Results

Are Black Americans Happy?

Data from Beckham (1929). The author investigated the happiness of Black Americans.

  1. profession: the respondent's job
  2. response: yes or no
  3. happy: counts of people who think Black Americans are happy (or not)
  4. you_happy: counts of people who are happy as Black Americans (or not)
  5. should_be_happy: counts of people who think Black Americans should be happy (or not)


The Cells tab is used to specify the information displayed in the contingency table. It is important that you ask for expected counts because this is how we check the assumptions about the expected frequencies. It is also useful to have a look at the row, column and total percentages because these values are usually more easily interpreted than the actual frequencies and provide some idea of the origin of any significant effects. We can also select standardized residuals to break down a significant effect (should we get one).

Contingency Tables
response
profession   Yes No Total
College students Count 390.000 1610.000 2000.000
Expected count 683.712 1316.288 2000.000
% within row 19.500 % 80.500 % 100.000 %
% within column 32.773 % 70.275 % 57.455 %
% of total 11.204 % 46.251 % 57.455 %
Standardized residuals -21.227 21.227
Unskilled laborers Count 378.000 122.000 500.000
Expected count 170.928 329.072 500.000
% within row 75.600 % 24.400 % 100.000 %
% within column 31.765 % 5.325 % 14.364 %
% of total 10.859 % 3.505 % 14.364 %
Standardized residuals 21.097 -21.097
Preachers Count 35.000 265.000 300.000
Expected count 102.557 197.443 300.000
% within row 11.667 % 88.333 % 100.000 %
% within column 2.941 % 11.567 % 8.618 %
% of total 1.005 % 7.613 % 8.618 %
Standardized residuals -8.602 8.602
Physicians Count 159.000 51.000 210.000
Expected count 71.790 138.210 210.000
% within row 75.714 % 24.286 % 100.000 %
% within column 13.361 % 2.226 % 6.033 %
% of total 4.568 % 1.465 % 6.033 %
Standardized residuals 13.088 -13.088
Housewives Count 78.000 122.000 200.000
Expected count 68.371 131.629 200.000
% within row 39.000 % 61.000 % 100.000 %
% within column 6.555 % 5.325 % 5.745 %
% of total 2.241 % 3.505 % 5.745 %
Standardized residuals 1.479 -1.479
School teachers Count 108.000 38.000 146.000
Expected count 49.911 96.089 146.000
% within row 73.973 % 26.027 % 100.000 %
% within column 9.076 % 1.659 % 4.194 %
% of total 3.103 % 1.092 % 4.194 %
Standardized residuals 10.355 -10.355
Lawyers Count 11.000 64.000 75.000
Expected count 25.639 49.361 75.000
% within row 14.667 % 85.333 % 100.000 %
% within column 0.924 % 2.794 % 2.155 %
% of total 0.316 % 1.839 % 2.155 %
Standardized residuals -3.603 3.603
Musician Count 31.000 19.000 50.000
Expected count 17.093 32.907 50.000
% within row 62.000 % 38.000 % 100.000 %
% within column 2.605 % 0.829 % 1.436 %
% of total 0.891 % 0.546 % 1.436 %
Standardized residuals 4.177 -4.177
Total Count 1190.000 2291.000 3481.000
Expected count 1190.000 2291.000 3481.000
% within row 34.186 % 65.814 % 100.000 %
% within column 100.000 % 100.000 % 100.000 %
% of total 34.186 % 65.814 % 100.000 %
Chi-Squared Tests
  Value df p
Χ² 936.139 7 < .001
N 3481  
Note.  Continuity correction is available only for 2x2 tables.
Nominal
  Value
Contingency coefficient 0.460
Phi-coefficient NaN
Cramer's V 0.519
Lambda (rows) 0.375
Lambda (columns) 0.000
Lambda (symmetric) 0.187
ᵃ Phi coefficient is only available for 2 by 2 contingency Tables

The chi-square test is highly significant, χ2(7) = 936.14, p < .001. This indicates that the profile of yes and no responses differed across the professions. Looking at the standardized residuals, the only profession for which these are non-significant are housewives who showed a fairly even split of whether they thought Black Americans were happy (40%) or not (60%). Within the other professions all of the standardized residuals are much higher than 1.96, so how can we make sense of the data? What’s interesting is to look at the direction of these residuals (i.e., whether they are positive or negative).


For the following professions the residual for ‘no’ was positive but for ‘yes’ was negative; these are therefore people who responded more than we would expect that Black Americans were not happy and less than expected that Black Americans were happy: college students, preachers and lawyers. In other words, people thought they were unhappier, compared to their Black American peers.


The remaining professions (labourers, physicians, school teachers and musicians) show the opposite pattern: the residual for ‘no’ was negative but for ‘yes’ was positive; these are, therefore, people who responded less than we would expect that Black Americans were not happy and more than expected that Black Americans were happy. In other words, people thought they were unhappier, compared to their Black American peers. It's worth noting that overall, the majority of responses thought that Black Americans would be unhappy.

Are they Happy as Black Americans?

We run this analysis in exactly the same way except that we now have to swap the variable happy to you_happy.

Contingency Tables
response
profession   Yes No Total
College students Count 1822.000 48.000 1870.000
Expected count 1598.968 271.032 1870.000
% within row 97.433 % 2.567 % 100.000 %
% within column 67.432 % 10.480 % 59.177 %
% of total 57.658 % 1.519 % 59.177 %
Standardized residuals 22.930 -22.930
Unskilled laborers Count 305.000 195.000 500.000
Expected count 427.532 72.468 500.000
% within row 61.000 % 39.000 % 100.000 %
% within column 11.288 % 42.576 % 15.823 %
% of total 9.652 % 6.171 % 15.823 %
Standardized residuals -16.966 16.966
Preachers Count 230.000 0.000 230.000
Expected count 196.665 33.335 230.000
% within row 100.000 % 0.000 % 100.000 %
% within column 8.512 % 0.000 % 7.278 %
% of total 7.278 % 0.000 % 7.278 %
Standardized residuals 6.484 -6.484
Physicians Count 203.000 7.000 210.000
Expected count 179.563 30.437 210.000
% within row 96.667 % 3.333 % 100.000 %
% within column 7.513 % 1.528 % 6.646 %
% of total 6.424 % 0.222 % 6.646 %
Standardized residuals 4.755 -4.755
Housewives Count 17.000 146.000 163.000
Expected count 139.375 23.625 163.000
% within row 10.429 % 89.571 % 100.000 %
% within column 0.629 % 31.878 % 5.158 %
% of total 0.538 % 4.620 % 5.158 %
Standardized residuals -27.958 27.958
School teachers Count 79.000 28.000 107.000
Expected count 91.492 15.508 107.000
% within row 73.832 % 26.168 % 100.000 %
% within column 2.924 % 6.114 % 3.386 %
% of total 2.500 % 0.886 % 3.386 %
Standardized residuals -3.490 3.490
Lawyers Count 30.000 0.000 30.000
Expected count 25.652 4.348 30.000
% within row 100.000 % 0.000 % 100.000 %
% within column 1.110 % 0.000 % 0.949 %
% of total 0.949 % 0.000 % 0.949 %
Standardized residuals 2.266 -2.266
Musician Count 16.000 34.000 50.000
Expected count 42.753 7.247 50.000
% within row 32.000 % 68.000 % 100.000 %
% within column 0.592 % 7.424 % 1.582 %
% of total 0.506 % 1.076 % 1.582 %
Standardized residuals -10.833 10.833
Total Count 2702.000 458.000 3160.000
Expected count 2702.000 458.000 3160.000
% within row 85.506 % 14.494 % 100.000 %
% within column 100.000 % 100.000 % 100.000 %
% of total 85.506 % 14.494 % 100.000 %
Chi-Squared Tests
  Value df p
Χ² 1390.740 7 < .001
N 3160  
Note.  Continuity correction is available only for 2x2 tables.
Nominal
  Value
Contingency coefficient 0.553
Phi-coefficient NaN
Cramer's V 0.663
Lambda (rows) 0.321
Lambda (columns) 0.114
Lambda (symmetric) 0.217
ᵃ Phi coefficient is only available for 2 by 2 contingency Tables

The chi-square test is highly significant, χ2(7) = 1390.74, p < .001. This indicates that the profile of yes and no responses differed across the professions. Looking at the standardized residuals, these are significant in most cells with a few exceptions: physicians, lawyers and school teachers saying ‘yes’. Within the other cells all of the standardized residuals are much higher than 1.96. Again, we can look at the direction of these residuals (i.e., whether they are positive or negative).


For labourers, housewives, school teachers and musicians the residual for ‘no’ was positive but for ‘yes’ was negative; these are, therefore, people who responded more than we would expect that they were not happy as Black Americans and less than expected that they were happy as Black Americans. In other words, they were generally unhappier than expected, compared to their Black American peers.


The remaining professions (college students, physicians, preachers and lawyers) show the opposite pattern: the residual for ‘no’ was negative but for ‘yes’ was positive; these are, therefore, people who responded less than we would expect that they were not happy as Black Americans and more than expected that they were happy as Black Americans. In other words, they were generally happier than expected, compared to their Black American peers.


Essentially, the former group are in low-paid jobs in which conditions would have been very hard (especially in the social context of the time). The latter group are in much more respected (and probably better-paid) professions. Therefore, the responses to this question could say more about the professions of the people asked than their views of being Black Americans.

Should Black Americans be Happy?

We run this analysis in exactly the same way except that we now have to swap the variable you_happy to should_be_happy.

Contingency Tables
response
profession   Yes No Total
College students Count 141.000 1810.000 1951.000
Expected count 680.234 1270.766 1951.000
% within row 7.227 % 92.773 % 100.000 %
% within column 11.919 % 81.900 % 57.501 %
% of total 4.156 % 53.345 % 57.501 %
Standardized residuals -39.296 39.296
Unskilled laborers Count 396.000 104.000 500.000
Expected count 174.330 325.670 500.000
% within row 79.200 % 20.800 % 100.000 %
% within column 33.474 % 4.706 % 14.736 %
% of total 11.671 % 3.065 % 14.736 %
Standardized residuals 22.529 -22.529
Preachers Count 264.000 36.000 300.000
Expected count 104.598 195.402 300.000
% within row 88.000 % 12.000 % 100.000 %
% within column 22.316 % 1.629 % 8.842 %
% of total 7.781 % 1.061 % 8.842 %
Standardized residuals 20.227 -20.227
Physicians Count 174.000 36.000 210.000
Expected count 73.218 136.782 210.000
% within row 82.857 % 17.143 % 100.000 %
% within column 14.708 % 1.629 % 6.189 %
% of total 5.128 % 1.061 % 6.189 %
Standardized residuals 15.067 -15.067
Housewives Count 90.000 120.000 210.000
Expected count 73.218 136.782 210.000
% within row 42.857 % 57.143 % 100.000 %
% within column 7.608 % 5.430 % 6.189 %
% of total 2.653 % 3.537 % 6.189 %
Standardized residuals 2.509 -2.509
School teachers Count 75.000 33.000 108.000
Expected count 37.655 70.345 108.000
% within row 69.444 % 30.556 % 100.000 %
% within column 6.340 % 1.493 % 3.183 %
% of total 2.210 % 0.973 % 3.183 %
Standardized residuals 7.664 -7.664
Lawyers Count 7.000 57.000 64.000
Expected count 22.314 41.686 64.000
% within row 10.938 % 89.063 % 100.000 %
% within column 0.592 % 2.579 % 1.886 %
% of total 0.206 % 1.680 % 1.886 %
Standardized residuals -4.055 4.055
Musician Count 36.000 14.000 50.000
Expected count 17.433 32.567 50.000
% within row 72.000 % 28.000 % 100.000 %
% within column 3.043 % 0.633 % 1.474 %
% of total 1.061 % 0.413 % 1.474 %
Standardized residuals 5.551 -5.551
Total Count 1183.000 2210.000 3393.000
Expected count 1183.000 2210.000 3393.000
% within row 34.866 % 65.134 % 100.000 %
% within column 100.000 % 100.000 % 100.000 %
% of total 34.866 % 65.134 % 100.000 %
Chi-Squared Tests
  Value df p
Χ² 1784.226 7 < .001
N 3393  
Note.  Continuity correction is available only for 2x2 tables.
Nominal
  Value
Contingency coefficient 0.587
Phi-coefficient NaN
Cramer's V 0.725
Lambda (rows) 0.610
Lambda (columns) 0.177
Lambda (symmetric) 0.394
ᵃ Phi coefficient is only available for 2 by 2 contingency Tables

The chi-square test is highly significant, χ2(7) = 1784.23, p < .001. This indicates that the profile of yes and no responses differed across the professions. Looking at the standardized residuals, these are nearly all significant. Again, we can look at the direction of these residuals (i.e., whether they are positive or negative).


For college students and lawyers the residual for ‘no’ was positive but for ‘yes’ was negative; these are, therefore, people who responded more than we would expect that they thought that Black Americans should not be happy and less than expected that they thought Black Americans should be happy.


The remaining professions show the opposite pattern: the residual for ‘no’ was negative but for ‘yes’ was positive; these are, therefore, people who responded less than we would expect that they did not think that Black Americans should be happy and more than expected that they thought that Black Americans should be happy.


What is interesting here and in the first question is that college students and lawyers are in vocations in which they are expected to be critical about the world. Lawyers may well have defended Black Americans who had been the subject of injustice and discrimination or racial abuse, and college students would likely be applying their critically trained minds to the immense social injustice that prevailed at the time. Therefore, these groups can see that their racial group should not be happy and should strive for the equitable and just society to which they are entitled. People in the other professions perhaps adopt a different social comparison.


It’s also possible for this final question that the groups interpreted the question differently: perhaps the lawyers and students interpreted the question as ‘should they be happy given the political and social conditions of the time?’, while the others interpreted the question as ‘do they deserve happiness?’


It might seem strange to have picked a piece of research from so long ago to illustrate the chi-square test, but what I wanted to demonstrate is that simple research can sometimes be incredibly illuminating. This study asked three simple questions, yet the data are fascinating. It raised further hypotheses that could be tested, it unearthed very different views in different professions, and it illuminated very important social and psychological issues. There are others studies that sometimes use the most elegant paradigms and the highly complex methodologies, but the questions they address are meaningless for the real world. They miss the big picture. Albert Beckham was a remarkable man, trying to understand important and big real-world issues that mattered to hundreds of thousands of people.