66193782
##  [62,] -1.386967094 -1.06940440
##  [63,]  1.775073896  0.51847102
##  [64,]  1.544627280  0.51698396
##  [65,]  0.941783188  1.59826602
##  [66,]  0.936241116 -1.29556223
##  [67,] -0.644615577  0.50285689
##  [68,]  0.853287430  0.51252278
##  [69,] -1.060039214 -0.82614537
##  [70,]  0.622840814  0.51103572
##  [71,]  1.064992001  0.75503827
##  [72,] -0.655372118 -0.10008596
##  [73,] -1.767350073  0.85733600
##  [74,] -1.427222220 -2.03426166
##  [75,]  0.148420004 -1.54179537
##  [76,]  0.976496243 -0.33070497
##  [77,]  0.046724273  0.50731807
##  [78,] -0.762609921 -0.94480077
##  [79,]  1.064992001  0.75503827
##  [80,]  0.384408693  1.35351994
##  [81,] -0.443667546  0.14242953
##  [82,] -0.532163305 -0.94331371
##  [83,] -1.912071967  0.49467806
##  [84,] -0.226748507 -1.90594038
##  [85,]  1.225684905 -0.57024634
##  [86,] -1.298471336  0.01633884
##  [87,]  0.054709777 -0.33665321
##  [88,]  1.389148845 -0.44861683
##  [89,]  1.708091219  0.63861347
##  [90,] -1.001042042 -0.10231655
##  [91,] -0.660586586  2.19079945
##  [92,] -0.438453078 -2.14845587
##  [93,] -1.654897801 -0.58883459
##  [94,]  0.421892783  0.87146307
##  [95,]  0.679066950 -0.21204958
##  [96,] -1.097523305 -0.34408851
##  [97,] -1.979054644  0.61482051
##  [98,] -2.056793862  0.13202012
##  [99,]  1.466888062  0.03418356
## [100,] -1.536903457  0.85882306
## [101,] -1.587915124 -0.70897704
## [102,] -0.907331815 -1.30745871
## [103,]  1.153487759  1.84078151
## [104,] -0.001516359  0.38643209
## [105,] -0.465180628 -1.06345616
## [106,] -0.419383429  2.79522935
## [107,] -0.872291157  1.94828395
## [108,]  0.888000485 -1.41644821
## [109,]  0.534345056 -0.57470752
## [110,] -1.392181562  1.22148101
## [111,]  0.405594171 -2.62530802
## [112,]  1.399905385  0.15432601
## [113,] -0.009501864  1.23040337
## [114,] -0.703612749 -0.22097194
## [115,] -0.443667546  0.14242953
## [116,]  1.523114198 -0.68890174
## [117,] -0.309702193 -0.09785537
## [118,] -0.923302825  0.38048385
## [119,] -1.057268178  0.62076875
## [120,]  1.466888062  0.03418356
## [121,]  0.266414348 -0.09413772
## [122,]  0.534345056 -0.57470752
## [123,]  0.596113264  1.59603543
## [124,]  0.228930258  0.38791915
## [125,]  1.373177835  1.23932572
## [126,] -0.521406764 -0.34037086
## [127,]  0.890771521  0.03046591
## [128,] -0.001516359  0.38643209
## [129,]  0.009240182  0.98937493
## [130,]  1.882311700  1.36318582
## [131,] -0.001516359  0.38643209
## [132,] -1.400167067  2.06545229
## [133,] -0.135481713  0.62671699
## [134,]  0.612084273 -0.09190713
## [135,]  0.622840814  0.51103572
## [136,] -1.223503154 -0.94777488
## [137,] -0.387441410 -0.58065576
## [138,]  0.220944753  1.23189042
## [139,]  1.791044905 -1.16947154
## [140,]  0.622840814  0.51103572
## [141,]  1.024736875 -0.20981899
## [142,]  0.266414348 -0.09413772
## [143,]  0.663095940  1.47589298
## [144,]  0.689823490  0.39089327
## [145,] -0.414168960  0.50434395
## [146,]  0.831774349 -0.69336292
## [147,]  0.628055282 -1.77984969
## [148,]  1.024736875 -0.20981899
## [149,]  1.016751370  0.63415229
## [150,]  1.440160512  1.11918327
## [151,]  1.121218137  0.03195297
## [152,] -0.856320148  0.26034140
## [153,]  0.936241116 -1.29556223
## [154,]  0.188675131 -0.57693811
## [155,] -0.521406764 -0.34037086
## [156,] -0.711598254  0.62299934
## [157,]  0.073451823 -0.57768164
## [158,]  0.344153566  0.38866268
## [159,]  1.188200814 -0.08818948
## [160,] -1.402938103  0.61853816
## [161,] -0.079255576 -0.09636831
## [162,]  0.218173717 -0.21502370
## [163,] -0.427696537 -1.54551302
## [164,] -1.737851487  1.21925042
## [165,]  0.159176545 -0.93885253
## [166,]  1.418647431 -0.08670242
## [167,] -0.465180628 -1.06345616
## [168,]  1.147945687 -1.05304674
## [169,] -0.845563607  0.86328424
## [170,]  0.054709777 -0.33665321
## [171,]  0.601327732 -0.69484998
## [172,]  1.147945687 -1.05304674
## [173,]  1.718847760  1.24155631
## [174,] -1.068024719  0.01782590
## [175,]  1.391919881  0.99829729
## [176,] -0.931288329  1.22445513
## [177,] -0.845563607  0.86328424
## [178,] -0.146238253  0.02377414
## [179,]  0.215402681 -1.66193782
## [180,] -0.692856208  0.38197091
## [181,]  0.333397025 -0.21428017
## [182,]  0.931026648  0.99532317
## [183,] -0.829592598 -0.82465831
## [184,] -0.068499036  0.50657454
## [185,] -1.577158583 -0.10603420
## [186,] -1.057268178  0.62076875
## [187,] -0.213220930  0.14391659
## [188,]  1.188200814 -0.08818948
## [189,] -0.376684870  0.02228708
## [190,] -0.079255576 -0.09636831
## [191,]  1.255183491 -0.20833193
## [192,]  0.802275763 -1.05527733
## [193,] -0.175736839 -0.33814027
## [194,]  1.574125866  0.87889837
## [195,] -0.403412420  1.10728679
## [196,]  0.518374046  1.11323503
## [197,]  1.745575310  0.15655660
## [198,] -0.443667546  0.14242953
## [199,] -0.655372118 -0.10008596
## [200,] -0.883047698  1.34534111
##
## $scores$corr.X.xscores
##             [,1]      [,2]
## read  -0.9271970 -0.374574
## write -0.8538903  0.520453
##
## $scores$corr.Y.xscores
##               [,1]         [,2]
## math    -0.7177974  0.008701966
## science -0.6750187 -0.011433002
##
## $scores$corr.X.yscores
##             [,1]         [,2]
## read  -0.7165758 -0.008794398
## write -0.6599214  0.012219404
##
## $scores$corr.Y.yscores
##               [,1]       [,2]
## math    -0.9287778  0.3706371
## science -0.8734252 -0.4869583

The output above shows the linear combinations corresponding to the first canonical correlation. At the bottom of the output are the two canonical correlations. These results indicate that the first canonical correlation is .7728. You will note that Stata is brief and may not provide you with all of the information that you may want. Several programs have been developed to provide more information regarding the analysis. You can download this family of programs by typing findit cancor (see How can I used the findit command to search for programs and get additional help? for more information about using findit). The F-test in this output tests the hypothesis that the first canonical correlation is equal to zero. Clearly, F = 56.4706 is statistically significant. However, the second canonical correlation of .0235 is not statistically significantly different from zero (F = 0.1087, p = 0.7420).