04 Correlation in SPSS – SPSS for Beginners

00:09:52
https://www.youtube.com/watch?v=6EH5DSaCF_8

Summary

TLDRIn this introductory video tutorial from the RStats Institute at Missouri State University, viewers learn how to perform simple analyses using SPSS, focusing on calculating correlations, specifically Pearson's r. Pearson's r describes the relationship between two variables, ranging from -1 to +1, where 0 indicates no relationship. The video delves into how to set up data for correlation, perform the analysis, interpret correlation matrices, and understand significance levels. A significant portion of the tutorial is dedicated to the relationship between height and weight of a sample, demonstrating how correlations are calculated and interpreted. Additionally, the importance of sample size for statistical significance, the handling of missing data in SPSS, and how to visualize data relationships through scatter plots using the chart builder are covered. Advanced topics briefly mentioned include nominal variable correlation and regression analysis. This instructional guide emphasizes practical steps and commands in SPSS, enriched with explanations of correlation concepts.

Takeaways

  • 🔍 Pearson's r explains relationships between two variables.
  • 📊 Set up data pairs correctly before analyzing.
  • 🚫 Missing values are ignored in SPSS correlation.
  • ⚠️ Significance levels help determine statistical relevance.
  • 🧮 Larger sample sizes yield more significant results.
  • 📈 Scatter plots visualize correlations effectively.
  • 🔄 Each variable correlates perfectly with itself.
  • 💬 Off-diagonal matrix values show variable relationships.
  • 🔢 Nominal variables can have point biserial correlations.
  • 📉 Regression analysis is related to correlation.

Timeline

  • 00:00:00 - 00:09:52

    In the fourth video of SPSS for beginners from RStats Institute at Missouri State University, we focus on learning the basics of doing correlation analyses. Building from our knowledge of descriptive statistics and graphs, the current focus is on Pearson's r correlation, which measures the relationship between two variables, such as height and weight. The video stresses the importance of correctly pairing data for accurate analysis and demonstrates how to calculate correlations using SPSS, specifically highlighting the process for setting up the analysis and interpreting the resulting correlation matrix. The discussion includes interpreting significance levels and acknowledging statistical significance, which is more likely with larger sample sizes. The utility of using SPSS to analyze correlations involving more than two variables is also showcased, along with the explanation of point biserial correlation when a nominal variable like gender is included. Lastly, the video introduces using scatter plots for visual representation of data relationships and mentions further exploration of correlation via additional RStats Institute resources.

Mind Map

Video Q&A

  • What is the main focus of this SPSS tutorial video?

    The video focuses on teaching beginners how to perform correlation analysis using SPSS, specifically Pearson's correlation.

  • What is Pearson's correlation?

    Pearson's correlation measures the relationship between two variables, ranging from -1 to +1, with 0 indicating no relationship.

  • Why is sample size important in correlation analysis?

    A larger sample size increases the likelihood of finding statistically significant correlations.

  • How does SPSS treat missing values in correlation analysis?

    SPSS ignores cases with missing values during correlation analysis.

  • What is a correlation matrix?

    A correlation matrix is a table showing correlation coefficients for combinations of variables.

  • What does a significant correlation mean?

    A significant correlation, usually indicated by significance levels smaller than .05, shows the relationship is statistically different from 0.

  • How can you visualize correlations in SPSS?

    Correlations can be visualized using scatter plots created through SPSS's chart builder.

  • Can nominal variables be correlated in SPSS?

    Yes, nominal variables can be correlated as point biserial correlations if they have two levels.

  • What are off diagonal correlations in a matrix?

    Off diagonal correlations in a matrix show the correlation coefficients between different variables.

  • What additional analysis related to correlation is mentioned?

    The video mentions regression analysis, which involves predicting variables.

View more video summaries

Get instant access to free YouTube video summaries powered by AI!
Subtitles
en
Auto Scroll:
  • 00:00:07
    Welcome to the fourth video in SPSS for beginners from the RStats Institute at Missouri State University.
  • 00:00:15
    Now that we have learned how to examine each variable using descriptive statistics and graphs,
  • 00:00:21
    I'm going to show you how to do some simple analyses. So this video will show you the basics of doing correlation.
  • 00:00:28
    When you're ready to do a correlation for real,
  • 00:00:31
    watch the other are stats Institute videos to learn more about the theory the analysis and
  • 00:00:38
    how to write up your findings in APA style.
  • 00:00:49
    We're still using the same
  • 00:00:50
    SPSS data set that we created in the first video, however, I deleted the z-score variables that we created last time.
  • 00:00:58
    Now I'm going to show you how to calculate
  • 00:01:01
    correlations in
  • 00:01:03
    SPSS
  • 00:01:05
    The correlation that we are doing is called Pearson's r.
  • 00:01:10
    A Pearson's correlation describes the relationship between two variables.
  • 00:01:16
    Pearson's r ranges between -1 and +1.
  • 00:01:21
    0 indicates no relationship at all.
  • 00:01:24
    The closer that the correlation is to either +1 or -1, the stronger the relationship
  • 00:01:31
    between the variables.
  • 00:01:34
    We are interested in the relationship between height and weight.
  • 00:01:39
    Notice how the data have already been set up. Each person has a pair of scores.
  • 00:01:45
    Your height should be paired with your weight, it makes no sense to pair your height with my weight.
  • 00:01:52
    So it's very important that each pair stays together
  • 00:01:56
    We have 10 pairs of scores. Our sample size is 10. Each pair counts as one case.
  • 00:02:04
    So remember that we have two people without height and weight scores.
  • 00:02:09
    They are not going to be included in this analysis.
  • 00:02:13
    In fact, SPSS will simply ignore those cases with missing values. So let's do a correlation.
  • 00:02:20
    Go to Analyze
  • 00:02:23
    Correlate
  • 00:02:24
    A Pearson's r correlates two variables, so choose Bivariate...
  • 00:02:31
    As before all of our variables are here on the left. The two that we want to correlate are height and weight.
  • 00:02:37
    So we need at least two
  • 00:02:39
    variables.When you move over the first, the "OK" is still not available until you move over the second.
  • 00:02:46
    And we could add additional variables, but each would be correlated only two at a time.
  • 00:02:53
    We have some additional options here as well. We could calculate Kendall's tau or
  • 00:02:59
    Spearman's Rho if we had different data, but for now let's just stick with Pearson's r.
  • 00:03:06
    SPSS assumes that we want two tailed significance tests and
  • 00:03:10
    that we want to flag significant correlations.
  • 00:03:14
    We haven't talked about significance tests yet,
  • 00:03:16
    so for now just know that significance tests tell us something important about the variables. In this case, our
  • 00:03:24
    correlation is statistically significantly different than 0. If it is,
  • 00:03:29
    SPSS will flag it. All of the default settings are just the way we want them, so click OK to run the analysis.
  • 00:03:37
    The box that we see is called a "correlation matrix."
  • 00:03:41
    The correlation matrix shows the correlation coefficient for every combination of variables.
  • 00:03:48
    So we have two rows: one for height, one for weight.
  • 00:03:52
    And we have two columns: one for height, one for weight.
  • 00:03:56
    Where each row and column intersect, we see the correlation coefficient between those two variables.
  • 00:04:05
    So in this quadrant of the matrix we see the correlation coefficient between height and
  • 00:04:11
    itself.
  • 00:04:13
    No surprise. It's 1. It's a perfect correlation.
  • 00:04:17
    We see another perfect correlation down here on the lower right which is the correlation between weight and itself.
  • 00:04:25
    SPSS will compare every combination of variables
  • 00:04:29
    including each variable and itself.
  • 00:04:32
    Now these correlations are not very interesting because we already know that
  • 00:04:38
    every variable will always correlate with itself at a +1, no matter the variable.
  • 00:04:45
    The interesting correlations are in these off diagonals.
  • 00:04:50
    The top left box is the correlation coefficient.
  • 00:04:53
    It will always be between +1 and -1.
  • 00:04:58
    Below that is the significance level.
  • 00:05:01
    Significance levels smaller than .05 are statistically significant.
  • 00:05:06
    Below that is the N, or the sample size, which is our 10 pairs of scores. So let's look at this coefficient.
  • 00:05:16
    Notice that the off diagonal correlations are the same because height correlates with weight exactly the same as weight
  • 00:05:22
    correlates with height. In this case it's a .574 which is pretty strong,
  • 00:05:29
    but not significant because the sample size of 10 is pretty small.
  • 00:05:35
    You are always more likely to find significance with larger sample sizes.
  • 00:05:40
    If this correlation was significant, we would see some asterisks next to the coefficient.
  • 00:05:47
    So as I mentioned, you can correlate more than two variables at a time,
  • 00:05:51
    and you could even use correlation with nominal variables as long as it only has two levels. In fact, let me show you.
  • 00:05:59
    Go to Analyze
  • 00:06:01
    Correlate
  • 00:06:03
    Bivariate
  • 00:06:05
    All we're going to do is throw in a third variable, Gender, and this is actually called a point biserial correlation,
  • 00:06:14
    more on all of that later. For now, just click OK.
  • 00:06:19
    We get another correlation matrix, but this time it's bigger. It has three rows and three columns.
  • 00:06:26
    The correlations between height and weight are exactly the same as before,
  • 00:06:31
    but we also have correlations with gender.
  • 00:06:35
    Because the correlations are negative, as one variable goes up the other goes down.
  • 00:06:41
    Remember that we coded males as 1, females as 2. So the 1 is smaller. We see this negative
  • 00:06:48
    correlation, the smaller numbers are associated with larger values. So basically the males were taller and weighed more.
  • 00:06:58
    And here we also see a significant correlation that's been flagged.
  • 00:07:03
    The biserial correlation between weight and gender has two asterisks, so what does that mean?
  • 00:07:11
    We can see that this correlation is significant at the .01 level. In fact, the p-value is .009.
  • 00:07:21
    So there' is a statistically significant relationship between weight and gender.
  • 00:07:26
    So there's one more thing that I want to show you with correlations,
  • 00:07:29
    and that is how to make a picture of them. The picture is called a scatter plot,
  • 00:07:35
    and it is created using a new tool called the chart builder. And here's how we do it.
  • 00:07:42
    Instead of the Analyze menu, we're going to use the Graphs menu. So go to Graphs
  • 00:07:49
    Chart Builder
  • 00:07:51
    We will learn more about the chart builder later when we learn about graphing.
  • 00:07:56
    For now, let's just have some fun and make a scatter plot.
  • 00:08:01
    Start by clicking on the word Scatter/Dot in the gallery.
  • 00:08:07
    Now we see our eight options. If you hover your cursor above them, SPSS will tell you what they are.
  • 00:08:16
    We want this first option: Simple Scatter
  • 00:08:22
    Click and drag it into the blank area known as the canvas.
  • 00:08:27
    You will see that we now have two drop zones: one for the x axis and one for the y axis.
  • 00:08:33
    So let's use height to predict weight.
  • 00:08:37
    Drag height to the x axis drop zone
  • 00:08:42
    weight to the y-axis drop zone.
  • 00:08:46
    And that is all you have to do. Click OK.
  • 00:08:51
    And there is our scatter plot of all 10 of the pairs of scores.
  • 00:08:57
    There is much more that we could do with correlation, so for instance, we could format the scatter plot in APA style.
  • 00:09:06
    We could do other types of correlations.
  • 00:09:09
    We could even use some variables to predict other variables using a technique called
  • 00:09:15
    regression
  • 00:09:16
    To learn more about correlation, scatter plots, simple regression, and multiple regression check out these other videos
  • 00:09:24
    from RStats Instiutue.
  • 00:09:27
    Correlations are about relationships between variables,
  • 00:09:31
    but we might also be interested in
  • 00:09:35
    differences between variables. So next we're going to learn about t-tests.
Tags
  • SPSS
  • Pearson's correlation
  • correlation analysis
  • statistics
  • scatter plot
  • regression
  • data visualization
  • RStats Institute